Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Skill "game-ai-patterns" from HermeticOrmus/LibreGameDev-Claude-Code, covering game ai patterns, behavior tree node types, composite nodes, sequence: all children must succeed (and) and selector: first child to succeed wins (or).
Autonomous ML research loop. Handles initialization (interactive dataset scan, EDA, user interview, strategy planning) and autonomous iteration (hypothesis selection, experiment execution via worker agent, state updates). Use when the user says "start research", "auto research", "run ML research", "initialize…
Audit and fix accessibility issues in React/Next.js components — WCAG compliance, ARIA patterns, keyboard navigation, color contrast, screen reader support, and semantic HTML. Use this skill whenever the user asks about accessibility, a11y, WCAG compliance, screen reader support, keyboard navigation, focus management…
Research, evaluate, and systematically document tools/resources for an awesome- curated list, then publish to a public GitHub repo. Use when: building or expanding an awesome list (e.g. awesome-llm-token-reduction); finding tools, libraries, papers, or datasets on a topic; auditing an existing list for dead links or…
This skill should be used when the user asks to "create an animation", "make a manim video", "animate this concept", "visualize this process", "create a GIF for my blog", "plot a graph", "animate a value", or mentions "manim", "mathematical animation", "code animation", "process visualization", "technical animation"…
Use when starting or closing an agent session, routing durable repository facts, maintaining status or task state, recording bugs, validating handoff conformance, or reconciling an older handoff layout.
Use when starting debugging, planning features, encountering errors, making design decisions, or working in unfamiliar code. Searches past solutions and engineering principles captured by compound-capture to surface institutional knowledge and prevent repeated mistakes. Trigger phrases include "have we seen this…
Build, author, or improve a Claude skill that transfers real domain expertise. Use when creating a skill from authoritative docs, distilling documentation into LLM-digestible guidance, deciding what belongs in a skill, or proving a skill actually improves output. Covers the…
Create a new release of tmux-scout-golang. Use this skill whenever the user asks to cut a release, create a new version, bump the version, tag a release, or ship a new version of this project.
Use when the user wants to critically review and refactor an existing DSO skill for clarity, token efficiency, and reliability — includes script relocation, reference updates, change-detector test removal, and ticket reconciliation. Invoke when the user says "review the [skill] skill", "optimize [skill]", "clean up…
Expert startup advisor with deep knowledge of Y Combinator principles, successful unicorn strategies, and building high-impact billion-dollar companies.
Search and inspect datasets in the Norwegian Marine Data Centre (NMDC, metadata.nmdc.no) — natural-language queries by keyword, provider, geography, and period; dataset detail views with file lists and on-demand link/size probing; and feasibility advice for ingesting NMDC data into the Ocean Data Platform (ODP).…
Consent-gated webcam access so the agent can see a single still frame from the user's camera while the user watches a live preview. NO VIDEO CAPTURE — every frame on disk is an explicit, on-demand PNG. Use for hardware testing, OCR, plant logs, posture coaching, instrument reading. Includes adjust for tweaking camera…
A web-search tool that finds current information on the internet through the DuckDuckGo search API.
★not rated 6 6mo agoA0 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: