Menu
O SkillsMP coletou 17 skills de dhanesh/agent-skills. Abra uma skill para revisar a origem e os detalhes.
Mostrando 17 de 17 skills coletadas.
Walk a person through a subject, codebase, whitepaper, or complex system until they genuinely understand it. Use whenever the user wants to understand or learn something: "explain X", "walk me through this repo/paper", "help me understand how Y works",…
Idioma do texto original: inglês
Design and build sound self-prompting loops — loops where a model iterates toward a goal across turns (draft→critique→revise, autonomous task loops, multi-agent orchestration, human-checkpointed loops). Use whenever the user wants to make a model "keep…
Idioma do texto original: inglês
One-time SETUP that installs durable context management into a Claude Code project (or global ~/.claude): a bounded, scored, tiered cache that keeps working memory lean (anti-bloat) and rot-proof across compactions (anti-rot). Use when setting up, installing,…
Idioma do texto original: inglês
One-time SETUP: installs a persistent SQLite-backed WORLD MODEL for a coding agent into a project (or global ~/.claude). Use when the user wants an agent to remember a codebase across sessions, detect contradictions, propose fixes, and improve correctness…
Idioma do texto original: inglês
Run a code migration (language port, framework/SDK upgrade, service rewrite) as an operating model — rulebook + queues + reviewers + objective verification — instead of a pile of agent edits. Use when the user says "migrate this service", "port X to Y",…
Idioma do texto original: inglês
Scaffold or extend a decision-oriented Astro + Starlight documentation handbook. Use when standing up a new handbook/knowledge-base site from scratch, or when adding a cluster (a group of topics) or a single topic page to an existing site that already follows…
Idioma do texto original: inglês
Turn any Open Knowledge Format (OKF v0.1) bundle into a beautiful, browsable static website. Use when the user wants to publish, browse, view, share, or "make a site from" an OKF bundle / knowledge folder / agent-readable markdown wiki — e.g. "generate a site…
Idioma do texto original: inglês
Adds a tmux-based agent cockpit with Zellij-like human ergonomics and Herdr-like agent supervision. Use when converting local tmux into a coding-agent workspace with menus, dashboard, pane navigation, per-agent status detection (Claude Code, Codex, Gemini,…
Idioma do texto original: inglês
Generate a runnable mockstar mock server for a service from its specs and docs. Use when asked to mock a service, stand up a fake/stub API, create mockstar mocks/fixtures, or scaffold a mock backend from an API spec or documentation. Accepts OpenAPI…
Idioma do texto original: inglês
Read-only audit that scores how ready a repository is for coding agents to work in safely and successfully, then optionally installs the missing rails. Use when asked "is our repo ready for agents / Claude Code / a background coding agent?", "why do agents…
Idioma do texto original: inglês
Research-grounded, read-only audit that validates a repository's codebase, architecture, and business logic against real-world knowledge from authoritative sources (arxiv, PubMed, Google Scholar, JSTOR, OpenAlex, Crossref, Semantic Scholar) plus standards…
Idioma do texto original: inglês
Read-only, offline audit of a repository's security hygiene posture: deterministic checks for unpinned dependencies (requirements/package.json/Dockerfile), committed .env/.pem/id_rsa files, hardcoded debug and wildcard-CORS flags, plain-http transports and…
Idioma do texto original: inglês
Turn a fuzzy feature request into a testable spec, then into a verifier-anchored task plan — every requirement a falsifiable must-statement, every task naming the check that proves it done. Use when the user says "plan this feature", "write a spec for X",…
Idioma do texto original: inglês
Trace a defect or incident that already happened end-to-end — trigger, propagation, detection, fix — and capture a blameless, evidence-cited post-mortem the next engineer can learn from, persisted as a Postmortem concept in the same Open Knowledge Format…
Idioma do texto original: inglês
Keep Open Knowledge Format (OKF v0.1) knowledge bundles alive: sweep one or more knowledge roots, detect subjects whose pinned sources have drifted, drive diff-aware refreshes, re-pin fingerprints, and regenerate any published site. Use when the user wants to…
Idioma do texto original: inglês
Scaffold, author, and review a new gate-passing Agent Skill for this repo (or any repo vendoring its quality gates): generate a standards-complete skeleton, write the real prompt over it, run the semantic review the mechanical gates cannot, and iterate the…
Idioma do texto original: inglês
Installs the runnable-verifier loop — format/build/test commands plus a CI workflow that runs them — into a repo that lacks it, turning agent-ready-rails' top finding (weak R1/R2 rails) into working files. Use when someone says "this repo has no tests or CI",…
Idioma do texto original: inglês