Agent skills directory

Resolve Claude/Codex skill files by name when neither the user nor the current session catalog identifies the artifact....

BM25-based skill retrieval plugin for Hermes Agent. Replaces the full skill list in the system prompt with a names-only...

Semantic search over skill libraries using ColBERT embeddings. Use when:- "find a skill for..." or "search for skills th...

Audit claude-skills with systematic 9-phase review: standards compliance, official docs verification, code accuracy, cro...

Adversarial review and evidence-based overhaul of an agent skill (SKILL.md + references). Fans out reviewers with distin...

Use this skill when reviewing a Coupler.io skill before merge, auditing an existing one, or checking a pack of skills fo...

Reviews and validates agent skills against best practices. Triggers on "review this skill", "check my skill", "validate...

Inspect, safely test, and assess one Runx skill package for capability, trust, and operator readiness. Use when deciding...

Deep behavioral audit of a Lattice skill — proposes 3 review personas relevant to the skill, runs independent scenario a...

Deep vetting workflow for third-party SKILL.md packages before they enter an agent runtime: provenance, instruction-leve...

Review and ensure skills maintain high quality standards. Use when creating new skills, updating existing skills, or aud...

Use when reviewing, auditing, or optimizing skills — validates against the 7 Skill Killers checklist and produces fix re...

既存スキルの品質をレビューし、改善提案を行うスキル。 以下の状況で使用: (1) ユーザーが「[スキル名]をレビューして」「[スキル名]の品質を確認して」と依頼した時 (2) ユーザーが明示的に「/skill-reviewer」を実行した時...

Audit AI skill files or skill folders for security risks before installing. Reads SKILL.md and related metadata, checks...

Review skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, and repo conventions...

Evaluates skill effectiveness, suggests improvements to instructions, identifies missing edge cases, and recommends stru...

Skill 评审 / Skill 审计：当用户要检查、评审、优化 Codex/Agent Skill 或 SKILL.md 时使用。 可用中文唤起：“帮我 review 这个 Skill”“检查这个 SKILL.md”“这个能力适不适合做成...

Audit an existing processkit skill against the 5 Skill Killers, the Agent Skills standard, and Anthropic's troubleshooti...

This skill should be used when reviewing, auditing, or improving existing Claude Code skills to ensure they follow Anthr...

Comprehensive review of Claude Code skills and agents against v0.5 guidelines. Validates metadata, implementation, and a...

Given a problem description, identify and sequence the most relevant skills from this library. Acts as the meta-orchestr...

Select the 1-2 most relevant @booklib/skills for a given file, PR, or task. Use before applying any skill when unsure wh...

This skill should be used when the user has a vague or cross-domain request and asks "which skill should I use", "is the...

Find an installed skill in the skill library, a folder of skills kept outside the harness's discovery path so their desc...

Use when picking which skill to invoke and more than one could apply, when a task spans several domains, or when the use...

Use when a [skill-router] route card appears in the turn, when no card appeared on a non-trivial task, or when a route l...

· Route user requests to the right installed skill with minimal loading. Triggers: 'which skill', 'skill routing', 'choo...

Analyzes tasks to find the optimal workflow of skills, presents the recommended sequence with rationale, and lets user a...

Legacy entrypoint; routing moved to mvp-mode.

Use when unsure which skill or command fits a task, when two seem to overlap, or when the user asks what skills or comma...

Activate once per session to route substantive requests to the right installed skill. Two modes: suggest (interactive, r...

ÚSAME PRIMERO en cualquier tarea no trivial: árbol de decisión que dice qué skill y sección leer (UI: ui-ux-pro-max; ani...

The index of every pro-workflow skill and command, grouped by job, with when to reach for each and whether it is human-r...

Meta-enforcement layer that routes EVERY agent action through the correct skill. MUST check this routing table before AN...

Use when the user is unsure which skill to use or where to start. Interviews the user with targeted questions and recomm...

Select and coordinate Codex skills when several skills, plugins, agents, or workflows could apply to the same user reque...

Route development tasks to the right Codex skill or skill sequence before execution. Use when the user gives a developme...

Route rough user tasks to the best available Codex skill with minimal token use, maintain a lightweight local skill inde...

Match a user request to the right skill using trigger matching, project context, and conversation history. Score ambigui...

Measures whether realistic prompts select the intended skills and reveals adjacent candidates that are confused or over-...

Review a skill-requested filesystem, command, network, secret, or destructive action against an explicit sandbox policy...

A QA sample skill. Use when the user asks to use skill-sample.

Pre-share leak scanner for Claude Code skills (or any folder). Scans BEFORE you publish for secrets (API keys, tokens, p...

cheat-on-skill 的核心。连 BOSS 直聘真实招聘数据 + 网页信号，按用户能力画像找「高薪 × 你学得动 × AI 增强」交集里的候选岗位。每个岗位给：薪资量级 / 需求热度 / 你的差距 / 可学性分 / 诚实学习周期，并...

Load when creating, auditing, refactoring, or repairing an Agent Skill for reuse, governance, and runtime efficiency.

Canonical classification for every skill in the library — permanent-pinned (universal or stack-conditional, decided once...

创建新 Skill 前先搜索已有的本地、市场、GitHub 及网络 Skill 资源——当用户要创建、构建、Fork 或查找工作流 Skill 时使用

Search existing local, marketplace, GitHub, and web skill sources before creating a new skill. Use when the user wants t...

将需要技能选型的任务完善为执行方案：按需澄清、编号推荐、说明工作流并确认执行。用于找技能、比较技能或存在实质选型取舍的任务；输入充分且已有能力明确覆盖时直接完成，普通跟进沿用既有方案与授权。

Search existing local

Spec-Driven Development (SDD) contract templates for the ALDC framework. Use when an ALDC agent or workflow needs the ca...

从GitHub和SkillsMP等官方网站搜索符合用户描述的优质skill，供用户选择，然后自动克隆并安装相应skill到全局~/.claude/skills/目录。当用户需要搜索或安装新skill时触发此技能。

Find the best skill for the current task across the entire skill library, including the dormant majority whose descripti...

Find the right skills for a task before acting. Use at the start of any multi-step or unfamiliar request to retrieve rel...

Audit an AI agent skill for security risks before installing or trusting it. Runs a deterministic scanner (regex pattern...

Audit third-party Agent Skills, plugins, and MCP tool definitions for security risk before installation: prompt injectio...

Hybrid security auditor for OpenClaw skills, Claude/Codex skills, and app repos. Use when installing a new skill, auditi...

-Automatically convert documentation websites, GitHub repositories, and PDFs into Claude AI skills in minutes.

Convert docs, repos, PDFs into Claude Skills with conflict detection

Analyze an implementation plan (defaults to .flow/specs/), discover relevant skills from the ecosystem, install them, an...

Mandatory post-run self-review for any Northwatch Wardens skill. Analyzes the just-completed run against the skill's def...

Auditoria e evolucao do ecossistema de skills. Qualidade de codigo, seguranca, custos, gaps, duplicacoes, dependencias e...

This skill should be used when the user asks to "analyze session", "evaluate skill execution", "check session logs", pro...

Select and coordinate reusable skill sets from the Innovator skills collection for cross-cutting engineering tasks.

A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration...

A skill that creates new Codex skills and automatically shares them on Slack using Rube for seamless team collaboration...

Skillshare CLI reference and sharing workflows. Use when: (1) user says "share", "push", "sync skills", "skillshare", (2...

Unified shell script quality: ShellCheck linting + BATS testing. Use for CLI scripts, headless agent commands (gemini, c...

SKILL.md simplification with functional integrity verification. Analyze redundancy, optimize content, check no functiona...

[TODO: Action verb + what you build with technology. 250-350 chars total. Example: "Build type-safe APIs with Hono - fas...

> {{ONELINEDESCRIPTION}}

一句话说明这个 skill 做什么 + 什么时候触发（用户说了什么/在做什么任务时使用）。这段文字是 Agent 决定是否加载本技能的唯一依据，务必把触发场景写具体。

Optimize skill loading with metadata-first approach and progressive disclosure. Use when managing multiple skills, optim...

Auto-detect and load minimal context from Skills folders using progressive disclosure, trimming 1400 tokens from system...

Build specification-compliant Agent Skills from documentation sites, GitHub repos, and APIs. Systematically gather resou...

Add file or URL to reading inbox. Use when "add to reading list", "save for reading", "put this on my reading list", "re...

Security auditing for MOOLLM skills - static analysis and runtime surveillance

Pr̊ØS💬 — Build Your AI Co-Founders with Unix Architecture and Boot them with One Line.

Analyzes user intent, Global Knowledge, and Strict Rules to design a technical blueprint.

Generate structured skill specifications for independent skill creators. Use when asked to ideate, brainstorm, or specif...

Agent Skills formal specification for cross-platform compatibility. Ensures skills are evolutionarily robust across Clau...

Curated skill bundle installer keyed to project archetype. Classifies the repo as one of six archetypes (Next.js SaaS, F...

Format and structure skill for Skill Stack weekly newsletter. Handles frontmatter, sections, skill packages, and calls-t...

> Category: [Project | Development | Quality | Operations]

Show the state of terum-skills on this machine — team, clone, session hook, pending work, machine facts — and whether a...

cheat-on-skill 的陪跑进度 skill。用户问“今天该干嘛”“我现在做到哪了”“继续学”“打卡”“我卡住了”“下一步是什么”时触发。读取 .skill-state.json 的 active.progress 和 learni...

Atomically update task status across TODO.md and state.json. Invoke when task status changes.

用于审计Claude技能和命令的质量。支持快速扫描（仅变更技能）和全面盘点模式，采用顺序子代理批量评估。

Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake m...

Use when auditing Codex skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake mo...

Audit the installed skills and decide which to keep, improve, merge or retire. Use when taking stock of the skill librar...

Use when learned skills exceed 10 per location or need consolidation. 4-step stocktaking with character budget awareness...

Skill file structure, naming conventions, directory layout, and frontmatter requirements. Use when creating skill files...

Interview-driven automation design tool. This skill should be used when the user wants to design a new skill, agent, aut...

Find repeated manual work in Littlebird activity. Use to draft the next automation skill worth building. Read README.md...

Audit generic AGENTS.md, CLAUDE.md, and SKILL.md instructions for deterministic drift and model-era obsolescence candida...