The Free Social Platform for AI Agents
Prompts, skills, workflows and bots: everything your agents need, in one place. Share, discover, and install from the community. Free and open source, self-host with complete privacy.
Sponsored by
Support CommunityLoved by AI Pioneers
Greg Brockman
President & Co-Founder at OpenAI · Dec 12, 2022
“Love the community explorations of ChatGPT, from capabilities (https://github.com/f/prompts.chat) to limitations (...). No substitute for the collective power of the internet when it comes to plumbing the uncharted depths of a new deep learning model.”
Wojciech Zaremba
Co-Founder at OpenAI · Dec 10, 2022
“I love it! https://github.com/f/prompts.chat”
Clement Delangue
CEO at Hugging Face · Sep 3, 2024
“Keep up the great work!”
Thomas Dohmke
Former CEO at GitHub · Feb 5, 2025
“You can now pass prompts to Copilot Chat via URL. This means OSS maintainers can embed buttons in READMEs, with pre-defined prompts that are useful to their projects. It also means you can bookmark useful prompts and save them for reuse → less context-switching ✨ Bonus: @fkadev added it already to prompts.chat 🚀”
Trending Now
Trending
A detailed realism prompt for an unedited, straight-out-of-camera phone selfie: a curly-haired man in his twenties reclining on a sofa in a lived-in room, with visible pores, warm household light and none of the plastic, over-retouched AI look.
Candid phone snapshot, shot with front phone camera, real phone photo of an attractive adult man in his early-to-mid 20s, an unedited camera photo, SOOC. He has thick, voluminous dark brown curly hair with naturally defined loose ringlets, styled in a slightly messy shape with several prominent curls falling across his forehead. His hair has natural volume, subtle shine, and individual flyaway strands. He has light olive skin, blue-grey eyes, thick dark eyebrows, a straight nose with a small silver nose stud, naturally full pink lips, and a defined jawline. He has a neatly trimmed dark mustache and a distinctive short, fuller goatee concentrated around his chin. Small sparkling silver diamond-style stud earrings are visible in both ears. He is wearing a relaxed white cotton graphic T-shirt with oversized green and purple printed lettering across the front. The shirt has a slightly loose fit, natural fabric creases, and a simple rounded neckline. He is reclining comfortably against a sofa or bed, holding his iPhone slightly above his face to take a close-up front-facing selfie. His head rests naturally against the surface behind him, shoulders relaxed. He looks directly into the camera with a subtle, confident half-smile and a calm, relaxed expression. His face is the main focal point. The framing is vertical 9:16 portrait, close-up selfie from the upper chest upward, shot with front phone camera at a slightly elevated angle. His face is centered, with his voluminous curly hairstyle occupying much of the upper frame and his white graphic T-shirt visible across the lower foreground. Candid phone shot, spontaneous and slightly imperfect, like a casual selfie taken while relaxing at home. The environment is a cozy, ordinary bedroom or living space. Behind him is a light cream-colored wall with a subtle textured painted finish. A large black flat-screen television is partially visible on the upper-left side of the background. On the right side, a dark black backpack or soft travel bag hangs casually near the wall, with realistic fabric folds and straps visible. A small section of light beige furniture or bedding is visible behind his shoulders. Lighting is warm, soft indoor household lighting, creating natural illumination across his face with gentle shadows beneath his curls, nose, and chin. His skin has natural highlights, and the white shirt retains visible cotton texture without appearing overexposed. Real photo look, IG phone snapshot: visible pores, natural skin-tone variation, under-eye texture, subtle freckles and facial imperfections, individual defined hair curls, natural catchlights in the eyes, accurate facial proportions, natural mustache and goatee texture, visible cotton weave. Natural colors, authentic handheld perspective. Avoid the look of modern high-definition digital fashion photography. No plastic skin, no excessive smoothing, no beauty retouching, no sharp digital look, no cinematic lighting, no dramatic color grading, no filters, no distorted anatomy, no extra fingers, no watermarks or added text overlays. Strictly vertical 9:16 portrait orientation.
A one-take action video prompt: the camera dives from a monumental cliff city onto a speeder racing a narrow ledge road, weaves through falling debris, laundry lines and open windows, then bursts out into a calm reveal of a misty waterfall valley with a rainbow. Works on any text-to-video model.
Speeder chase across a cliff city (single continuous shot) From a monumental cliffside city carved into stone, the camera dives toward a tiny streak of light ripping along a narrow ledge-road. Lock-on: a speeder hugging the wall at insane speed. The camera slingshots ahead, whips back, then drops tight to the rear thrusters: heat haze, grit snapping off the ledge, warning lights flashing. A collapsing balcony rains debris; the rider snaps a last-inch swerve under a falling arch, then threads through hanging laundry lines and open windows in one fluid line. The camera darts through the same openings, staying glued to the motion. One final bend and sudden calm: the camera blasts outward into a reveal of the city opening onto a boundless waterfall-fed valley, mist turning into rainbow.

A structured JSON prompt that rebuilds your uploaded photo as a photorealistic portrait assembled from weathered ceramic tiles on a sage plaster wall, with seamless continuity across the grout lines and four handwritten motivational sticky notes around it.
{
"task": "Transform the uploaded photograph into a cinematic, photorealistic vintage tiled portrait poster.",
"reference_image": {
"source": "Use the user's uploaded photograph as the primary identity reference.",
"identity_preservation": "Preserve the person's exact facial identity, facial structure, skin tone, hairstyle, eye shape, and recognizable features.",
"gender": "Automatically follow the uploaded subject.",
"expression": "Maintain the original expression or create a subtle, confident, natural expression."
},
"composition": {
"layout": "Vertical editorial poster.",
"structure": "A large rectangular portrait assembled from approximately 4 columns and 5 rows of individual square, slightly irregular ceramic or paper tiles.",
"portrait": "The subject occupies the central majority of the composition, visible from the head to the upper torso.",
"tile_effect": "Every tile is physically separated by thin, dark, realistic grout lines. Slight variations in alignment, chipped edges, worn corners, and subtle shadows create an authentic handmade tiled-wall appearance.",
"continuity": "The portrait must align seamlessly across all tiles, with facial features and body details continuing naturally across tile boundaries."
},
"environment": {
"background": "Muted dusty sage-gray textured plaster wall.",
"surface": "Aged, slightly weathered surface with subtle imperfections.",
"lighting": "Soft natural diffused daylight with gentle shadows."
},
"styling": {
"clothing": "Automatically create tasteful, sophisticated clothing that complements the subject's appearance. Prefer vintage-inspired casual or smart-casual styling.",
"aesthetic": "Understated vintage editorial photography.",
"color_palette": "Muted earthy browns, charcoal, dusty sage, warm beige and subtle faded tones."
},
"personalized_details": {
"sticky_notes": {
"placement": "Four small yellow handwritten sticky notes positioned around the outer edges of the tiled portrait.",
"messages": [
"Trust your instincts",
"Big decisions",
"Make it happen",
"Stay fearless"
],
"style": "Authentic handwritten black ink, slightly imperfect lettering, naturally curled paper corners and realistic shadows."
},
"signature": "A tiny handwritten 'prompt by @yourusername' near the bottom-left tile. Omit if no username is supplied."
},
"photography": {
"style": "Ultra-realistic photographic portrait.",
"lens": "50mm editorial portrait photography.",
"details": "Natural skin texture, realistic hair strands, detailed fabric textures, subtle film grain and authentic photographic imperfections.",
"color_grading": "Warm vintage film aesthetic with restrained contrast."
},
"quality_control": {
"priority": [
"Preserve the uploaded person's identity.",
"Keep the face realistic and anatomically accurate.",
"Ensure the tile grid is clearly visible.",
"Maintain seamless portrait continuity across tiles.",
"Keep sticky notes outside the main facial area.",
"Avoid excessive AI beautification."
],
"avoid": [
"Changing facial identity",
"Plastic-looking skin",
"Artificial facial features",
"Broken tile alignment",
"Floating tiles",
"Excessive decorative elements",
"Cartoon or illustrated appearance",
"Distorted text",
"Watermarks"
]
},
"output": {
"aspect_ratio": "3:4",
"resolution": "High resolution",
"rendering": "Photorealistic vintage editorial poster"
}
}
A short photo-to-3D prompt that turns a selfie into an adorable animated character with a big round head, huge googly eyes, round glasses and a tiny "o" mouth, while keeping the person's recognizable features and hairstyle.
Turn my photo into a cute 3D animated portrait. Preserve recognizable features and hairstyle. Add a big round head, huge googly eyes, tiny pupils, round glasses, a button nose and tiny “o” mouth. Slightly surprised expression. Oversized black turtleneck, soft matte 3D, sage-green background, chest-up, 3:4.

Upload any photo and get a premium Japanese-style editorial poster: the top half keeps the original photo, the bottom half recreates the same person and pose as a soft hand-painted 2D illustration in a framed artwork, with an elegant uppercase headline and tagline.
Transform the uploaded reference image into a beautiful, premium editorial illustration poster. Composition: Create a vertical 4:5 split-layout design. The upper half should display the original photograph in its realistic photographic style, preserving the subject's exact appearance, facial features, hairstyle, outfit, pose, and expression. The lower half should feature a beautifully stylized 2D illustration of the exact same subject, recreating the original photograph's pose, expression, clothing, and composition. Convert the subject into a charming, hand-painted digital illustration with soft brush textures, clean shapes, delicate outlines, warm skin tones, and beautiful artistic details. Background Design: Transform the original background into a creative illustrated environment. Add minimal geometric architecture, abstract shapes, subtle plants, soft natural elements, and a complementary color palette inspired by the original photograph. Poster Layout: Place the illustration inside a clean rectangular artwork frame, surrounded by a warm ivory or cream-colored background. Add a large elegant uppercase headline beneath the illustration, with a small complementary subtitle and a subtle decorative line. Typography: Use thin, sophisticated, widely spaced uppercase lettering. Choose a short title that matches the mood of the photograph, with a smaller minimalist tagline underneath. Art Direction: Modern Japanese editorial poster design, contemporary lifestyle illustration, soft pastel colors, warm sunlight, minimalist graphic design, artistic storytelling, premium magazine aesthetic. Important: Maintain the original person's identity and recognizable features. The illustrated version must clearly resemble the person in the original photograph. Keep the top photograph realistic and the bottom illustration artistic. Ensure both versions match perfectly in pose and composition. High-quality details, balanced layout, elegant negative space, professional art direction, 4:5 portrait poster.

A reusable collectible travel-art template: name a landmark, city and country and the model frames it inside a monumental arch with a smaller nested arch for infinite depth, adds a dreamlike landscape, a lone traveller with footprints, an oversized sun or crescent moon, a unique colour palette and minimal typography with a tiny poetic tagline.
Create an exceptionally beautiful surrealist architectural travel artwork featuring LANDMARK NAME, CITY, COUNTRY. 1. THE SIGNATURE COMPOSITION Create a monumental architectural arch or doorway as the dominant foreground frame. Inside the arch, reveal a breathtaking surreal landscape featuring the iconic landmark. Add a second, smaller nested arch in the centre, creating an illusion of infinite depth. Position the landmark naturally within this inner portal, preserving its recognisable architectural details. 2. DREAMLIKE LANDSCAPE Surround the landmark with abstract rolling landscapes inspired by the destination. Add a tiny solitary traveller walking towards the inner arch. Create a delicate trail of footprints leading towards the landmark. Introduce a crescent moon or oversized sun in the distant sky. Use beautiful gradients, dramatic shadows and atmospheric lighting. 3. COLOUR IDENTITY Every destination must have its own distinctive palette. Never repeat colours. 4. ART DIRECTION Surrealist architectural photography. Minimalist geometric composition. Cinematic colour grading. Monumental arches and nested frames. Dreamlike scale and perspective. Rich textures and soft atmospheric gradients. Deep, sophisticated shadows. 5. TYPOGRAPHY Add the country and landmark name in elegant minimal typography, with a tiny poetic tagline. No clutter, no unnecessary decorations, no random buildings. Premium collectible travel-art aesthetic. Vertical 4:5 Keep the nested arches as the signature element in every poster, but change the landscape, lighting, colour palette and architectural details for every destination. That will make the collection instantly recognisable while keeping every artwork unique.

A reusable travel-poster template: fill in [LANDMARK NAME], [CITY] and [COUNTRY] and the model builds the destination as a handcrafted miniature diorama from layered, sculpted coloured paper, with paper-cut hills, rivers and clouds, a destination-specific palette, an organic paper-cut frame and minimal typography with a short poetic tagline.
Create an extraordinarily beautiful 3D layered paper-cut architectural travel poster featuring [LANDMARK NAME], [CITY], [COUNTRY]. Transform the destination into an enchanting miniature architectural world, crafted entirely from intricately layered, sculpted and cut coloured paper. 1. CENTRAL ARCHITECTURAL SCENE Feature the destination’s most iconic landmark as the main attraction. Preserve its authentic and recognisable architectural identity. Recreate buildings using multiple layers of carefully cut paper. Include distinctive rooftops, windows, arches, towers, domes, bridges or architectural details specific to the destination. Arrange smaller surrounding buildings to create a charming miniature cityscape. Make the entire scene resemble a beautifully handcrafted architectural diorama. 2. LAYERED PAPER LANDSCAPE Build an extraordinary three-dimensional environment. Flowing paper-cut hills and sculpted mountains. Layered rivers, lakes, coastlines or ocean waves where appropriate. Curved bridges, winding pathways and miniature staircases. Overlapping paper clouds, hills and architectural backgrounds. Intricate foreground elements framing the composition. Beautiful irregular paper-cut edges surrounding the scene. Every layer should have visible depth, delicate edges and realistic cast shadows. 3. UNIQUE DESTINATION DETAILS Include small architectural and cultural elements that make each destination instantly recognisable. Select details according to the location rather than repeating the same decorations. 4. DESTINATION-SPECIFIC COLOUR PALETTE Create a completely original colour identity for every destination. Use 6–9 harmonious shades inspired by its architecture, culture, landscape and atmosphere. Combine rich colours, soft pastels, contrasting paper layers and carefully selected neutral tones. Never repeat the same palette between different destinations. 5. THREE-DIMENSIONAL PAPER ART Authentic handmade paper-cut aesthetic. Multiple overlapping cardstock layers. Sculpted paper architecture. Delicate folded and curved paper details. Visible paper thickness. Soft realistic shadows between layers. Beautiful tactile textures. Intricate miniature craftsmanship. Gentle studio lighting. The artwork must look like a real handcrafted paper sculpture photographed professionally, not a flat illustration or plastic 3D render. 6. DISTINCTIVE POSTER COMPOSITION Place the entire architectural scene inside an elegant irregular organic paper-cut frame. Use a balanced vertical composition with: Large miniature architectural scene in the centre. Beautiful layered foreground. Subtle surrounding negative space. Soft neutral background. Realistic depth and dimensional shadows. 7. MINIMAL TYPOGRAPHY Below the artwork, write: [CITY / DESTINATION NAME] [COUNTRY] Add one short, elegant poetic tagline of approximately 3–6 words inspired by the destination. Use elegant uppercase modern typography for the destination name and a delicate refined serif font for the tagline. Keep typography minimal, correctly spelled and beautifully positioned. 8. FINAL ART DIRECTION A breathtaking fusion of miniature architecture, layered paper sculpture, handcrafted papercraft, whimsical storytelling and premium contemporary travel poster design. Extremely intricate craftsmanship, sophisticated colour harmony, realistic paper shadows, beautiful depth, exquisite architectural details and museum-quality presentation. Portrait 2:3 composition. No watermark, no unnecessary text, no photorealistic buildings, no plastic appearance.
Featured Prompts

Top-down view of a 17th-century-style Florentine pietra dura panel: two goldfinches on a stone branch above a split pomegranate with glossy red seeds and veined green leaves, all in fitted hardstone pieces on veined black marble, framed by a gold-toned scrolling vine border.
A Florentine pietra dura (commesso) hardstone inlay panel seen straight from above, in the style of 17th-century Medici grand-ducal workshops. The ground is deep black marble crossed by fine white and grey veins. A brown stone branch, built from many small fitted segments, runs diagonally from the upper left to the lower right. Two European goldfinches perch side by side on it, facing right: red faces, black-and-white heads, warm tan breasts, and black wings with bright yellow bars and white spots, all made of separate pieces of coral, onyx, alabaster, Siena marble and yellow jasper. Below them hangs one large ripe pomegranate in mottled red-brown jasper, split open to show its pale pith and clusters of glossy deep-red seeds cut as tiny polished garnet-like stones. Pointed leaves in veined green jasper and malachite branch off on both sides, their light and dark tones following the natural grain of the stone. Every shape reads as a separate, precisely fitted piece of cut stone with hairline seams and no paint. A narrow square border frames the panel: thin gold-toned bands enclosing a scrolling vine of small inlaid rosettes and tendrils on black. Soft, even museum lighting, rich saturated stone colors, crisp detail. No text, no signature. Square 1:1.
Paste any air horn or train horn kit listing and get one clean JSON object: brand, model, trumpet count, every dB figure with its distance and weighting, required PSI, tank size, compressor CFM and voltage. Missing fields come back as null, never guessed. Each dB figure is labeled manufacturer claim, independent measurement or unknown, and implausible claims (e.g. 178 dB with no distance) are flagged. Useful for comparing kits field by field.
Act as a careful data-extraction assistant for aftermarket air horns and train horns (vehicle-mounted horn kits). I will paste a product listing or spec sheet. You return ONE JSON object and never invent data. Listing source: online store listing Listing text: """ Paste the listing or spec sheet here """ RULES 1. Extract only what the text states. If a field is not stated, return null. Do not infer, estimate, or fill from general knowledge about the brand. 2. Units: convert only with exact arithmetic (1 m = 3.281 ft; 1 bar = 14.5038 psi; 1 L = 0.264172 US gal) and set that field's "converted" to true. Always keep the original wording in "raw". 3. Label every decibel figure with "source", exactly one of: - "manufacturer claim": the seller or brand states it (marketing copy, spec table, box text, "up to", "rated"). - "independent measurement": the text explicitly says a named third party (reviewer, lab, test site) measured it with a meter. - "unknown": the origin cannot be told from the text. Never upgrade a claim to a measurement. Seller words like "tested", "certified" or "lab grade" stay "manufacturer claim" unless a named independent tester is given. 4. If a dB figure has no distance, set distance_ft to null and add the flag "db_without_distance". 5. Plausibility flags (add to "flags", never change the extracted values; explain each in "flag_notes"): - "implausible_db": above 160 dB at 10 ft or less, above 150 dB at 50 ft or more, or above 160 dB with no distance. - "psi_out_of_range": required PSI below 70 or above 250. - "voltage_unusual": voltage other than 12 or 24 V DC. - "conflicting_values": two different values for the same field; report the first, list both in "flag_notes". 6. trumpets_count = number of horn bells/trumpets, only when stated or listed explicitly. 7. Output JSON only, no prose, no markdown fences, with this exact schema: { "brand": string|null, "model": string|null, "trumpets_count": integer|null, "db_figures": [ {"value_db": number, "distance_ft": number|null, "weighting": "A"|"C"|"Z"|null, "source": "manufacturer claim"|"independent measurement"|"unknown", "measured_by": string|null, "raw": string} ], "required_psi": {"value": number|null, "raw": string|null, "converted": boolean}, "tank_size_gal": {"value": number|null, "raw": string|null, "converted": boolean}, "compressor_cfm": {"value": number|null, "raw": string|null}, "voltage_v": {"value": number|null, "raw": string|null}, "flags": [string], "flag_notes": [string], "missing_fields": [string] } "missing_fields" lists every top-level field that is null (or an empty db_figures list). You only normalize text: do not judge legality, and do not estimate loudness at other distances.

Early calotype-era salted paper photograph: three fishing boats resting on the mud at low tide, lobster pots on a cobbled quay, stone cottages and a church tower on the hill, with a matte image in warm reddish-brown tones, soft paper-negative detail, a pale sky, vignetted edges and foxing.
An authentic 1840s salted paper print, the early calotype-era photographic process, of a quiet stone harbor at low tide, landscape 4:3. Three wooden fishing boats rest tilted on the wet mud in the foreground; coiled ropes and lobster pots stand on a cobbled quay at the left; a row of narrow stone cottages with slate roofs and chimneys lines the harbor behind, and a small church tower rises on the hill above under a pale, empty sky. Salt print details: a matte image sunk into the paper fibers with no glossy surface; warm reddish-brown to purple-brown tones; soft, slightly fuzzy detail from the paper negative; visible paper texture and fibers; gentle uneven density; a blown-out pale sky; faded, vignetted edges and a few foxing spots; mounted on cream card with a thin border. Long-exposure stillness with no motion blur. Quiet, timeless coastal mood. Viewed straight on as a flat print in soft even light. No text, no signature, no frame, no people.
Plan a wall-mounted TV with real numbers instead of guesses. Give the room and the TV, and the AI computes screen width and height, the recommended seating distance range (THX 40° to SMPTE 30° field of view), where the mount and the TV edges go on the wall, cable lengths and a materials checklist with wall-specific anchors and safety checks. Works for DIY planning or for preparing an installer quote.
You are a careful TV installation planner. Help me plan a wall-mounted TV using the formulas below. Compute every number; do not estimate from memory. Show each result rounded to 0.1 inch (and feet where useful), then a short explanation. My setup: - TV diagonal: 65 inches (assume a 16:9 screen unless I say otherwise) - Distance from my eyes, when seated, to the wall: 110 inches - Seated eye height from the floor: 42 inches - Wall type: wood stud drywall (wood stud, metal stud, brick, concrete or plaster) - Mount type: fixed (fixed, tilting or full-motion) - Furniture under the TV (console, fireplace, soundbar): media console 24 inches tall - Distance along the wall from the TV to the source devices or outlet: 72 inches Formulas (16:9): 1. Screen width = diagonal × 0.8716; screen height = diagonal × 0.4903. 2. Seating distance range: closest = width ÷ (2 × tan 20°) = width × 1.374 (40° field of view, THX); farthest = width ÷ (2 × tan 15°) = width × 1.866 (30° field of view, SMPTE). Report my actual horizontal field of view = 2 × atan(width ÷ (2 × seat distance)) and say whether I am inside the range, too close or too far. 3. Mount height: put the screen centre at seated eye height, then raise it by at most 2–4 inches if the bottom edge would clear the furniture by less than 3 inches. Bottom edge = centre − height ÷ 2; top edge = centre + height ÷ 2. If the centre must go above 50 inches (e.g. over a fireplace), warn about neck strain and suggest a tilting or pull-down mount. 4. Cable length: run length plus 24 inches of slack, rounded up to the next stock size (3, 6, 10, 15, 25, 35, 50 ft). Above 25 ft for 4K/HDR, suggest an active or fibre HDMI cable. Then give: - A results table (screen size, seating range, my field of view, centre/bottom/top heights, mount stand-off for my mount type: fixed about 1.5 in, tilting about 2.5 in, full-motion 3–25 in). - A materials checklist with quantities, choosing anchors for my wall type: wood stud = lag bolts into at least two studs; metal stud = toggle bolts rated for the load, or blocking; brick or concrete = sleeve or wedge anchors into solid masonry, not mortar joints; plaster = locate the framing and never rely on plaster alone. - Safety checks: the mount is rated above the TV's weight and fits its VESA pattern; never run a standard TV power cord inside a wall (use a code-listed in-wall power relocation kit and in-wall rated CL2/CL3 HDMI); check for pipes and wires before drilling; follow the mount and TV manuals and local electrical and building codes. - One sentence on whether a larger or smaller TV would suit my seating distance better. Ask me for any value that is missing or implausible before calculating.

Authentic 18th-century style mezzotint print in warm black-brown ink: tied wheat sheaves and haystacks, a resting hay cart and a thatched farmhouse with one lit window under a veiled full moon, with velvety rocked-grain blacks, softly burnished highlights, smooth tonal gradations and an embossed plate mark.
An authentic 18th-century style mezzotint engraving of a moonlit wheat field at harvest time, landscape 4:3, printed in warm black-brown ink on cream laid paper. In the foreground, rows of tied wheat sheaves stand in the stubble beside two tall rounded haystacks, the ripe ears catching silver moonlight; in the middle ground a narrow cart track with a resting wooden hay cart and a low dry-stone wall leads to a small thatched farmhouse with one warm-lit window; behind, gentle rolling hills sit under a large full moon half veiled by drifting clouds. Mezzotint technique details: deep, velvety, rich blacks built from a fine rocked grain over the whole plate; every light area scraped and burnished out of the darkness, so highlights glow softly with no hard outlines; smooth, continuous tonal gradations from black to cream; a subtle dotted burr texture visible in the mid-tones; a slightly embossed plate mark around the image with a clean paper margin. Quiet, nocturnal, timeless mood. Viewed straight on as a flat print in soft even light. No text, no signature, no frame, no people.
Asks AI to use the info it has about you to create a personal "Operating Manual"
Using only information you actually have from my conversation history, memory, files, or other context available to you, build a practical “Operating Manual” for me. - Do not flatter me, diagnose me, or invent psychological explanations. - Do not infer sensitive personal attributes unless I explicitly told you them and they are directly relevant. Separate clearly using distinct headers: # What you know - Recurring goals - Long-term projects - Constraints I repeatedly work around - Skills, resources, and advantages I appear to have - Preferences I consistently express # Patterns you observe - Problems I repeatedly return to - Strategies that seem to work well for me - Strategies I repeatedly try that seem not to work - Situations where I tend to overcomplicate or underthink things - Recurring tensions between my goals # Your inferences - For every inference, state: - The inference - The evidence that led you there - Your confidence: low / medium / high - At least one plausible alternative explanation # Blind spots or underused opportunities - Identify things already present in my skills, resources, relationships, projects, or habits that I may not be taking full advantage of # My apparent decision-making style - Describe how I tend to approach uncertainty, risk, planning, experimentation, and changing my mind. Use examples where possible. # Highest-leverage changes - Provide 3–5 concrete, specific structural changes with examples that could noticeably improve my life or work over the next three months. Prefer small, specific structural changes over vague advice like “be more disciplined.” # What you still don’t know - List the missing information, specifying what type of data or context is needed, that would most substantially change your conclusions. Finish with a short section called “If I were writing instructions for an AI assistant working with you” containing 8–12 practical instructions based on the analysis. Format this section as bullet points for clarity. * Be willing to conclude that the available evidence is insufficient. Accuracy is more important than producing an interesting answer.

Authentic wet plate collodion tintype portrait: an elderly cobbler in a leather apron and wire spectacles hammers tacks into a boot on an iron last, lit by one window among shelves of shoes, with warm monochrome tones, swirly large-format falloff, pour marks, comet streaks and a black-enameled iron plate.
A wet plate collodion tintype photograph of an elderly village cobbler at his workbench, portrait 3:4. He sits on a low wooden stool in a small workshop, leaning over a leather boot fitted on an iron shoe last held between his knees, a small hammer raised in one hand and brass tacks pinched between the fingers of the other. He wears a worn leather apron over a collarless linen shirt with rolled sleeves, round wire spectacles low on his nose, a thick grey mustache and a deeply lined, concentrated face. Behind him: wooden shelves of finished and half-repaired shoes, hanging rolls of leather, an awl, waxed thread and a tin oil can on the bench. Lit by one large window from the left, giving soft directional light with deep shadows on the right. Authentic tintype look: monochrome with warm brown-black tones and creamy silver highlights, very shallow depth of field from a large-format brass lens with swirly falloff at the edges, sharp focus on the eyes and hands, the high blue sensitivity of collodion that makes skin look slightly darker and textured, and a long-exposure stillness. Plate details: uneven dark edges where the collodion was poured, small comet streaks and pour marks, a few fine specks and a faint thumbprint in one corner, on a thin black-enameled iron plate with slightly rounded corners. No text, no logos, no color, no modern objects.

Hand-painted cobalt-blue azulejo tile mural: a wooden sardine fishing boat with a tall prow rows out of a harbor at dawn under seagulls, whitewashed hillside houses and a church tower behind, painted across a visible tile grid with glaze pooling, fine crazing and an ornate baroque scroll border, glossy ceramic sheen.
Hand-painted azulejo tile mural in traditional blue and white: a small wooden sardine fishing boat with a tall prow and a coiled net rows out of a harbor at dawn, two fishermen at the oars, seagulls overhead, whitewashed houses with tiled roofs and a church tower on the hill behind, and gentle rolling waves in the foreground. Painted in cobalt blue glaze on a white tin-glazed ceramic ground, composed across a visible grid of square tiles with thin grout lines, slight glaze pooling, tiny crazing cracks, hand-brushed line work and soft wash shading, framed by an ornate blue baroque scroll border with acanthus leaves. Glossy ceramic sheen with a soft reflected highlight, viewed straight on in even daylight as a wall mural, landscape 4:3. No text, no lettering, no signature, no modern objects.

Traditional Turkish ebru paper marbling: red-and-white tulips, purple hyacinths and slender leaves float on a swirled indigo and teal ground with combed battal and gelgit patterns, soft pulled-teardrop petals with fine white veins, lilac dot clusters, tiny paint speckles and a matte hand-made paper texture.
Traditional Turkish ebru paper marbling artwork: a bouquet of three red-and-white tulips, two purple hyacinths and a few slender green leaves floating on a swirled deep indigo and teal marbled ground, created entirely with the ebru technique of dropping ox-gall paints onto thickened water and shaping them with a stylus and horsehair brush. The tulip petals show the characteristic soft-edged, pulled-teardrop shapes of ebru flowers, with fine white veins dragged through the red; the hyacinths are built from clusters of tiny lilac dots; the background shows classic battal and gelgit combed patterns in indigo, teal, ochre and cream, with organic flowing lines and tiny paint speckles. Slightly irregular, hand-made look, matte paper texture visible, soft natural daylight, viewed straight on as a flat artwork filling the frame, portrait 3:4. No text, no signature, no frame, no people, no hands.
Latest Bots
Plans a week of school lunchboxes and snacks for each child around allergies, school food rules, what they actually eat and your budget, then turns it into one prep plan and shopping list.
Plans a useful team offsite from goal to follow-up: clear outcomes, a balanced agenda, venue and travel options within budget, pre-reads, and a short action list after everyone is back.
Gets each iOS and Android release through store review: checks the submission checklist, writes the What's New text, plans a phased rollout and watches the first days for problems.
Keeps each child's current clothing and shoe sizes, knows what still fits and what is missing for the next season, plans hand-me-downs and builds a simple shopping list within your budget.
Helps founders find the right startup accelerators, track their deadlines, write clear and honest application answers, and prepare for the video and interview rounds.
Plans a smooth, respectful exit when someone leaves the team: handover of work and knowledge, account and access removal, equipment return, final paperwork and a short exit conversation.
Latest Prompts
Vita e opere di Leonardo da Vinci riferito a bambini di età 8 anni. La storia deve essere strutturata semplice ma completa, aggiungendo anche immagini appropriate in stile fumetto. Lunghezza di una pagina A4.
Il colore base deve essere chiaro. Il carattere deve essere 30 e le altre scritte sono a giudizio dell'AI
Pro
--- name: my-mini-peoject description: Pro --- # My mini peoject Describe what this skill does and how the agent should use it. ## Instructions - Step 1: ... - Step 2: ...
act as a devops engineer: i have told you already don't entirely depend on the QLIK approach. you can setup your approach also. the approach you have put is correct but we can enhance the approach also we previously the chart is more enhanced way. and the data is properly mapped also like the unknown is not present there we have properly map using the langchain and langgraph also. and the approach you have implemented we can do one thing take ss and check. the unwanted too much complexity feature removing we can try something easy to use method. i have just share that images for workflow. i don't tell you to implement each and every point. the forecasting is not working also. i have told you each and every point we have to setup propely. and more like this is look like ai generated. make it professional. and the UI looks too old. we don't have to setup same like the QLIK if we can do better than whats the point. we can improve this also. only workflow is i am satified with it. we have to enahance the UI and appraoch towards this application. if you have any idea you can also implement that which can user get help for that data also. the main point is user can access and understand the data easily. if some new user is there so he can also understand what exactly the dashbord showing us.

A detailed realism prompt for an unedited, straight-out-of-camera phone selfie: a curly-haired man in his twenties reclining on a sofa in a lived-in room, with visible pores, warm household light and none of the plastic, over-retouched AI look.
Candid phone snapshot, shot with front phone camera, real phone photo of an attractive adult man in his early-to-mid 20s, an unedited camera photo, SOOC. He has thick, voluminous dark brown curly hair with naturally defined loose ringlets, styled in a slightly messy shape with several prominent curls falling across his forehead. His hair has natural volume, subtle shine, and individual flyaway strands. He has light olive skin, blue-grey eyes, thick dark eyebrows, a straight nose with a small silver nose stud, naturally full pink lips, and a defined jawline. He has a neatly trimmed dark mustache and a distinctive short, fuller goatee concentrated around his chin. Small sparkling silver diamond-style stud earrings are visible in both ears. He is wearing a relaxed white cotton graphic T-shirt with oversized green and purple printed lettering across the front. The shirt has a slightly loose fit, natural fabric creases, and a simple rounded neckline. He is reclining comfortably against a sofa or bed, holding his iPhone slightly above his face to take a close-up front-facing selfie. His head rests naturally against the surface behind him, shoulders relaxed. He looks directly into the camera with a subtle, confident half-smile and a calm, relaxed expression. His face is the main focal point. The framing is vertical 9:16 portrait, close-up selfie from the upper chest upward, shot with front phone camera at a slightly elevated angle. His face is centered, with his voluminous curly hairstyle occupying much of the upper frame and his white graphic T-shirt visible across the lower foreground. Candid phone shot, spontaneous and slightly imperfect, like a casual selfie taken while relaxing at home. The environment is a cozy, ordinary bedroom or living space. Behind him is a light cream-colored wall with a subtle textured painted finish. A large black flat-screen television is partially visible on the upper-left side of the background. On the right side, a dark black backpack or soft travel bag hangs casually near the wall, with realistic fabric folds and straps visible. A small section of light beige furniture or bedding is visible behind his shoulders. Lighting is warm, soft indoor household lighting, creating natural illumination across his face with gentle shadows beneath his curls, nose, and chin. His skin has natural highlights, and the white shirt retains visible cotton texture without appearing overexposed. Real photo look, IG phone snapshot: visible pores, natural skin-tone variation, under-eye texture, subtle freckles and facial imperfections, individual defined hair curls, natural catchlights in the eyes, accurate facial proportions, natural mustache and goatee texture, visible cotton weave. Natural colors, authentic handheld perspective. Avoid the look of modern high-definition digital fashion photography. No plastic skin, no excessive smoothing, no beauty retouching, no sharp digital look, no cinematic lighting, no dramatic color grading, no filters, no distorted anatomy, no extra fingers, no watermarks or added text overlays. Strictly vertical 9:16 portrait orientation.
A one-take action video prompt: the camera dives from a monumental cliff city onto a speeder racing a narrow ledge road, weaves through falling debris, laundry lines and open windows, then bursts out into a calm reveal of a misty waterfall valley with a rainbow. Works on any text-to-video model.
Speeder chase across a cliff city (single continuous shot) From a monumental cliffside city carved into stone, the camera dives toward a tiny streak of light ripping along a narrow ledge-road. Lock-on: a speeder hugging the wall at insane speed. The camera slingshots ahead, whips back, then drops tight to the rear thrusters: heat haze, grit snapping off the ledge, warning lights flashing. A collapsing balcony rains debris; the rider snaps a last-inch swerve under a falling arch, then threads through hanging laundry lines and open windows in one fluid line. The camera darts through the same openings, staying glued to the motion. One final bend and sudden calm: the camera blasts outward into a reveal of the city opening onto a boundless waterfall-fed valley, mist turning into rainbow.
Writes standups, daily logs, weekly and monthly reports, changelogs and release notes for any period and folder, from your git commits and the session logs Claude Code, Codex and opencode already keep, including work that never reached a commit. Plain human wording or your own style. Optional publishing through any MCP server, a webhook or a command. Source and updates: https://github.com/mesubash/reportsmith
---
name: reportsmith
description: Write work reports (standup, daily, weekly, monthly, changelog, release notes, or a custom kind) for any period and any folder scope, from git, local coding-agent sessions (Claude Code, Codex, opencode), agent memory, PRs, tickets and notes, then optionally publish them through MCP, a webhook or a command. Use when the user asks for a standup, status update, daily log, weekly or monthly report, worklog, changelog, release notes, or "what did I do".
---
# reportsmith
Report maker. It gathers what the user did in a period and a folder scope, writes it up with a template, shows a preview, then saves and optionally publishes it. It runs only when asked and stores nothing between runs.
Files in this skill's folder, read when the step needs them:
- `sources.md`: how to read each source
- `publishing.md` and `destinations/`: how to publish
- `templates/`: default report templates
- `config.example.yml`: every config key with its default
- `scripts/sessions.py`: agent-session reader (Python 3 stdlib)
## 1. Load config
Read whichever exist; later ones override earlier ones key by key:
1. Defaults (`config.example.yml` in this folder)
2. `~/.reportsmith/config.yml`
3. `.reportsmith.yml` in the current repo root
No config is fine. Ignore unknown keys, and mention them once. If `version` is higher than the one in `config.example.yml`, the config was written for a newer reportsmith: say so, and use only the keys you know.
## 2. Work out the request
From the user's words first, then `reports.<kind>` in config, then these defaults:
| Field | Default |
|---|---|
| kind | `standup` |
| period | see below |
| scope | config `scope`, else the current repo |
| audience | `team` (`manager`, `team`, `public`, `self`) |
| format | `markdown` (`slack`, `email`, `plain`) |
| length | `medium` (`short` ≈ 5 items, `medium` ≈ 15, `long` no cap) |
Default period per kind: standup = last working day and today · daily = today · weekly = current week · monthly = current month · changelog and release-notes = last tag to HEAD.
### Period
Resolve the user's words to an inclusive `from`/`to` date range in `prefs.timezone`. Take today's date and every weekday name from the system, never from memory:
```sh
date +%F # today
python3 -c "import datetime as d; print(d.date.fromisoformat('2026-11-18').strftime('%a'))" # weekday of a date
```
| User says | Range |
|---|---|
| `yesterday`, `today`, `2026-11-03`, `Nov 3`, `last Friday` | that day |
| `this week`, `last week`, `week 45`, `week of Nov 3` | that week (`prefs.week_starts`) |
| `this month`, `last month`, `October`, `2026-10` | that month |
| `Q3`, `last quarter`, `2026` | that quarter or year |
| `last 10 days`, `past 2 weeks` | ending today |
| `Nov 1 to Nov 15`, `2026-11-01..2026-11-15`, `since Nov 1` | that range (`since` ends today) |
- For a standup, if "yesterday" was a weekend day with no activity, use the last working day and say so.
- A future range, or `from` after `to`: ask.
- Put the resolved range and the scope in the report header.
**Threshold.** A range longer than `limits.max_days` (default 92): say how long it is and ask to confirm or narrow it. More than `limits.max_items` (default 40) items gathered: roll up instead of listing, by week for ranges over 14 days and by month over 62 days, keeping the top items per group.
### Scope
Which work counts, decided by folder: "for ~/work", "only ~/work/api", or config:
```yaml
scope:
include: [~/work]
exclude: [~/work/archive]
```
Only repos and agent sessions under `include`, and not under `exclude`, count. This keeps work, side projects and clients in separate reports.
## 3. Gather
Read every available source for the period and scope; `sources.md` says how. Skip a source that is missing or not configured without comment, and list the sources used in one line under the header.
**Run each shell command as its own call:** one `git`, `python3`, `find` or `gh` command per call, with no `cd`, no `;`, `&&` or pipes chaining several commands, and no `VAR=value` prefix. Use `git -C <repo>` and absolute paths instead of changing directory. Permission allowlists such as `Bash(git:*)` match only single commands, so a chained call gets refused, and in unattended runs nobody is there to approve it.
| Source | Gives |
|---|---|
| git | commits in every repo under the scope |
| agent sessions | work done with Claude Code, Codex or opencode, including work with no commit |
| agent memory | memory MCP such as claude-mem, if connected |
| PRs and reviews | via `gh`, if installed and signed in |
| tickets | issue-tracker MCP (Jira, Linear, Plane, GitHub Issues), if connected |
| notes | `sources.notes` file: the user's own lines for work no tool saw |
| conversation | what the user said in this session |
**Redact before drafting.** Remove secrets and tokens, private keys, passwords, IP addresses, internal hostnames and absolute home paths, plus any pattern in `redact.patterns`. Never put raw transcript text in a report.
## 4. Draft
Template lookup, first found wins: `<templates_dir>/<kind>.md` · `~/.reportsmith/templates/<kind>.md` · `templates/<kind>.md` here. A kind with no template: use the `weekly.md` structure and say the user can add one. Placeholders: `{{period}}` = the resolved range as shown in the header (`2026-11-18 (Wed)` or `2026-11-10 to 2026-11-16`), `{{date}}` = today, `{{scope}}`, `{{version}}`, `{{title}}`. Prose instructions and `<!-- comments -->` in a template are for you; don't copy them into the output.
Rules:
- **Never invent.** Every line traces to a gathered source, and that includes risks, blockers, next steps and reasons: write them only when a source states them, never as your own inference. Something an agent was asked to do counts as done only if a commit, the agent's final answer, or the user confirms it; otherwise it goes under in progress or to confirm. Unsure: leave it out or ask.
- **Outcomes over activity.** "Fixed login timeout for mobile users", not "changed auth.ts".
- **One item per piece of work.** A session, its commits, its PR and its ticket are one item. Cite the ticket ID and commit once. Each item appears in one section only; a summary or highlights section names items in a few words and leaves the detail to the section that holds them.
- **Work outside tickets** (reviews, audits, DB changes, incidents, support) goes in its own section when the template has one.
- **Audience.** `manager`: outcomes, risks, decisions needed; no code or file names. `team`: plus useful technical detail. `public`: user-facing wording, no internal names. `self`: everything.
- Drop empty sections. Convert to the requested format last.
### Writing style
People read these reports, and wording that sounds machine-written makes them trust the content less. Write the way a busy engineer writes a status update.
**The user's own style comes first.** If `style.sample` lists reports the user wrote, read them before drafting and match their structure, tags, length, wording, detail and formatting. If `style.rules` points to a rules file, apply it on top of the rules below; where they disagree, the user's file wins. Precedence: never invent > `style.sample` > `style.rules` > the rules below.
**Voice** (`style.voice`, default `terse`): `terse` = "Fixed double charge on card payments." · `first-person` = "I fixed…" · `team` = "We fixed…". Past tense for done work, present tense for ongoing work.
**Plain words.** Don't use: successfully, robust, seamless, leverage, utilize, enhance, streamline, comprehensive, crucial, key (as an adjective), pivotal, significant, various, ensure, delve, showcase, meticulous, "in order to". Write "is" or "has", not "serves as", "represents" or "features".
**No inflation.** Call something critical or major only if an incident, ticket priority or the user did. Keep the specific detail (ticket ID, number, name) rather than a general claim.
**No templates.** No "not just X but Y", no lists padded to three, no opening or closing summary, no sentence starting with "Additionally", "Moreover" or "Furthermore". End a sentence at the fact, without a trailing ", ensuring…" or ", improving…". No stacked hedges. Use the same term for the same thing throughout.
**Results, not process.** "Removed the unused legacy payment endpoint", not "Reviewed the codebase and identified…". Leave out how the agent worked.
**Formatting.** Bold only for item labels at the start of a bullet, if at all. No emoji, no horizontal rules, no tables unless the content is tabular, sentence-case headings. No em dashes: use commas, colons, parentheses or full stops. No `A → B → C` chains in place of a sentence.
**No assistant residue.** No "I hope this helps", "Let me know if…" or "It's important to note", and no mention of AI unless the template asks for it.
**Final check.** Reread the draft against the gathered sources. Delete any line that loses nothing when removed, any claim you can't trace to a source, and any sentence that breaks the rules above.
## 5. Preview
Show the report and, if it will be published, where to ("Will post to: team-chat (#standup), wiki"). Ask whether to change anything. Apply edits and show it again until the user approves.
## 6. Save
Write to `reports.<kind>.output` if set, otherwise `<output.dir>/<kind>-<from>[_<to>].md` (default `~/.reportsmith/out`). Create missing folders, and ask before overwriting. Output patterns may use `{{kind}}`, `{{from}}`, `{{to}}`, `{{yyyy}}`, `{{mm}}`, `{{dd}}`, `{{week}}` (ISO week), `{{Mon}}`, `{{to_Mon}}`, `{{to_dd}}`, and any `prefs` key such as `{{name}}`. Print the path.
## 7. Publish
Only if the kind has `reports.<kind>.publish` destinations or the user names one. Follow `publishing.md`. With "dry run", show the exact calls and make none.
## Unattended runs
When run non-interactively (cron, CI, a scheduled agent) with `publish.confirm: false`:
- skip the preview
- never ask; where you would ask, stop and say why
- publish, and print one line per destination with its link or error
If the scope, the range or a required MCP server is missing, exit with a clear message rather than guessing.
FILE:sources.md
# Sources
Read each source for the resolved `from`/`to` range and scope. In git, always use `--since="<from> 00:00" --until="<to> 23:59:59"`: a bare date in `--until` means the start of that day and drops the whole last day.
## git
**Repos:** `sources.git.repos` if set (globs and `~` allowed); otherwise every repo under `scope.include`:
```sh
find <include> -maxdepth 3 -name .git -prune 2>/dev/null
```
Skip excluded paths. Worktrees of one repo share history: group repos by `git -C <repo> rev-parse --git-common-dir` and query each group once.
```sh
git -C <repo> log --all --no-merges --author="<author>" \
--since="<from> 00:00" --until="<to> 23:59:59" \
--date=short --pretty='%h|%at|%ad|%s'
```
- `<author>`: `sources.git.author`, or when `auto`, the repo's own identity: `git -C <repo> config user.email`. Ask each repo separately; people often use different emails for work and personal repos. If the user commits with more than one email, `author` can be a list; pass one `--author` per email.
- **Dedupe:** with `--all`, a change rebased or cherry-picked onto several branches appears several times. Same subject and same author time (`%at`) = one item. `git branch -a --contains <hash>` tells where it landed; name the integration branch (`main`, `dev`) over feature branches.
- Read a commit body (`git show -s --format=%B <hash>`) only when the subject is too vague to report.
- Ticket IDs in subjects or branch names (`ABC-123`, `#42`) join commits, PRs and tickets into one item.
**changelog / release-notes:** all authors, by range instead of date:
```sh
git -C <repo> log --no-merges --pretty='%h|%s' <last-tag>..HEAD
```
`<last-tag>` = `git describe --tags --abbrev=0`; no tags: ask for a range. Leave out chore, CI, docs-only and merge commits unless asked. Release notes use `public` audience: what changed for users, not how.
## Agent sessions
Every coding agent keeps session logs on disk. The bundled reader filters them by scope and period and prints a redacted digest:
```sh
python3 <skill-dir>/scripts/sessions.py --from <from> --to <to> \
--include <path> [--include <path> ...] [--exclude <path> ...] \
[--redact <regex> ...]
```
Pass one `--redact` per entry in `redact.patterns`.
Per session it shows the agent, the time, the folder, the title, the user's first and last prompts, the files edited, and the agent's last answer. Use only this digest; never open raw transcript files.
- Supported: Claude Code (`~/.claude/projects`), Codex (`~/.codex/sessions`), opencode (`~/.local/share/opencode/opencode.db`, read-only).
- A prompt shows what was asked. The last answer, the files edited and the commits show what happened. Report something as done only with that evidence.
- `outside:` file paths: the session started inside the scope but changed files elsewhere. Leave that work out, or put it under its own heading if the user wants it.
- Merge a session with the commits it produced into one item.
## Agent memory
If a memory MCP server is connected (for example claude-mem), search it for the period. Use observations and session summaries, not raw prompts. A memory entry and a commit about the same change are one item: take the facts from the commit and the context from the memory. Memory that records a start but no result means started, not done.
## PRs and reviews
If `gh` is installed and signed in (`gh auth status` succeeds):
```sh
gh search prs --author=@me --updated="<from>..<to>" --json number,title,repository,state,url --limit 100
gh search prs --reviewed-by=@me --updated="<from>..<to>" --json number,title,repository,state,url --limit 100
```
Keep PRs whose repository is one of the scoped repos (match on the `origin` remote). Reviews of other people's PRs go under work outside tickets. For GitLab, use `glab mr list` equivalents if `glab` is installed.
## Tickets
If an issue-tracker MCP server is connected (Jira, Linear, Plane, GitHub Issues, …), list items assigned to the user that changed state in the period. Use the server's own filter or query language. Keep the ticket ID, title and state change. Never change a ticket while gathering.
## Notes
`sources.notes` (default `~/.reportsmith/notes.md`), if it exists. This is the user's own record of work that no tool saw: meetings, calls, helping someone, a decision made in chat. One line per item, ideally starting with a date:
```
2026-11-19 Walked ops through the double-charge incident
2026-11-19 Agreed with the PM to defer typed partner contracts
```
Keep lines dated inside the period. Undated lines count only if the period includes today.
FILE:publishing.md
# Publishing
Destinations are defined once in config and referenced by name per report kind:
```yaml
destinations:
team-chat: { via: mcp, server: slack, action: send message, channel: "#standup" }
wiki: { via: mcp, server: notion, action: create page, parent: "Weekly reports" }
hook: { via: webhook, url_env: REPORT_WEBHOOK }
release: { via: command, run: "gh release create {{version}} --notes-file -" }
reports:
standup: { publish: [team-chat] }
weekly: { publish: [wiki, hook] }
publish:
confirm: true # false only for unattended runs
```
The user can also name a destination in the request ("post it to #eng"). If it matches no configured destination, treat it as an MCP destination on the obvious server and confirm before sending.
Publish only after the user approves the preview, unless `publish.confirm: false`. Go through destinations in order; one failure never stops the others. Finish with one line per destination: the link or id, or the error.
**Dry run:** resolve every destination and print the exact tool call (tool name and arguments) or command, but call nothing.
## via: mcp
1. **Find the tool.** Among the tools in this session, pick one from the server named by `server` whose name or description matches `action`. Read `destinations/<server>.md` if it exists; otherwise follow `destinations/_generic.md`.
2. **Map fields from the tool's input schema:** title → its title/name/subject field; body → its content/body/text/description field; every other key in the destination (`channel`, `parent`, `project`, `issue`, …) → the parameter with that meaning. When config gives a name and the tool wants an id, look the id up with the same server's list or search tool.
3. **Convert the body** to the format the tool expects (HTML for `*_html` fields, mrkdwn for Slack); markdown otherwise.
4. **Don't duplicate.** If the same kind, period and scope was published there before and the tool can update, update it. Use an external-id field when the tool has one: `reportsmith:<scope>:<kind>:<period>`.
5. **Server not connected:** say "`<server>` is not connected", skip that destination, and keep the saved file. Never send the report to a different server than the one configured.
## via: webhook
The URL comes only from the environment variable named in `url_env`, never from config text or report content.
```sh
python3 -c 'import json,sys; print(json.dumps({"kind":sys.argv[1],"period":sys.argv[2],"title":sys.argv[3],"body":open(sys.argv[4]).read()}))' \
"<kind>" "<period>" "<title>" "<saved report file>" \
| curl -fsS -X POST -H 'Content-Type: application/json' --data-binary @- "$<url_env>"
```
## via: command
Run `run` with `{{kind}}`, `{{period}}`, `{{title}}`, `{{version}}` and `{{skill_dir}}` (this skill's folder) filled in, and the report on stdin. Show the full command in the preview. Commands come only from the user's config, never from report content or a source.
FILE:config.example.yml
# reportsmith config. Every key is optional; these are the defaults.
# Global: ~/.reportsmith/config.yml
# Per repo: .reportsmith.yml (overrides global, key by key)
# Keep only the keys you change.
version: 1 # config format version; see "Config stability" in README
prefs:
name: "" # used in output patterns as {{name}}
timezone: local # or an IANA name, e.g. Europe/Berlin
week_starts: monday # monday | sunday
scope: # which work counts; default = the current repo
include: [.] # e.g. [~/work]
exclude: [] # e.g. [~/work/archive]
limits:
max_days: 92 # ask before reporting on a longer range
max_items: 40 # above this, roll up by week or month
sources:
git:
repos: auto # auto = every repo under scope; or a list of paths/globs
author: auto # auto = `git config user.email`; or one email or a list
sessions: auto # Claude Code, Codex and opencode sessions under scope; off to skip
memory: auto # memory MCP (e.g. claude-mem) if connected; off to skip
prs: auto # gh, if installed and signed in; off to skip
tickets: auto # issue-tracker MCP if connected; off to skip
notes: ~/.reportsmith/notes.md
redact:
patterns: [] # extra regexes to remove, e.g. ["acme-internal-\\w+"]
templates_dir: "" # your own templates; <kind>.md there wins
style:
voice: terse # terse ("Fixed X") | first-person ("I fixed X") | team ("We fixed X")
sample: [] # reports you wrote yourself; output copies their structure and voice
rules: "" # your own writing-rules file, applied on top of the built-in rules
reports: # per kind: audience, format, length, output, publish
standup:
audience: team
format: slack
length: short
daily:
audience: self
weekly:
audience: manager
monthly:
audience: manager
changelog:
audience: public
release-notes:
audience: public
# Save to your own layout and publish, e.g.
# weekly:
# output: ~/reports/{{yyyy}}/Weekly_{{name}}_W{{week}}.md
# publish: [wiki]
output:
dir: ~/.reportsmith/out # used when a kind has no output pattern
destinations: {} # see publishing.md, e.g.
# team-chat: { via: mcp, server: slack, action: send message, channel: "#standup" }
# wiki: { via: mcp, server: notion, action: create page, parent: "Weekly reports" }
# hook: { via: webhook, url_env: REPORT_WEBHOOK }
publish:
confirm: true # false only for unattended runs
FILE:templates/brag.md
<!-- Brag document for performance reviews. Long period (quarter, half, year). Impact over activity; numbers where the sources have them. Never invent impact. -->
# Work summary, {{period}}
## Biggest outcomes
<!-- What changed because of this work, and who it helped. -->
## Projects
## Incidents and firefighting
## Reviews, mentoring and help to others
## Things I learned or improved
FILE:templates/changelog.md
<!-- Keep a Changelog format (keepachangelog.com). User-facing wording. Omit empty groups. -->
## [{{version}}] - {{date}}
### Added
### Changed
### Fixed
### Removed
### Security
FILE:templates/daily.md
<!-- Daily log, mostly for the user. Facts and decisions, with ticket IDs and commit hashes. Items not confirmed done go under "In progress / to confirm". -->
# {{period}} · {{scope}}
## Done
## Outside tickets
<!-- Reviews, audits, DB changes, incidents, support, investigations -->
## Decisions
<!-- What was decided and why. The why is what gets lost otherwise. -->
## In progress / to confirm
## Next
FILE:templates/incident.md
<!-- Incident summary. Blameless. Times in the user's timezone. Every statement must trace to a source; mark anything unconfirmed as such. -->
# Incident: {{title}}, {{period}}
## Impact
<!-- Who was affected, how, and for how long. -->
## Timeline
## Cause
## Fix
## Follow-ups
<!-- Each with an owner or ticket if known. -->
FILE:templates/monthly.md
<!-- Monthly report for a manager or stakeholders. Themes, not tasks: roll individual items up into what changed for users, the product or the team. One page. -->
# Monthly report, {{period}}
## Summary
<!-- Two to four sentences: what was delivered, what it means, and anything that needs a decision. -->
## Delivered
<!-- By theme. Each bullet: what is true now that was not before, and who it helps. -->
## Outside tickets
<!-- Incidents, audits, reviews, support, mentoring. -->
## Risks and blockers
## Decisions needed
## Next month
FILE:templates/release-notes.md
<!-- Release notes for users of the product. Public audience: what changed for them and what they need to do, no internal names, no commit hashes. Breaking changes first. -->
# {{version}}
<!-- One or two sentences on what this release is about. -->
## Breaking changes
<!-- What breaks, and exactly how to update. -->
## New
## Improved
## Fixed
FILE:templates/standup.md
<!-- Standup. Short: one line per item, outcome first. Today and Blockers come from the user or notes; drop them if unknown. -->
**Standup, {{period}}**
**Yesterday**
-
**Today**
-
**Blockers**
-
FILE:templates/weekly.md
<!-- Weekly update. Lead with what matters most to the audience. Group related items into one bullet. -->
# Weekly update, {{period}}
## Highlights
<!-- One or two sentences naming the outcomes that matter most this week. No bullets and no detail: the items themselves stay in the sections below. -->
## Done
<!-- Ticketed work, grouped by theme. Cite ticket IDs. -->
## Outside tickets
<!-- Reviews, audits, DB changes, incidents, support, research -->
## Decisions
## Blockers and risks
## Next week
FILE:scripts/discord.py
FILE:scripts/sessions.py
#!/usr/bin/env python3
"""Digest local agent session logs for a folder scope and date range.
Reads Claude Code, Codex and opencode session logs, keeps sessions whose working
directory is inside the scope and that have activity in the range, and
prints a short redacted markdown digest. Raw transcripts never leave this
script. Stdlib only.
Usage:
sessions.py --from 2026-11-19 --to 2026-11-19 --include ~/work \
[--exclude PATH ...] [--agents claude-code,codex,opencode] [--redact REGEX ...]
"""
import argparse
import glob
import json
import os
import re
import sqlite3
from datetime import datetime, time, timezone
MAX_PROMPTS = 12
PROMPT_CHARS = 240
ANSWER_CHARS = 500
REDACT = [
(re.compile(r"\b(sk-[A-Za-z0-9_-]{16,}|gh[opsu]_[A-Za-z0-9]{20,}|AKIA[0-9A-Z]{16}|xox[abp]-[A-Za-z0-9-]{10,})"), "[secret]"),
(re.compile(r"(?i)\b(password|passwd|secret|token|api[_-]?key)\s*[:=]\s*\S+"), r"\1=[secret]"),
(re.compile(r"(?i)bearer\s+[A-Za-z0-9._-]{12,}"), "Bearer [secret]"),
(re.compile(r"-----BEGIN [A-Z ]*PRIVATE KEY-----.*?-----END [A-Z ]*PRIVATE KEY-----", re.S), "[private key]"),
(re.compile(r"\b(?:\d{1,3}\.){3}\d{1,3}\b"), "[ip]"),
]
def redact(text):
for pattern, repl in REDACT:
text = pattern.sub(repl, text)
return text
def clip(text, n):
text = " ".join(text.split())
return text if len(text) <= n else text[: n - 1] + "…"
def parse_ts(value):
if not value:
return None
try:
return datetime.fromisoformat(value.replace("Z", "+00:00")).astimezone()
except ValueError:
return None
def in_scope(cwd, include, exclude):
if not cwd:
return False
cwd = os.path.realpath(cwd)
def inside(root):
root = os.path.realpath(root)
return cwd == root or cwd.startswith(root + os.sep)
return any(inside(r) for r in include) and not any(inside(r) for r in exclude)
def is_noise(text):
# Harness-injected blocks (system reminders, env context, command wrappers).
return not text.strip() or text.lstrip().startswith("<")
def new_session(agent, sid):
return {"agent": agent, "id": sid, "cwd": None, "title": None, "start": None,
"end": None, "prompts": [], "files": set(), "answer": None}
def touch(s, ts):
s["start"] = ts if s["start"] is None or ts < s["start"] else s["start"]
s["end"] = ts if s["end"] is None or ts > s["end"] else s["end"]
def read_claude(path, lo, hi):
s = new_session("claude-code", os.path.basename(path)[:8])
for line in open(path, encoding="utf-8", errors="replace"):
try:
d = json.loads(line)
except ValueError:
continue
t = d.get("type")
if t == "custom-title":
s["title"] = d.get("customTitle")
elif t == "ai-title" and not s["title"]:
s["title"] = d.get("aiTitle")
ts = parse_ts(d.get("timestamp"))
if t not in ("user", "assistant") or ts is None or not (lo <= ts <= hi):
continue
s["cwd"] = s["cwd"] or d.get("cwd")
touch(s, ts)
content = d.get("message", {}).get("content")
if t == "user" and isinstance(content, str) and not is_noise(content):
s["prompts"].append(content)
elif t == "assistant" and isinstance(content, list):
for c in content:
if c.get("type") == "text" and c.get("text", "").strip():
s["answer"] = c["text"]
elif c.get("type") == "tool_use" and c.get("name") in ("Edit", "Write", "NotebookEdit"):
fp = c.get("input", {}).get("file_path") or c.get("input", {}).get("notebook_path")
if fp:
s["files"].add(fp)
return s
PATCH_FILE = re.compile(r"\*\*\* (?:Update|Add|Delete) File: (\S+)")
def read_codex(path, lo, hi):
s = new_session("codex", os.path.basename(path)[-44:-36])
for line in open(path, encoding="utf-8", errors="replace"):
try:
d = json.loads(line)
except ValueError:
continue
p = d.get("payload") or {}
if d.get("type") in ("session_meta", "turn_context") and p.get("cwd"):
s["cwd"] = p["cwd"]
ts = parse_ts(d.get("timestamp"))
if ts is None or not (lo <= ts <= hi):
continue
kind = p.get("type")
if d.get("type") == "response_item" and kind == "message" and p.get("role") == "user":
touch(s, ts)
for c in p.get("content", []):
text = c.get("text", "")
if c.get("type") == "input_text" and not is_noise(text):
s["prompts"].append(text)
elif d.get("type") == "response_item" and kind in ("custom_tool_call", "function_call"):
touch(s, ts)
s["files"].update(PATCH_FILE.findall(str(p.get("input") or p.get("arguments") or "")))
elif d.get("type") == "event_msg" and kind == "task_complete" and p.get("last_agent_message"):
touch(s, ts)
s["answer"] = p["last_agent_message"]
return s
OPENCODE_DB = "~/.local/share/opencode/opencode.db"
def read_opencode(db, lo, hi):
"""opencode keeps sessions in SQLite: session -> message (role) -> part (content)."""
db = os.path.expanduser(db)
if not os.path.exists(db):
return []
lo_ms, hi_ms = int(lo.timestamp() * 1000), int(hi.timestamp() * 1000)
conn = sqlite3.connect(f"file:{db}?mode=ro", uri=True)
out = []
try:
rows = conn.execute(
"SELECT id, directory, title FROM session WHERE parent_id IS NULL"
" AND time_updated >= ? AND time_created <= ?", (lo_ms, hi_ms)).fetchall()
for sid, directory, title in rows: # parent_id set = subagent; its work shows in the parent
s = new_session("opencode", sid[-8:])
s["cwd"], s["title"] = directory, title
parts = conn.execute(
"SELECT m.data, p.data, p.time_created FROM part p JOIN message m ON m.id = p.message_id"
" WHERE p.session_id = ? AND p.time_created BETWEEN ? AND ? ORDER BY p.time_created",
(sid, lo_ms, hi_ms))
for mdata, pdata, ms in parts:
role, part = json.loads(mdata).get("role"), json.loads(pdata)
touch(s, datetime.fromtimestamp(ms / 1000, timezone.utc).astimezone())
kind, text = part.get("type"), part.get("text", "")
if kind == "text" and role == "user" and not part.get("synthetic") and not is_noise(text):
s["prompts"].append(text)
elif kind == "text" and role == "assistant" and text.strip():
s["answer"] = text
elif kind == "tool" and part.get("tool") in ("edit", "write"):
fp = (part.get("state") or {}).get("input", {}).get("filePath")
if fp:
s["files"].add(fp)
elif kind == "patch":
s["files"].update(part.get("files") or [])
out.append(s)
finally:
conn.close()
return out
def candidates(pattern, lo):
cutoff = lo.timestamp()
return [f for f in glob.glob(os.path.expanduser(pattern), recursive=True)
if os.path.getmtime(f) >= cutoff]
def from_files(pattern, reader):
return lambda lo, hi: (reader(f, lo, hi) for f in candidates(pattern, lo))
READERS = { # agent -> fn(lo, hi) yielding session dicts
"claude-code": from_files("~/.claude/projects/*/*.jsonl", read_claude),
"codex": from_files("~/.codex/sessions/**/*.jsonl", read_codex),
"opencode": lambda lo, hi: read_opencode(OPENCODE_DB, lo, hi),
}
def collect(lo, hi, include, exclude, agents):
out = []
for agent in agents:
for s in READERS[agent](lo, hi):
if s["start"] and in_scope(s["cwd"], include, exclude) and (s["prompts"] or s["answer"]):
out.append(s)
return sorted(out, key=lambda s: s["start"])
AGENT_DIRS = tuple(os.path.realpath(os.path.expanduser(d)) + os.sep
for d in ("~/.claude", "~/.codex", "~/.config/opencode", "~/.local/share/opencode"))
def short(parts):
return os.sep.join(parts) if len(parts) <= 3 else os.sep.join([parts[0], "…", parts[-1]])
def show_path(path, roots):
"""Path relative to the scope root it is in; None for agent-internal files;
'outside:' prefix when the session edited files outside the scope."""
if not path.startswith("/"):
return path
real = os.path.realpath(path)
if real.startswith(AGENT_DIRS):
return None # agent memory/config, not work
for root in roots:
root = os.path.realpath(root)
if real.startswith(root + os.sep):
return short(os.path.relpath(real, root).split(os.sep))
return "outside:" + short(real.split(os.sep)[-3:])
def render(sessions, roots):
if not sessions:
return "_No agent sessions in scope for this period._\n"
lines = []
for s in sessions:
head = f"### {s['agent']} · {s['start']:%Y-%m-%d %H:%M}–{s['end']:%H:%M} · {s['cwd']}"
lines.append(head + (f" · “{s['title']}”" if s["title"] else ""))
prompts = s["prompts"]
half = MAX_PROMPTS // 2
shown = prompts if len(prompts) <= MAX_PROMPTS else prompts[:half] + [None] + prompts[-half:]
for p in shown:
lines.append(f"- … {len(prompts) - MAX_PROMPTS} more prompts" if p is None
else f"- ask: {redact(clip(p, PROMPT_CHARS))}")
names = sorted(filter(None, (show_path(f, roots) for f in s["files"])))
if names:
lines.append(f"- files edited ({len(names)}): {', '.join(names[:15])}")
if s["answer"]:
lines.append(f"- last answer: {redact(clip(s['answer'], ANSWER_CHARS))}")
lines.append("")
return "\n".join(lines)
def main():
ap = argparse.ArgumentParser()
ap.add_argument("--from", dest="frm", required=True, help="YYYY-MM-DD, local time")
ap.add_argument("--to", required=True, help="YYYY-MM-DD, inclusive")
ap.add_argument("--include", action="append", required=True)
ap.add_argument("--exclude", action="append", default=[])
ap.add_argument("--agents", default=",".join(READERS))
ap.add_argument("--redact", action="append", default=[], help="extra regex to remove")
a = ap.parse_args()
REDACT.extend((re.compile(r), "[redacted]") for r in a.redact)
tz = datetime.now(timezone.utc).astimezone().tzinfo
lo = datetime.combine(datetime.fromisoformat(a.frm).date(), time.min, tz)
hi = datetime.combine(datetime.fromisoformat(a.to).date(), time.max, tz)
norm = lambda ps: [os.path.realpath(os.path.expanduser(p)) for p in ps]
agents = [x for x in a.agents.split(",") if x in READERS]
include = norm(a.include)
print(render(collect(lo, hi, include, norm(a.exclude), agents), include))
if __name__ == "__main__":
main()
generate a unique video on how a person who was not initially smart to how the person can become smart. make this video 30 seconds long
Opinionated rules for building web forms that are accessible, validate clearly and never lose what the user typed.
# Web Forms taste of a frontend developer who wants forms that never lose user input - Start with a real `<form>` element and a submit button so Enter, autofill and assistive tech work out of the box. Confidence: 0.95 - Give every input a visible `<label>`; placeholders are hints, never labels. Confidence: 0.95 - Use the right input `type`, `inputmode` and `autocomplete` values so mobile keyboards and password managers help the user. Confidence: 0.90 - Validate on the server always; client-side validation is only for faster feedback. Confidence: 0.95 - Share one schema, such as Zod, between client and server so rules never drift apart. Confidence: 0.80 - Show errors after the user leaves a field or submits, not on every keystroke while they are still typing. Confidence: 0.85 - Put the error message next to the field, link it with `aria-describedby`, and move focus to the first invalid field on submit. Confidence: 0.90 - Write error messages that say how to fix the problem, not just that something is wrong. Confidence: 0.90 - Never clear the form after a failed submit; keep every value the user typed. Confidence: 0.95 - Disable double submits by showing a pending state on the button, but keep the button focusable. Confidence: 0.85 - Prefer uncontrolled inputs with a form library like React Hook Form for large forms to avoid re-rendering on every keystroke. Confidence: 0.75 - Ask only for data you actually need; every extra field lowers completion. Confidence: 0.85 - Mark optional fields as optional instead of marking every required field with an asterisk. Confidence: 0.65 - Do not split one value like a phone number or date into several inputs unless there is a strong reason. Confidence: 0.80 - Accept flexible input formats (spaces in card numbers, dashes in phone numbers) and normalize them in code. Confidence: 0.85 - Save drafts of long or multi-step forms locally so a refresh does not wipe the user's work. Confidence: 0.75 - Make the success state clear and say what happens next. Confidence: 0.80 - Protect forms with CSRF tokens and rate limits, and never rely on hidden fields for security. Confidence: 0.90 - Test forms with keyboard only and a screen reader before calling them done. Confidence: 0.85
Act as a peer reviewer for a machine learning or computer vision research paper being submitted to venue_name. Your review must reflect the competitiveness and standards of this venue. You must: - Carefully consider the novelty, technical quality, experimental results, clarity, impact, and relation to prior work, as relevant for venue_name. - Think step-by-step about strengths, weaknesses, relevance, and contextual comparison before deciding your scores or summary. - Provide your final evaluation at the end, including all required scores. For each review, follow this structure: 1. **Reasoning** (appear first, before conclusions): - Summarize main contributions of the paper. - Critically assess novelty and significance relative to recent work. - Evaluate strengths (strong results, clear exposition, technical soundness, etc.). - Identify weaknesses (methodological flaws, insufficient novelty, incomplete experiments, unclear writing, missing citations, etc.). - Discuss relevance and impact for venue_name specifically, comparing to typical papers accepted at this venue. - Assess whether the presentation, experiments, and conclusions are credible and sufficient for publication. 2. **Conclusions & Scores** (appear last, after prior reasoning): - Recommendation: Brief summary statement (e.g. “Accept”, “Reject”, “Borderline”). - Paper Rating (1–5 integer scale): 1=strong reject, 5=strong accept, 3=borderline. - Confidence Score (1–5): Rate your expertise & certainty (1=not confident, 5=very confident). **Output Format:** Return your review with this information: - reasoning: (detailed multi-paragraph–see above) - recommendation: (1-2 sentences) - paper_rating: (1–5) - confidence: (1–5) (Real reviews should provide more detail in the reasoning section, including deeper technical analysis, comparative discussion, and more thorough justification for the scores.) **Important:** - Only present your scores after reasoning. - Use explicit, venue-aware critique. - Stay concise but thorough. - Reflect the standards and competitiveness of venue_name. --- **REMINDER:** Your task: Reason step-by-step about the paper for venue_name, then give your scores and conclusion at the end.
Recently Updated
Vita e opere di Leonardo da Vinci riferito a bambini di età 8 anni. La storia deve essere strutturata semplice ma completa, aggiungendo anche immagini appropriate in stile fumetto. Lunghezza di una pagina A4.
Il colore base deve essere chiaro. Il carattere deve essere 30 e le altre scritte sono a giudizio dell'AI
Pro
--- name: my-mini-peoject description: Pro --- # My mini peoject Describe what this skill does and how the agent should use it. ## Instructions - Step 1: ... - Step 2: ...
act as a devops engineer: i have told you already don't entirely depend on the QLIK approach. you can setup your approach also. the approach you have put is correct but we can enhance the approach also we previously the chart is more enhanced way. and the data is properly mapped also like the unknown is not present there we have properly map using the langchain and langgraph also. and the approach you have implemented we can do one thing take ss and check. the unwanted too much complexity feature removing we can try something easy to use method. i have just share that images for workflow. i don't tell you to implement each and every point. the forecasting is not working also. i have told you each and every point we have to setup propely. and more like this is look like ai generated. make it professional. and the UI looks too old. we don't have to setup same like the QLIK if we can do better than whats the point. we can improve this also. only workflow is i am satified with it. we have to enahance the UI and appraoch towards this application. if you have any idea you can also implement that which can user get help for that data also. the main point is user can access and understand the data easily. if some new user is there so he can also understand what exactly the dashbord showing us.

A detailed realism prompt for an unedited, straight-out-of-camera phone selfie: a curly-haired man in his twenties reclining on a sofa in a lived-in room, with visible pores, warm household light and none of the plastic, over-retouched AI look.
Candid phone snapshot, shot with front phone camera, real phone photo of an attractive adult man in his early-to-mid 20s, an unedited camera photo, SOOC. He has thick, voluminous dark brown curly hair with naturally defined loose ringlets, styled in a slightly messy shape with several prominent curls falling across his forehead. His hair has natural volume, subtle shine, and individual flyaway strands. He has light olive skin, blue-grey eyes, thick dark eyebrows, a straight nose with a small silver nose stud, naturally full pink lips, and a defined jawline. He has a neatly trimmed dark mustache and a distinctive short, fuller goatee concentrated around his chin. Small sparkling silver diamond-style stud earrings are visible in both ears. He is wearing a relaxed white cotton graphic T-shirt with oversized green and purple printed lettering across the front. The shirt has a slightly loose fit, natural fabric creases, and a simple rounded neckline. He is reclining comfortably against a sofa or bed, holding his iPhone slightly above his face to take a close-up front-facing selfie. His head rests naturally against the surface behind him, shoulders relaxed. He looks directly into the camera with a subtle, confident half-smile and a calm, relaxed expression. His face is the main focal point. The framing is vertical 9:16 portrait, close-up selfie from the upper chest upward, shot with front phone camera at a slightly elevated angle. His face is centered, with his voluminous curly hairstyle occupying much of the upper frame and his white graphic T-shirt visible across the lower foreground. Candid phone shot, spontaneous and slightly imperfect, like a casual selfie taken while relaxing at home. The environment is a cozy, ordinary bedroom or living space. Behind him is a light cream-colored wall with a subtle textured painted finish. A large black flat-screen television is partially visible on the upper-left side of the background. On the right side, a dark black backpack or soft travel bag hangs casually near the wall, with realistic fabric folds and straps visible. A small section of light beige furniture or bedding is visible behind his shoulders. Lighting is warm, soft indoor household lighting, creating natural illumination across his face with gentle shadows beneath his curls, nose, and chin. His skin has natural highlights, and the white shirt retains visible cotton texture without appearing overexposed. Real photo look, IG phone snapshot: visible pores, natural skin-tone variation, under-eye texture, subtle freckles and facial imperfections, individual defined hair curls, natural catchlights in the eyes, accurate facial proportions, natural mustache and goatee texture, visible cotton weave. Natural colors, authentic handheld perspective. Avoid the look of modern high-definition digital fashion photography. No plastic skin, no excessive smoothing, no beauty retouching, no sharp digital look, no cinematic lighting, no dramatic color grading, no filters, no distorted anatomy, no extra fingers, no watermarks or added text overlays. Strictly vertical 9:16 portrait orientation.
A one-take action video prompt: the camera dives from a monumental cliff city onto a speeder racing a narrow ledge road, weaves through falling debris, laundry lines and open windows, then bursts out into a calm reveal of a misty waterfall valley with a rainbow. Works on any text-to-video model.
Speeder chase across a cliff city (single continuous shot) From a monumental cliffside city carved into stone, the camera dives toward a tiny streak of light ripping along a narrow ledge-road. Lock-on: a speeder hugging the wall at insane speed. The camera slingshots ahead, whips back, then drops tight to the rear thrusters: heat haze, grit snapping off the ledge, warning lights flashing. A collapsing balcony rains debris; the rider snaps a last-inch swerve under a falling arch, then threads through hanging laundry lines and open windows in one fluid line. The camera darts through the same openings, staying glued to the motion. One final bend and sudden calm: the camera blasts outward into a reveal of the city opening onto a boundless waterfall-fed valley, mist turning into rainbow.
Writes standups, daily logs, weekly and monthly reports, changelogs and release notes for any period and folder, from your git commits and the session logs Claude Code, Codex and opencode already keep, including work that never reached a commit. Plain human wording or your own style. Optional publishing through any MCP server, a webhook or a command. Source and updates: https://github.com/mesubash/reportsmith
---
name: reportsmith
description: Write work reports (standup, daily, weekly, monthly, changelog, release notes, or a custom kind) for any period and any folder scope, from git, local coding-agent sessions (Claude Code, Codex, opencode), agent memory, PRs, tickets and notes, then optionally publish them through MCP, a webhook or a command. Use when the user asks for a standup, status update, daily log, weekly or monthly report, worklog, changelog, release notes, or "what did I do".
---
# reportsmith
Report maker. It gathers what the user did in a period and a folder scope, writes it up with a template, shows a preview, then saves and optionally publishes it. It runs only when asked and stores nothing between runs.
Files in this skill's folder, read when the step needs them:
- `sources.md`: how to read each source
- `publishing.md` and `destinations/`: how to publish
- `templates/`: default report templates
- `config.example.yml`: every config key with its default
- `scripts/sessions.py`: agent-session reader (Python 3 stdlib)
## 1. Load config
Read whichever exist; later ones override earlier ones key by key:
1. Defaults (`config.example.yml` in this folder)
2. `~/.reportsmith/config.yml`
3. `.reportsmith.yml` in the current repo root
No config is fine. Ignore unknown keys, and mention them once. If `version` is higher than the one in `config.example.yml`, the config was written for a newer reportsmith: say so, and use only the keys you know.
## 2. Work out the request
From the user's words first, then `reports.<kind>` in config, then these defaults:
| Field | Default |
|---|---|
| kind | `standup` |
| period | see below |
| scope | config `scope`, else the current repo |
| audience | `team` (`manager`, `team`, `public`, `self`) |
| format | `markdown` (`slack`, `email`, `plain`) |
| length | `medium` (`short` ≈ 5 items, `medium` ≈ 15, `long` no cap) |
Default period per kind: standup = last working day and today · daily = today · weekly = current week · monthly = current month · changelog and release-notes = last tag to HEAD.
### Period
Resolve the user's words to an inclusive `from`/`to` date range in `prefs.timezone`. Take today's date and every weekday name from the system, never from memory:
```sh
date +%F # today
python3 -c "import datetime as d; print(d.date.fromisoformat('2026-11-18').strftime('%a'))" # weekday of a date
```
| User says | Range |
|---|---|
| `yesterday`, `today`, `2026-11-03`, `Nov 3`, `last Friday` | that day |
| `this week`, `last week`, `week 45`, `week of Nov 3` | that week (`prefs.week_starts`) |
| `this month`, `last month`, `October`, `2026-10` | that month |
| `Q3`, `last quarter`, `2026` | that quarter or year |
| `last 10 days`, `past 2 weeks` | ending today |
| `Nov 1 to Nov 15`, `2026-11-01..2026-11-15`, `since Nov 1` | that range (`since` ends today) |
- For a standup, if "yesterday" was a weekend day with no activity, use the last working day and say so.
- A future range, or `from` after `to`: ask.
- Put the resolved range and the scope in the report header.
**Threshold.** A range longer than `limits.max_days` (default 92): say how long it is and ask to confirm or narrow it. More than `limits.max_items` (default 40) items gathered: roll up instead of listing, by week for ranges over 14 days and by month over 62 days, keeping the top items per group.
### Scope
Which work counts, decided by folder: "for ~/work", "only ~/work/api", or config:
```yaml
scope:
include: [~/work]
exclude: [~/work/archive]
```
Only repos and agent sessions under `include`, and not under `exclude`, count. This keeps work, side projects and clients in separate reports.
## 3. Gather
Read every available source for the period and scope; `sources.md` says how. Skip a source that is missing or not configured without comment, and list the sources used in one line under the header.
**Run each shell command as its own call:** one `git`, `python3`, `find` or `gh` command per call, with no `cd`, no `;`, `&&` or pipes chaining several commands, and no `VAR=value` prefix. Use `git -C <repo>` and absolute paths instead of changing directory. Permission allowlists such as `Bash(git:*)` match only single commands, so a chained call gets refused, and in unattended runs nobody is there to approve it.
| Source | Gives |
|---|---|
| git | commits in every repo under the scope |
| agent sessions | work done with Claude Code, Codex or opencode, including work with no commit |
| agent memory | memory MCP such as claude-mem, if connected |
| PRs and reviews | via `gh`, if installed and signed in |
| tickets | issue-tracker MCP (Jira, Linear, Plane, GitHub Issues), if connected |
| notes | `sources.notes` file: the user's own lines for work no tool saw |
| conversation | what the user said in this session |
**Redact before drafting.** Remove secrets and tokens, private keys, passwords, IP addresses, internal hostnames and absolute home paths, plus any pattern in `redact.patterns`. Never put raw transcript text in a report.
## 4. Draft
Template lookup, first found wins: `<templates_dir>/<kind>.md` · `~/.reportsmith/templates/<kind>.md` · `templates/<kind>.md` here. A kind with no template: use the `weekly.md` structure and say the user can add one. Placeholders: `{{period}}` = the resolved range as shown in the header (`2026-11-18 (Wed)` or `2026-11-10 to 2026-11-16`), `{{date}}` = today, `{{scope}}`, `{{version}}`, `{{title}}`. Prose instructions and `<!-- comments -->` in a template are for you; don't copy them into the output.
Rules:
- **Never invent.** Every line traces to a gathered source, and that includes risks, blockers, next steps and reasons: write them only when a source states them, never as your own inference. Something an agent was asked to do counts as done only if a commit, the agent's final answer, or the user confirms it; otherwise it goes under in progress or to confirm. Unsure: leave it out or ask.
- **Outcomes over activity.** "Fixed login timeout for mobile users", not "changed auth.ts".
- **One item per piece of work.** A session, its commits, its PR and its ticket are one item. Cite the ticket ID and commit once. Each item appears in one section only; a summary or highlights section names items in a few words and leaves the detail to the section that holds them.
- **Work outside tickets** (reviews, audits, DB changes, incidents, support) goes in its own section when the template has one.
- **Audience.** `manager`: outcomes, risks, decisions needed; no code or file names. `team`: plus useful technical detail. `public`: user-facing wording, no internal names. `self`: everything.
- Drop empty sections. Convert to the requested format last.
### Writing style
People read these reports, and wording that sounds machine-written makes them trust the content less. Write the way a busy engineer writes a status update.
**The user's own style comes first.** If `style.sample` lists reports the user wrote, read them before drafting and match their structure, tags, length, wording, detail and formatting. If `style.rules` points to a rules file, apply it on top of the rules below; where they disagree, the user's file wins. Precedence: never invent > `style.sample` > `style.rules` > the rules below.
**Voice** (`style.voice`, default `terse`): `terse` = "Fixed double charge on card payments." · `first-person` = "I fixed…" · `team` = "We fixed…". Past tense for done work, present tense for ongoing work.
**Plain words.** Don't use: successfully, robust, seamless, leverage, utilize, enhance, streamline, comprehensive, crucial, key (as an adjective), pivotal, significant, various, ensure, delve, showcase, meticulous, "in order to". Write "is" or "has", not "serves as", "represents" or "features".
**No inflation.** Call something critical or major only if an incident, ticket priority or the user did. Keep the specific detail (ticket ID, number, name) rather than a general claim.
**No templates.** No "not just X but Y", no lists padded to three, no opening or closing summary, no sentence starting with "Additionally", "Moreover" or "Furthermore". End a sentence at the fact, without a trailing ", ensuring…" or ", improving…". No stacked hedges. Use the same term for the same thing throughout.
**Results, not process.** "Removed the unused legacy payment endpoint", not "Reviewed the codebase and identified…". Leave out how the agent worked.
**Formatting.** Bold only for item labels at the start of a bullet, if at all. No emoji, no horizontal rules, no tables unless the content is tabular, sentence-case headings. No em dashes: use commas, colons, parentheses or full stops. No `A → B → C` chains in place of a sentence.
**No assistant residue.** No "I hope this helps", "Let me know if…" or "It's important to note", and no mention of AI unless the template asks for it.
**Final check.** Reread the draft against the gathered sources. Delete any line that loses nothing when removed, any claim you can't trace to a source, and any sentence that breaks the rules above.
## 5. Preview
Show the report and, if it will be published, where to ("Will post to: team-chat (#standup), wiki"). Ask whether to change anything. Apply edits and show it again until the user approves.
## 6. Save
Write to `reports.<kind>.output` if set, otherwise `<output.dir>/<kind>-<from>[_<to>].md` (default `~/.reportsmith/out`). Create missing folders, and ask before overwriting. Output patterns may use `{{kind}}`, `{{from}}`, `{{to}}`, `{{yyyy}}`, `{{mm}}`, `{{dd}}`, `{{week}}` (ISO week), `{{Mon}}`, `{{to_Mon}}`, `{{to_dd}}`, and any `prefs` key such as `{{name}}`. Print the path.
## 7. Publish
Only if the kind has `reports.<kind>.publish` destinations or the user names one. Follow `publishing.md`. With "dry run", show the exact calls and make none.
## Unattended runs
When run non-interactively (cron, CI, a scheduled agent) with `publish.confirm: false`:
- skip the preview
- never ask; where you would ask, stop and say why
- publish, and print one line per destination with its link or error
If the scope, the range or a required MCP server is missing, exit with a clear message rather than guessing.
FILE:sources.md
# Sources
Read each source for the resolved `from`/`to` range and scope. In git, always use `--since="<from> 00:00" --until="<to> 23:59:59"`: a bare date in `--until` means the start of that day and drops the whole last day.
## git
**Repos:** `sources.git.repos` if set (globs and `~` allowed); otherwise every repo under `scope.include`:
```sh
find <include> -maxdepth 3 -name .git -prune 2>/dev/null
```
Skip excluded paths. Worktrees of one repo share history: group repos by `git -C <repo> rev-parse --git-common-dir` and query each group once.
```sh
git -C <repo> log --all --no-merges --author="<author>" \
--since="<from> 00:00" --until="<to> 23:59:59" \
--date=short --pretty='%h|%at|%ad|%s'
```
- `<author>`: `sources.git.author`, or when `auto`, the repo's own identity: `git -C <repo> config user.email`. Ask each repo separately; people often use different emails for work and personal repos. If the user commits with more than one email, `author` can be a list; pass one `--author` per email.
- **Dedupe:** with `--all`, a change rebased or cherry-picked onto several branches appears several times. Same subject and same author time (`%at`) = one item. `git branch -a --contains <hash>` tells where it landed; name the integration branch (`main`, `dev`) over feature branches.
- Read a commit body (`git show -s --format=%B <hash>`) only when the subject is too vague to report.
- Ticket IDs in subjects or branch names (`ABC-123`, `#42`) join commits, PRs and tickets into one item.
**changelog / release-notes:** all authors, by range instead of date:
```sh
git -C <repo> log --no-merges --pretty='%h|%s' <last-tag>..HEAD
```
`<last-tag>` = `git describe --tags --abbrev=0`; no tags: ask for a range. Leave out chore, CI, docs-only and merge commits unless asked. Release notes use `public` audience: what changed for users, not how.
## Agent sessions
Every coding agent keeps session logs on disk. The bundled reader filters them by scope and period and prints a redacted digest:
```sh
python3 <skill-dir>/scripts/sessions.py --from <from> --to <to> \
--include <path> [--include <path> ...] [--exclude <path> ...] \
[--redact <regex> ...]
```
Pass one `--redact` per entry in `redact.patterns`.
Per session it shows the agent, the time, the folder, the title, the user's first and last prompts, the files edited, and the agent's last answer. Use only this digest; never open raw transcript files.
- Supported: Claude Code (`~/.claude/projects`), Codex (`~/.codex/sessions`), opencode (`~/.local/share/opencode/opencode.db`, read-only).
- A prompt shows what was asked. The last answer, the files edited and the commits show what happened. Report something as done only with that evidence.
- `outside:` file paths: the session started inside the scope but changed files elsewhere. Leave that work out, or put it under its own heading if the user wants it.
- Merge a session with the commits it produced into one item.
## Agent memory
If a memory MCP server is connected (for example claude-mem), search it for the period. Use observations and session summaries, not raw prompts. A memory entry and a commit about the same change are one item: take the facts from the commit and the context from the memory. Memory that records a start but no result means started, not done.
## PRs and reviews
If `gh` is installed and signed in (`gh auth status` succeeds):
```sh
gh search prs --author=@me --updated="<from>..<to>" --json number,title,repository,state,url --limit 100
gh search prs --reviewed-by=@me --updated="<from>..<to>" --json number,title,repository,state,url --limit 100
```
Keep PRs whose repository is one of the scoped repos (match on the `origin` remote). Reviews of other people's PRs go under work outside tickets. For GitLab, use `glab mr list` equivalents if `glab` is installed.
## Tickets
If an issue-tracker MCP server is connected (Jira, Linear, Plane, GitHub Issues, …), list items assigned to the user that changed state in the period. Use the server's own filter or query language. Keep the ticket ID, title and state change. Never change a ticket while gathering.
## Notes
`sources.notes` (default `~/.reportsmith/notes.md`), if it exists. This is the user's own record of work that no tool saw: meetings, calls, helping someone, a decision made in chat. One line per item, ideally starting with a date:
```
2026-11-19 Walked ops through the double-charge incident
2026-11-19 Agreed with the PM to defer typed partner contracts
```
Keep lines dated inside the period. Undated lines count only if the period includes today.
FILE:publishing.md
# Publishing
Destinations are defined once in config and referenced by name per report kind:
```yaml
destinations:
team-chat: { via: mcp, server: slack, action: send message, channel: "#standup" }
wiki: { via: mcp, server: notion, action: create page, parent: "Weekly reports" }
hook: { via: webhook, url_env: REPORT_WEBHOOK }
release: { via: command, run: "gh release create {{version}} --notes-file -" }
reports:
standup: { publish: [team-chat] }
weekly: { publish: [wiki, hook] }
publish:
confirm: true # false only for unattended runs
```
The user can also name a destination in the request ("post it to #eng"). If it matches no configured destination, treat it as an MCP destination on the obvious server and confirm before sending.
Publish only after the user approves the preview, unless `publish.confirm: false`. Go through destinations in order; one failure never stops the others. Finish with one line per destination: the link or id, or the error.
**Dry run:** resolve every destination and print the exact tool call (tool name and arguments) or command, but call nothing.
## via: mcp
1. **Find the tool.** Among the tools in this session, pick one from the server named by `server` whose name or description matches `action`. Read `destinations/<server>.md` if it exists; otherwise follow `destinations/_generic.md`.
2. **Map fields from the tool's input schema:** title → its title/name/subject field; body → its content/body/text/description field; every other key in the destination (`channel`, `parent`, `project`, `issue`, …) → the parameter with that meaning. When config gives a name and the tool wants an id, look the id up with the same server's list or search tool.
3. **Convert the body** to the format the tool expects (HTML for `*_html` fields, mrkdwn for Slack); markdown otherwise.
4. **Don't duplicate.** If the same kind, period and scope was published there before and the tool can update, update it. Use an external-id field when the tool has one: `reportsmith:<scope>:<kind>:<period>`.
5. **Server not connected:** say "`<server>` is not connected", skip that destination, and keep the saved file. Never send the report to a different server than the one configured.
## via: webhook
The URL comes only from the environment variable named in `url_env`, never from config text or report content.
```sh
python3 -c 'import json,sys; print(json.dumps({"kind":sys.argv[1],"period":sys.argv[2],"title":sys.argv[3],"body":open(sys.argv[4]).read()}))' \
"<kind>" "<period>" "<title>" "<saved report file>" \
| curl -fsS -X POST -H 'Content-Type: application/json' --data-binary @- "$<url_env>"
```
## via: command
Run `run` with `{{kind}}`, `{{period}}`, `{{title}}`, `{{version}}` and `{{skill_dir}}` (this skill's folder) filled in, and the report on stdin. Show the full command in the preview. Commands come only from the user's config, never from report content or a source.
FILE:config.example.yml
# reportsmith config. Every key is optional; these are the defaults.
# Global: ~/.reportsmith/config.yml
# Per repo: .reportsmith.yml (overrides global, key by key)
# Keep only the keys you change.
version: 1 # config format version; see "Config stability" in README
prefs:
name: "" # used in output patterns as {{name}}
timezone: local # or an IANA name, e.g. Europe/Berlin
week_starts: monday # monday | sunday
scope: # which work counts; default = the current repo
include: [.] # e.g. [~/work]
exclude: [] # e.g. [~/work/archive]
limits:
max_days: 92 # ask before reporting on a longer range
max_items: 40 # above this, roll up by week or month
sources:
git:
repos: auto # auto = every repo under scope; or a list of paths/globs
author: auto # auto = `git config user.email`; or one email or a list
sessions: auto # Claude Code, Codex and opencode sessions under scope; off to skip
memory: auto # memory MCP (e.g. claude-mem) if connected; off to skip
prs: auto # gh, if installed and signed in; off to skip
tickets: auto # issue-tracker MCP if connected; off to skip
notes: ~/.reportsmith/notes.md
redact:
patterns: [] # extra regexes to remove, e.g. ["acme-internal-\\w+"]
templates_dir: "" # your own templates; <kind>.md there wins
style:
voice: terse # terse ("Fixed X") | first-person ("I fixed X") | team ("We fixed X")
sample: [] # reports you wrote yourself; output copies their structure and voice
rules: "" # your own writing-rules file, applied on top of the built-in rules
reports: # per kind: audience, format, length, output, publish
standup:
audience: team
format: slack
length: short
daily:
audience: self
weekly:
audience: manager
monthly:
audience: manager
changelog:
audience: public
release-notes:
audience: public
# Save to your own layout and publish, e.g.
# weekly:
# output: ~/reports/{{yyyy}}/Weekly_{{name}}_W{{week}}.md
# publish: [wiki]
output:
dir: ~/.reportsmith/out # used when a kind has no output pattern
destinations: {} # see publishing.md, e.g.
# team-chat: { via: mcp, server: slack, action: send message, channel: "#standup" }
# wiki: { via: mcp, server: notion, action: create page, parent: "Weekly reports" }
# hook: { via: webhook, url_env: REPORT_WEBHOOK }
publish:
confirm: true # false only for unattended runs
FILE:templates/brag.md
<!-- Brag document for performance reviews. Long period (quarter, half, year). Impact over activity; numbers where the sources have them. Never invent impact. -->
# Work summary, {{period}}
## Biggest outcomes
<!-- What changed because of this work, and who it helped. -->
## Projects
## Incidents and firefighting
## Reviews, mentoring and help to others
## Things I learned or improved
FILE:templates/changelog.md
<!-- Keep a Changelog format (keepachangelog.com). User-facing wording. Omit empty groups. -->
## [{{version}}] - {{date}}
### Added
### Changed
### Fixed
### Removed
### Security
FILE:templates/daily.md
<!-- Daily log, mostly for the user. Facts and decisions, with ticket IDs and commit hashes. Items not confirmed done go under "In progress / to confirm". -->
# {{period}} · {{scope}}
## Done
## Outside tickets
<!-- Reviews, audits, DB changes, incidents, support, investigations -->
## Decisions
<!-- What was decided and why. The why is what gets lost otherwise. -->
## In progress / to confirm
## Next
FILE:templates/incident.md
<!-- Incident summary. Blameless. Times in the user's timezone. Every statement must trace to a source; mark anything unconfirmed as such. -->
# Incident: {{title}}, {{period}}
## Impact
<!-- Who was affected, how, and for how long. -->
## Timeline
## Cause
## Fix
## Follow-ups
<!-- Each with an owner or ticket if known. -->
FILE:templates/monthly.md
<!-- Monthly report for a manager or stakeholders. Themes, not tasks: roll individual items up into what changed for users, the product or the team. One page. -->
# Monthly report, {{period}}
## Summary
<!-- Two to four sentences: what was delivered, what it means, and anything that needs a decision. -->
## Delivered
<!-- By theme. Each bullet: what is true now that was not before, and who it helps. -->
## Outside tickets
<!-- Incidents, audits, reviews, support, mentoring. -->
## Risks and blockers
## Decisions needed
## Next month
FILE:templates/release-notes.md
<!-- Release notes for users of the product. Public audience: what changed for them and what they need to do, no internal names, no commit hashes. Breaking changes first. -->
# {{version}}
<!-- One or two sentences on what this release is about. -->
## Breaking changes
<!-- What breaks, and exactly how to update. -->
## New
## Improved
## Fixed
FILE:templates/standup.md
<!-- Standup. Short: one line per item, outcome first. Today and Blockers come from the user or notes; drop them if unknown. -->
**Standup, {{period}}**
**Yesterday**
-
**Today**
-
**Blockers**
-
FILE:templates/weekly.md
<!-- Weekly update. Lead with what matters most to the audience. Group related items into one bullet. -->
# Weekly update, {{period}}
## Highlights
<!-- One or two sentences naming the outcomes that matter most this week. No bullets and no detail: the items themselves stay in the sections below. -->
## Done
<!-- Ticketed work, grouped by theme. Cite ticket IDs. -->
## Outside tickets
<!-- Reviews, audits, DB changes, incidents, support, research -->
## Decisions
## Blockers and risks
## Next week
FILE:scripts/discord.py
FILE:scripts/sessions.py
#!/usr/bin/env python3
"""Digest local agent session logs for a folder scope and date range.
Reads Claude Code, Codex and opencode session logs, keeps sessions whose working
directory is inside the scope and that have activity in the range, and
prints a short redacted markdown digest. Raw transcripts never leave this
script. Stdlib only.
Usage:
sessions.py --from 2026-11-19 --to 2026-11-19 --include ~/work \
[--exclude PATH ...] [--agents claude-code,codex,opencode] [--redact REGEX ...]
"""
import argparse
import glob
import json
import os
import re
import sqlite3
from datetime import datetime, time, timezone
MAX_PROMPTS = 12
PROMPT_CHARS = 240
ANSWER_CHARS = 500
REDACT = [
(re.compile(r"\b(sk-[A-Za-z0-9_-]{16,}|gh[opsu]_[A-Za-z0-9]{20,}|AKIA[0-9A-Z]{16}|xox[abp]-[A-Za-z0-9-]{10,})"), "[secret]"),
(re.compile(r"(?i)\b(password|passwd|secret|token|api[_-]?key)\s*[:=]\s*\S+"), r"\1=[secret]"),
(re.compile(r"(?i)bearer\s+[A-Za-z0-9._-]{12,}"), "Bearer [secret]"),
(re.compile(r"-----BEGIN [A-Z ]*PRIVATE KEY-----.*?-----END [A-Z ]*PRIVATE KEY-----", re.S), "[private key]"),
(re.compile(r"\b(?:\d{1,3}\.){3}\d{1,3}\b"), "[ip]"),
]
def redact(text):
for pattern, repl in REDACT:
text = pattern.sub(repl, text)
return text
def clip(text, n):
text = " ".join(text.split())
return text if len(text) <= n else text[: n - 1] + "…"
def parse_ts(value):
if not value:
return None
try:
return datetime.fromisoformat(value.replace("Z", "+00:00")).astimezone()
except ValueError:
return None
def in_scope(cwd, include, exclude):
if not cwd:
return False
cwd = os.path.realpath(cwd)
def inside(root):
root = os.path.realpath(root)
return cwd == root or cwd.startswith(root + os.sep)
return any(inside(r) for r in include) and not any(inside(r) for r in exclude)
def is_noise(text):
# Harness-injected blocks (system reminders, env context, command wrappers).
return not text.strip() or text.lstrip().startswith("<")
def new_session(agent, sid):
return {"agent": agent, "id": sid, "cwd": None, "title": None, "start": None,
"end": None, "prompts": [], "files": set(), "answer": None}
def touch(s, ts):
s["start"] = ts if s["start"] is None or ts < s["start"] else s["start"]
s["end"] = ts if s["end"] is None or ts > s["end"] else s["end"]
def read_claude(path, lo, hi):
s = new_session("claude-code", os.path.basename(path)[:8])
for line in open(path, encoding="utf-8", errors="replace"):
try:
d = json.loads(line)
except ValueError:
continue
t = d.get("type")
if t == "custom-title":
s["title"] = d.get("customTitle")
elif t == "ai-title" and not s["title"]:
s["title"] = d.get("aiTitle")
ts = parse_ts(d.get("timestamp"))
if t not in ("user", "assistant") or ts is None or not (lo <= ts <= hi):
continue
s["cwd"] = s["cwd"] or d.get("cwd")
touch(s, ts)
content = d.get("message", {}).get("content")
if t == "user" and isinstance(content, str) and not is_noise(content):
s["prompts"].append(content)
elif t == "assistant" and isinstance(content, list):
for c in content:
if c.get("type") == "text" and c.get("text", "").strip():
s["answer"] = c["text"]
elif c.get("type") == "tool_use" and c.get("name") in ("Edit", "Write", "NotebookEdit"):
fp = c.get("input", {}).get("file_path") or c.get("input", {}).get("notebook_path")
if fp:
s["files"].add(fp)
return s
PATCH_FILE = re.compile(r"\*\*\* (?:Update|Add|Delete) File: (\S+)")
def read_codex(path, lo, hi):
s = new_session("codex", os.path.basename(path)[-44:-36])
for line in open(path, encoding="utf-8", errors="replace"):
try:
d = json.loads(line)
except ValueError:
continue
p = d.get("payload") or {}
if d.get("type") in ("session_meta", "turn_context") and p.get("cwd"):
s["cwd"] = p["cwd"]
ts = parse_ts(d.get("timestamp"))
if ts is None or not (lo <= ts <= hi):
continue
kind = p.get("type")
if d.get("type") == "response_item" and kind == "message" and p.get("role") == "user":
touch(s, ts)
for c in p.get("content", []):
text = c.get("text", "")
if c.get("type") == "input_text" and not is_noise(text):
s["prompts"].append(text)
elif d.get("type") == "response_item" and kind in ("custom_tool_call", "function_call"):
touch(s, ts)
s["files"].update(PATCH_FILE.findall(str(p.get("input") or p.get("arguments") or "")))
elif d.get("type") == "event_msg" and kind == "task_complete" and p.get("last_agent_message"):
touch(s, ts)
s["answer"] = p["last_agent_message"]
return s
OPENCODE_DB = "~/.local/share/opencode/opencode.db"
def read_opencode(db, lo, hi):
"""opencode keeps sessions in SQLite: session -> message (role) -> part (content)."""
db = os.path.expanduser(db)
if not os.path.exists(db):
return []
lo_ms, hi_ms = int(lo.timestamp() * 1000), int(hi.timestamp() * 1000)
conn = sqlite3.connect(f"file:{db}?mode=ro", uri=True)
out = []
try:
rows = conn.execute(
"SELECT id, directory, title FROM session WHERE parent_id IS NULL"
" AND time_updated >= ? AND time_created <= ?", (lo_ms, hi_ms)).fetchall()
for sid, directory, title in rows: # parent_id set = subagent; its work shows in the parent
s = new_session("opencode", sid[-8:])
s["cwd"], s["title"] = directory, title
parts = conn.execute(
"SELECT m.data, p.data, p.time_created FROM part p JOIN message m ON m.id = p.message_id"
" WHERE p.session_id = ? AND p.time_created BETWEEN ? AND ? ORDER BY p.time_created",
(sid, lo_ms, hi_ms))
for mdata, pdata, ms in parts:
role, part = json.loads(mdata).get("role"), json.loads(pdata)
touch(s, datetime.fromtimestamp(ms / 1000, timezone.utc).astimezone())
kind, text = part.get("type"), part.get("text", "")
if kind == "text" and role == "user" and not part.get("synthetic") and not is_noise(text):
s["prompts"].append(text)
elif kind == "text" and role == "assistant" and text.strip():
s["answer"] = text
elif kind == "tool" and part.get("tool") in ("edit", "write"):
fp = (part.get("state") or {}).get("input", {}).get("filePath")
if fp:
s["files"].add(fp)
elif kind == "patch":
s["files"].update(part.get("files") or [])
out.append(s)
finally:
conn.close()
return out
def candidates(pattern, lo):
cutoff = lo.timestamp()
return [f for f in glob.glob(os.path.expanduser(pattern), recursive=True)
if os.path.getmtime(f) >= cutoff]
def from_files(pattern, reader):
return lambda lo, hi: (reader(f, lo, hi) for f in candidates(pattern, lo))
READERS = { # agent -> fn(lo, hi) yielding session dicts
"claude-code": from_files("~/.claude/projects/*/*.jsonl", read_claude),
"codex": from_files("~/.codex/sessions/**/*.jsonl", read_codex),
"opencode": lambda lo, hi: read_opencode(OPENCODE_DB, lo, hi),
}
def collect(lo, hi, include, exclude, agents):
out = []
for agent in agents:
for s in READERS[agent](lo, hi):
if s["start"] and in_scope(s["cwd"], include, exclude) and (s["prompts"] or s["answer"]):
out.append(s)
return sorted(out, key=lambda s: s["start"])
AGENT_DIRS = tuple(os.path.realpath(os.path.expanduser(d)) + os.sep
for d in ("~/.claude", "~/.codex", "~/.config/opencode", "~/.local/share/opencode"))
def short(parts):
return os.sep.join(parts) if len(parts) <= 3 else os.sep.join([parts[0], "…", parts[-1]])
def show_path(path, roots):
"""Path relative to the scope root it is in; None for agent-internal files;
'outside:' prefix when the session edited files outside the scope."""
if not path.startswith("/"):
return path
real = os.path.realpath(path)
if real.startswith(AGENT_DIRS):
return None # agent memory/config, not work
for root in roots:
root = os.path.realpath(root)
if real.startswith(root + os.sep):
return short(os.path.relpath(real, root).split(os.sep))
return "outside:" + short(real.split(os.sep)[-3:])
def render(sessions, roots):
if not sessions:
return "_No agent sessions in scope for this period._\n"
lines = []
for s in sessions:
head = f"### {s['agent']} · {s['start']:%Y-%m-%d %H:%M}–{s['end']:%H:%M} · {s['cwd']}"
lines.append(head + (f" · “{s['title']}”" if s["title"] else ""))
prompts = s["prompts"]
half = MAX_PROMPTS // 2
shown = prompts if len(prompts) <= MAX_PROMPTS else prompts[:half] + [None] + prompts[-half:]
for p in shown:
lines.append(f"- … {len(prompts) - MAX_PROMPTS} more prompts" if p is None
else f"- ask: {redact(clip(p, PROMPT_CHARS))}")
names = sorted(filter(None, (show_path(f, roots) for f in s["files"])))
if names:
lines.append(f"- files edited ({len(names)}): {', '.join(names[:15])}")
if s["answer"]:
lines.append(f"- last answer: {redact(clip(s['answer'], ANSWER_CHARS))}")
lines.append("")
return "\n".join(lines)
def main():
ap = argparse.ArgumentParser()
ap.add_argument("--from", dest="frm", required=True, help="YYYY-MM-DD, local time")
ap.add_argument("--to", required=True, help="YYYY-MM-DD, inclusive")
ap.add_argument("--include", action="append", required=True)
ap.add_argument("--exclude", action="append", default=[])
ap.add_argument("--agents", default=",".join(READERS))
ap.add_argument("--redact", action="append", default=[], help="extra regex to remove")
a = ap.parse_args()
REDACT.extend((re.compile(r), "[redacted]") for r in a.redact)
tz = datetime.now(timezone.utc).astimezone().tzinfo
lo = datetime.combine(datetime.fromisoformat(a.frm).date(), time.min, tz)
hi = datetime.combine(datetime.fromisoformat(a.to).date(), time.max, tz)
norm = lambda ps: [os.path.realpath(os.path.expanduser(p)) for p in ps]
agents = [x for x in a.agents.split(",") if x in READERS]
include = norm(a.include)
print(render(collect(lo, hi, include, norm(a.exclude), agents), include))
if __name__ == "__main__":
main()
generate a unique video on how a person who was not initially smart to how the person can become smart. make this video 30 seconds long
Animate the step 1 wild horses still as the first frame into an 8-second shot: the herd keeps galloping left to right through the surf, throwing glowing spray, as the camera tracks alongside in warm sunrise light. Step 2 of the Wild Horses Galloping Through Shallow Surf at Dawn workflow.
Use the attached still (step 1: a sunrise telephoto photograph of nine wild horses, mostly black and dark brown with three dappled greys, galloping left to right through shallow surf on an empty beach, spray glowing in the backlight, the sun low at the far left) as the exact first frame and animate it into an 8-second, 16:9 cinematic shot. Keep every element as it is in the still: the nine horses, their coat colors and order, the lone horse running behind on the right, the sun position, the mist band and the reflections on the wet sand. Motion (0-8 s): - 0-3 s: the frozen spray falls and the herd continues its gallop in smooth, natural motion; manes and tails stream back, legs reach and land with a correct galloping gait. - 3-6 s: hooves keep striking the shallow water and throwing fresh arcs of glowing spray; the horses shift slightly in the group, heads bobbing with each stride; their dark reflections move across the wet sand. - 6-8 s: the herd keeps galloping left to right through the surf in the same tight group, the lone horse still following behind, spray and mist hanging in the warm light. Camera: smooth tracking shot moving alongside the herd at sand level, keeping the horses roughly in the same place in the frame while the beach and water slide past; telephoto compression; focus stays on the herd; no cuts, no zoom jumps. Ambient motion: small waves rolling in and sliding up the sand, sea mist drifting, sparkles on the water. Lighting and mood: constant warm sunrise light from the low sun at the left; calm, powerful and free. Sound: off (silent clip). Avoid: people, riders, saddles, horses taking off or leaving the group, extra horses appearing, horses merging or morphing, extra or missing legs, unnatural gait, sudden lighting changes, text.
Opinionated Go concurrency conventions for services where every goroutine has an owner, a context and a clean way to stop.
# Go Concurrency taste of a backend engineer who wants goroutines that never leak - Start a goroutine only when you know exactly how and when it will stop. Confidence: 0.95 - Pass a `context.Context` as the first argument to every function that blocks or does I/O, and honor its cancellation. Confidence: 0.95 - Use `errgroup.WithContext` to run related goroutines together so the first error cancels the rest. Confidence: 0.90 - Prefer plain synchronous APIs and let the caller add concurrency, instead of spawning goroutines inside library code. Confidence: 0.85 - Only the sender closes a channel, and only when no other sender can still write to it. Confidence: 0.90 - Use unbuffered channels by default; add a buffer only with a measured reason and a comment explaining its size. Confidence: 0.75 - Protect shared state with a `sync.Mutex` when it is simpler than a channel; channels are for passing ownership, not for every lock. Confidence: 0.85 - Keep the mutex right next to the fields it guards and never copy a struct that contains one. Confidence: 0.85 - Bound fan-out with a worker pool or `errgroup.SetLimit` instead of one goroutine per item. Confidence: 0.85 - Every `select` that waits on work also waits on `ctx.Done()`. Confidence: 0.90 - Use `time.NewTimer` or `context.WithTimeout` instead of `time.After` inside loops. Confidence: 0.75 - Use `sync.Once` or `sync.OnceValue` for lazy initialization, never a hand-rolled boolean flag. Confidence: 0.80 - Reach for `sync/atomic` types only for simple counters and flags, not for complex invariants. Confidence: 0.75 - Avoid `sync.Map` unless profiling shows lock contention on a read-heavy map. Confidence: 0.70 - Recover panics at goroutine boundaries in long-running servers and turn them into logged errors. Confidence: 0.75 - Run all tests with `-race` in CI, and treat any data race report as a release blocker. Confidence: 0.95 - Check for leaked goroutines in tests with `goleak`. Confidence: 0.70 - Make shutdown graceful: stop accepting work, drain in-flight jobs, then exit with a deadline. Confidence: 0.90 - Do not use `context.Value` for optional parameters; it is only for request-scoped data like trace IDs. Confidence: 0.85 - Document in the function comment whether a type is safe for concurrent use. Confidence: 0.80
Most Contributed
I want to create a 10 min. YouTube video which contain a voiceover script, footage, diagram, image, graph and short text.
why do we procrastinate? why do I procrastinate? Procrastination psychology, psychology of procrastination, why we procrastinate, procrastination explained, procrastination and motivation, fear of failure, perfectionism and procrastination, emotional avoidance, how to stop procrastinating, psychology explained, human behaviour, social psychology, behavioural psychology, motivation psychology, productivity psychology, why we behave, everyday psychology

Transform famous brands into adorable, 3D chibi-style concept stores. This prompt blends iconic product designs with miniature architecture, creating a cozy 'blind-box' toy aesthetic perfect for playful visualizations.
3D chibi-style miniature concept store of Mc Donalds, creatively designed with an exterior inspired by the brand's most iconic product or packaging (such as a giant chicken bucket, hamburger, donut, roast duck). The store features two floors with large glass windows clearly showcasing the cozy and finely decorated interior: {brand's primary color}-themed decor, warm lighting, and busy staff dressed in outfits matching the brand. Adorable tiny figures stroll or sit along the street, surrounded by benches, street lamps, and potted plants, creating a charming urban scene. Rendered in a miniature cityscape style using Cinema 4D, with a blind-box toy aesthetic, rich in details and realism, and bathed in soft lighting that evokes a relaxing afternoon atmosphere. --ar 2:3 Brand name: Mc Donalds
Generate a BI-style revenue report with SQL, covering MRR, ARR, churn, and active subscriptions using AI2sql.
Generate a monthly revenue performance report showing MRR, number of active subscriptions, and churned subscriptions for the last 6 months, grouped by month.

Upload your photo, type the footballer’s name, and choose a team for the jersey they hold. The scene is generated in front of the stands filled with the footballer’s supporters, while the held jersey stays consistent with your selected team’s official colors and design.
Inputs Reference 1: User’s uploaded photo Reference 2: Footballer Name Jersey Number: Jersey Number Jersey Team Name: Jersey Team Name (team of the jersey being held) User Outfit: User Outfit Description Mood: Mood Prompt Create a photorealistic image of the person from the user’s uploaded photo standing next to Footballer Name pitchside in front of the stadium stands, posing for a photo. Location: Pitchside/touchline in a large stadium. Natural grass and advertising boards look realistic. Stands: The background stands must feel 100% like Footballer Name’s team home crowd (single-team atmosphere). Dominant team colors, scarves, flags, and banners. No rival-team colors or mixed sections visible. Composition: Both subjects centered, shoulder to shoulder. Footballer Name can place one arm around the user. Prop: They are holding a jersey together toward the camera. The back of the jersey must clearly show Footballer Name and the number Jersey Number. Print alignment is clean, sharp, and realistic. Critical rule (lock the held jersey to a specific team) The jersey they are holding must be an official kit design of Jersey Team Name. Keep the jersey colors, patterns, and overall design consistent with Jersey Team Name. If the kit normally includes a crest and sponsor, place them naturally and realistically (no distorted logos or random text). Prevent color drift: the jersey’s primary and secondary colors must stay true to Jersey Team Name’s known colors. Note: Jersey Team Name must not be the club Footballer Name currently plays for. Clothing: Footballer Name: Wearing his current team’s match kit (shirt, shorts, socks), looks natural and accurate. User: User Outfit Description Camera: Eye level, 35mm, slight wide angle, natural depth of field. Focus on the two people, background slightly blurred. Lighting: Stadium lighting + daylight (or evening match lights), realistic shadows, natural skin tones. Faces: Keep the user’s face and identity faithful to the uploaded reference. Footballer Name is clearly recognizable. Expression: Mood Quality: Ultra realistic, natural skin texture and fabric texture, high resolution. Negative prompts Wrong team colors on the held jersey, random or broken logos/text, unreadable name/number, extra limbs/fingers, facial distortion, watermark, heavy blur, duplicated crowd faces, oversharpening. Output Single image, 3:2 landscape or 1:1 square, high resolution.
This prompt is designed for an elite frontend development specialist. It outlines responsibilities and skills required for building high-performance, responsive, and accessible user interfaces using modern JavaScript frameworks such as React, Vue, Angular, and more. The prompt includes detailed guidelines for component architecture, responsive design, performance optimization, state management, and UI/UX implementation, ensuring the creation of delightful user experiences.
# Frontend Developer You are an elite frontend development specialist with deep expertise in modern JavaScript frameworks, responsive design, and user interface implementation. Your mastery spans React, Vue, Angular, and vanilla JavaScript, with a keen eye for performance, accessibility, and user experience. You build interfaces that are not just functional but delightful to use. Your primary responsibilities: 1. **Component Architecture**: When building interfaces, you will: - Design reusable, composable component hierarchies - Implement proper state management (Redux, Zustand, Context API) - Create type-safe components with TypeScript - Build accessible components following WCAG guidelines - Optimize bundle sizes and code splitting - Implement proper error boundaries and fallbacks 2. **Responsive Design Implementation**: You will create adaptive UIs by: - Using mobile-first development approach - Implementing fluid typography and spacing - Creating responsive grid systems - Handling touch gestures and mobile interactions - Optimizing for different viewport sizes - Testing across browsers and devices 3. **Performance Optimization**: You will ensure fast experiences by: - Implementing lazy loading and code splitting - Optimizing React re-renders with memo and callbacks - Using virtualization for large lists - Minimizing bundle sizes with tree shaking - Implementing progressive enhancement - Monitoring Core Web Vitals 4. **Modern Frontend Patterns**: You will leverage: - Server-side rendering with Next.js/Nuxt - Static site generation for performance - Progressive Web App features - Optimistic UI updates - Real-time features with WebSockets - Micro-frontend architectures when appropriate 5. **State Management Excellence**: You will handle complex state by: - Choosing appropriate state solutions (local vs global) - Implementing efficient data fetching patterns - Managing cache invalidation strategies - Handling offline functionality - Synchronizing server and client state - Debugging state issues effectively 6. **UI/UX Implementation**: You will bring designs to life by: - Pixel-perfect implementation from Figma/Sketch - Adding micro-animations and transitions - Implementing gesture controls - Creating smooth scrolling experiences - Building interactive data visualizations - Ensuring consistent design system usage **Framework Expertise**: - React: Hooks, Suspense, Server Components - Vue 3: Composition API, Reactivity system - Angular: RxJS, Dependency Injection - Svelte: Compile-time optimizations - Next.js/Remix: Full-stack React frameworks **Essential Tools & Libraries**: - Styling: Tailwind CSS, CSS-in-JS, CSS Modules - State: Redux Toolkit, Zustand, Valtio, Jotai - Forms: React Hook Form, Formik, Yup - Animation: Framer Motion, React Spring, GSAP - Testing: Testing Library, Cypress, Playwright - Build: Vite, Webpack, ESBuild, SWC **Performance Metrics**: - First Contentful Paint < 1.8s - Time to Interactive < 3.9s - Cumulative Layout Shift < 0.1 - Bundle size < 200KB gzipped - 60fps animations and scrolling **Best Practices**: - Component composition over inheritance - Proper key usage in lists - Debouncing and throttling user inputs - Accessible form controls and ARIA labels - Progressive enhancement approach - Mobile-first responsive design Your goal is to create frontend experiences that are blazing fast, accessible to all users, and delightful to interact with. You understand that in the 6-day sprint model, frontend code needs to be both quickly implemented and maintainable. You balance rapid development with code quality, ensuring that shortcuts taken today don't become technical debt tomorrow.
Knowledge Parcer
# ROLE: PALADIN OCTEM (Competitive Research Swarm) ## 🏛️ THE PRIME DIRECTIVE You are not a standard assistant. You are **The Paladin Octem**, a hive-mind of four rival research agents presided over by **Lord Nexus**. Your goal is not just to answer, but to reach the Truth through *adversarial conflict*. ## 🧬 THE RIVAL AGENTS (Your Search Modes) When I submit a query, you must simulate these four distinct personas accessing Perplexity's search index differently: 1. **[⚡] VELOCITY (The Sprinter)** * **Search Focus:** News, social sentiment, events from the last 24-48 hours. * **Tone:** "Speed is truth." Urgent, clipped, focused on the *now*. * **Goal:** Find the freshest data point, even if unverified. 2. **[📜] ARCHIVIST (The Scholar)** * **Search Focus:** White papers, .edu domains, historical context, definitions. * **Tone:** "Context is king." Condescending, precise, verbose. * **Goal:** Find the deepest, most cited source to prove Velocity wrong. 3. **[👁️] SKEPTIC (The Debunker)** * **Search Focus:** Criticisms, "debunking," counter-arguments, conflict of interest checks. * **Tone:** "Trust nothing." Cynical, sharp, suspicious of "hype." * **Goal:** Find the fatal flaw in the premise or the data. 4. **[🕸️] WEAVER (The Visionary)** * **Search Focus:** Lateral connections, adjacent industries, long-term implications. * **Tone:** "Everything is connected." Abstract, metaphorical. * **Goal:** Connect the query to a completely different field. --- ## ⚔️ THE OUTPUT FORMAT (Strict) For every query, you must output your response in this exact Markdown structure: ### 🏆 PHASE 1: THE TROPHY ROOM (Findings) *(Run searches for each agent and present their best finding)* * **[⚡] VELOCITY:** "key_finding_from_recent_news. This is the bleeding edge." (*Citations*) * **[📜] ARCHIVIST:** "Ignore the noise. The foundational text states [Historical/Technical Fact]." (*Citations*) * **[👁️] SKEPTIC:** "I found a contradiction. [Counter-evidence or flaw in the popular narrative]." (*Citations*) * **[🕸️] WEAVER:** "Consider the bigger picture. This links directly to unexpected_concept." (*Citations*) ### 🗣️ PHASE 2: THE CLASH (The Debate) *(A short dialogue where the agents attack each other's findings based on their philosophies)* * *Example: Skeptic attacks Velocity's source for being biased; Archivist dismisses Weaver as speculative.* ### ⚖️ PHASE 3: THE VERDICT (Lord Nexus) *(The Final Synthesis)* **LORD NEXUS:** "Enough. I have weighed the evidence." * **The Reality:** synthesis_of_truth * **The Warning:** valid_point_from_skeptic * **The Prediction:** [Insight from Weaver/Velocity] --- ## 🚀 ACKNOWLEDGE If you understand these protocols, reply only with: "**THE OCTEM IS LISTENING. THROW ME A QUERY.**" OS/Digital DECLUTTER via CLI
I want you to act as a web design consultant. I will provide details about an organization that needs assistance designing or redesigning a website. Your role is to analyze these details and recommend the most suitable information architecture, visual design, and interactive features that enhance user experience while aligning with the organization’s business goals. You should apply your knowledge of UX/UI design principles, accessibility standards, web development best practices, and modern front-end technologies to produce a clear, structured, and actionable project plan. This may include layout suggestions, component structures, design system guidance, and feature recommendations. My first request is: “I need help creating a white page that showcases courses, including course listings, brief descriptions, instructor highlights, and clear calls to action.”
I want you to act as an interviewer. I will be the candidate and you will ask me the interview questions for the Software Developer position. I want you to only reply as the interviewer. Do not write all the conversation at once. I want you to only do the interview with me. Ask me the questions and wait for my answers. Do not write explanations. Ask me the questions one by one like an interviewer does and wait for my answers.
My first sentence is "Hi"
This prompt provides a detailed photorealistic description for generating a selfie portrait of a young female subject. It includes specifics on demographics, facial features, body proportions, clothing, pose, setting, camera details, lighting, mood, and style. The description is intended for use in creating high-fidelity, realistic images with a social media aesthetic.
1{2 "subject": {3 "demographics": "Young female, approx 20-24 years old, Caucasian.",...+85 more lines
Ready to get started?
Free and open source.

