Photoreal Arctic evening landscape from water level: a tall white and deep-blue tidewater glacier front with crevasses and a leaning ice tower near the center, snow-patched dark mountains under a pink-gold sky, and a glassy turquoise fjord with small icebergs and seabirds on a floe. Step 1 of the Glacier Calving into a Turquoise Arctic Fjord workflow.
Photorealistic wide landscape of a tidewater glacier meeting a calm turquoise fjord in the soft light of an Arctic summer evening. A tall, jagged glacier front of white and deep-blue ice with vertical crevasses and seracs fills the middle of the frame from left to right, its face about forty meters high, with one large leaning ice tower near the center that looks ready to fall. Dark rocky mountains with patches of snow rise behind the glacier under a pale pink and gold sky with thin high clouds. In the foreground, still glassy water reflects the ice wall, with a scatter of small floating icebergs and brash ice; a few seabirds rest on a floe on the right. Golden low sun from the right rims the ice in warm light while the shadows stay cool blue. Camera: shot from a small boat at water level, 35 mm lens, f/8, deep focus, cinematic 16:9 composition with the glacier front across the middle third and open water in the lower third. Crisp ice texture, natural colors, subtle haze over the mountains. Avoid: people, boats in frame, buildings, text, watermarks, oversaturated colors.
Plans a day hike leg by leg. Estimates time with Naismith's rule and Langmuir's descent corrections, adjusted for terrain, fitness, pack weight and breaks, gives clock times for each leg, checks the finish against sunset and the latest safe start, and works out water to carry between refills and snacks to pack. Flags after-dark finishes, long dry stretches and hard terrain late in the day. Includes a stdlib Python planner with --self-test.
A disciplined implementation workflow for coding agents. Guides agents to inspect repository state before editing, preserve unrelated changes, plan substantial work before implementation, keep changes narrowly scoped, run relevant verification, and create concern-scoped commits only when authorized. Designed for implementation, bug fixing, refactoring, and remediation tasks across software projects.
A read-only maintenance audit workflow for Agent Skills. Reviews existing skills for stale or version-sensitive guidance, trigger conflicts, overlap, broken references, unsafe helper behavior, specification drift, context bloat, and outdated technology assumptions. Verifies material freshness claims against authoritative sources and reports only evidence-backed maintenance findings without modifying the audited skills.