scoring-agent-skills
Score or compare one or more agent skills across trigger clarity, workflow actionability, safety boundaries, verification rigor, incremental knowledge value,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,657 results
triage
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
zotero-rag
Semantic search across your project's local library (library/markdown/). Index papers, search by meaning, find similar passages, and get expanded context.…
agentwiki
Drive the AgentWiki knowledge platform via its CLI (`@aiagentwiki/cli`, command `agentwiki`) and MCP server (`https://api.agentwiki.cc/mcp`). Use this skill…
code-best-practices
(NS) Security, compatibility, and modern web quality pass — headers, CSP, dependencies, accessibility baselines, and pragmatic modernization. Use when the user…
code-import
Read an existing repository's structure into the project cwd as a normalised snapshot the agent can analyse without re-walking the tree on every turn.
handoff
Push the run's accepted artifact to a downstream collaboration surface (cli, other code agents, cloud, desktop) and stamp the artifact manifest with the export…
todo-write
TodoWrite-driven plan that the agent commits to before generation.
lazy-agent-loader
Load agent definitions on-demand to reduce context usage. Only loads full agent when needed.
lazy-agent-loader
Load agent definitions on-demand to reduce context usage. Only loads full agent when needed.
coverage-report
Generate a .NET code coverage report scoped to files changed in the current branch. Runs tests with coverage collection and produces filtered HTML reports.
improve-agents-md
Write, audit, and improve AGENTS.md files for AI coding agents. Use when creating or improving agent context for a codebase.
cluster
Use for work with two or more independently owned workstreams that need coordinated integration.
bootstrap-agents-md
Bootstrap a repository's AI coding agent operating system — AGENTS.md, CLAUDE.md, docs/agents (architecture, code-style, lessons-learned), docs/plans,…
qdrant-codebase-search
Russian-language guide on semantic codebase search via Qdrant + Ollama. MCP server `@mhalder/qdrant-mcp-server`: AST-aware indexing…
hermes-atropos-environments
Build, test, and debug Hermes Agent RL environments for Atropos training. Covers the HermesAgentBaseEnv interface, reward functions, agent loop integration,…
peft
Fine-tune large LLMs with LoRA on limited GPU memory.
setup-review-sandbox
One-time setup of the sandbox prerequisites used by the reproduce-issue skill and the reproduce-verifier agent — Docker, the isolation runtime (gVisor on Linux…
mcp-server-builder
Build Model Context Protocol (MCP) servers with best practices. Generate production-ready MCP servers in Python or TypeScript with tools, resources, and…
disk-reduction
Reclaim disk on the maintainer's Mac when the volume is full or filling — ENOSPC, "no space left on device", a failed build or agent harness, or a routine…
brucelee-perspective
Bruce Lee's Jeet Kune Do philosophy and wisdom of self-transcendence. Based on in-depth research from 30+ sources including The Tao of Jeet Kune Do, Bruce Lee's personal notes and letters, annotations in Bruce Lee's library books, Linda Lee Cadwell's Bruce Lee: The Man Only I Knew, John Little's The Warrior Within: The Philosophies of Bruce Lee, etc., distilling 5 core thought models, 7 life heuristics, and a complete expression DNA. Purpose: to serve as a thinking advisor, using Bruce Lee's perspective to analyze self-transcendence, removing redundancy, creativity, personal...
dongmingzhu-perspective
A mental model from the perspective of Dong Mingzhu's iron-lady management style and obsession with quality. Use when the user explicitly requests this person's perspective, mentions "dongmingzhu-perspective", or wants to apply her core methods to analyze a problem; do not trigger automatically for general questions.
clinical-delegation
How to delegate clinical tasks to specialist agents. Always use sub-agent runtime with explicit agentId — never ACP. Never call FHIR via web_fetch.
agent-debug-ci
Investigate failed scheduled or nightly GitHub Actions runs on the default branch, determine whether the failure is reproducible and repository-owned,…