В каталоге 183 730 навыков в 14 категориях.
Ultimate Claude Code skill creator and architect. Designs, scaffolds, builds, reviews, evolves, and publishes production...
Advanced skill creation system for Claude Code that combines deep intent analysis, evidence-based prompting principles,...
Creates new Claude Code skills with proper structure and best practices. Use when user wants to create a skill, update a...
Harden a skill or any agent instruction file (CLAUDE.md, AGENTS.md, GEMINI.md, .cursor/rules, .github/copilot-instructio...
When Claude discovers a non-obvious solution, unusual pattern, or hard-won insight during a session, automatically forge...
Write a skill, or forge a script tool, so a solved problem survives.
Use when creating a new skill, when an existing skill never loads, does not fire or fires on the wrong prompts, when its...
Create a new Lattice skill — atom, molecule, or refiner — following all framework conventions. Writing skill files manua...
Use when the user asks to forge, scaffold, author, or ship a new skill or agent — the skill-creator's own namesake artif...
Create a node-local skill on a follower machine and prepare its promotion into the shared set through a gate. Use when a...
Create new skills when existing ones don
Benchmark Claude Code skill performance with variance analysis, tracking pass rate, execution time, and token usage acro...
Scaffold and build Claude Code skills from plans or descriptions. Generates SKILL.md files, sub-skills, scripts, referen...
Convert Claude Code skills to work on OpenAI Codex, Google Gemini CLI, Google Antigravity, and Cursor. Analyzes platform...
Improve and iterate on existing Claude Code skills based on usage feedback, test results, or changing requirements. Hand...
Arquitecto y generador de Skills. Define, estructura y registra nuevas capacidades para el agente Antigravity.
Architecture and design planning for new Claude Code skills. Guides through use case definition, complexity tier selecti...
Package and distribute Claude Code skills for sharing via GitHub, Claude.ai uploads, or team deployment. Creates install...
Audit and validate existing Claude Code skills for quality, triggering accuracy, structure compliance, and best practice...
Meta-skill creation and optimization system that analyzes, designs, and builds new specialized skills using the integrat...
skill-format
Systematic skill freshness auditing with verification anchors, volatility classification, staleness detection, and upstr...
This skill should be used every time you generate, refresh, or validate codebase-derived SKILL.md documentation for this...
Create skills by learning from high-quality GitHub projects
Extract methodologies from documents or examples to create executable skills
Mine repeated pain from transcripts, project retrospectives, debugging logs, failed prompts, deployment notes, or work h...
Fuse two skills from this library into one hybrid brief for a task that sits between them — the meta-skill. Use when a t...
Audit recent agent work for recurring manual patterns that have no skill yet, cross-check against installed skills and p...
Analyzes the user's skill library to identify coverage gaps, redundant overlaps, and optimization opportunities. Use whe...
Analyzes project requirements to identify missing skills and automatically creates them. Enforces MCP Code Execution pat...
Before starting any significant task, force explicit evaluation of available skills. For each potentially relevant skill...
Session-start meta-skill that enforces the 1% rule: before any action on a processkit entity or context/ file, if there...
Manage Gemini RAG stores with Code-RAG support
Query Gemini with Google Maps grounding
Query Gemini with Google Search grounding
在現有 domain stack 中新增單一 skill。不是重建整個 repo，是加一個新的。 Trigger: 用戶說「加一個 skill」、「我需要一個做 X 的 skill」、「新增」。 Do NOT use when: 要建整個...
Generalize a skill beyond its origin: strip names, parameterize case-local constants, move domain-locked values to opt-i...
Use when turning local, private, or personal Agent Skills into publishable skills for GitHub, marketplaces, teams, or pu...
Create well-structured Agent Skills with proper formatting, best practices, and validation. Use when the user wants to c...
Ingests external documentation, repository patterns, or best practices and translates them into a formalized Antigravity...
Reactant direct-entry skill authoring utility. Use when the user directly asks to create a project-local Reactant tag sk...
Generate SKILL.md files with proper YAML frontmatter, capabilities documentation, and usage examples following Babysitte...
Creates new Antigravity skills with proper SKILL.md format, directory structure, scripts, and resources. Triggers when c...
Meta-skill for creating new Claude Code skills with configurable execution modes. Supports sequential (fixed order) and...
Transform extracted patterns into SKILL.md files following agentskills.io spec. Use when generating skills from patterns...
Meta-skill for creating, refining, and managing Agent Skills. Use when needing to create new skills, improve existing sk...
Meta-skill that creates new skills. Use when user repeatedly explains the same workflow, or mentions "save this as a ski...
自動生成符合標準的 SKILL.md 和資料夾結構。
Create scoped git commits for task operations. Invoke after task status changes or artifact creation.
Clean and publish Hermes Agent skills to GitHub. Security checks, sensitive info removal, repo setup.
Access Google Gmail, Calendar, Tasks, Drive APIs
Evaluates Claude Agent Skills on 10 quality axes with letter grades (A+ through F) and specific improvement recommendati...
スキルの適切な粒度を定義（1スキル1目的、分割基準、結合基準）する。スキル設計時、粒度判断時、またはユーザーがスキル粒度、1スキル1目的、分割基準、結合基準、スキル設計原則に言及した際に使用する。
Neo4j query interface for skill discovery — replaces flat skill injection, Cypher traversal
Audit Skill() refs; detect hubs, isolates, and dangling targets. Use when auditing skills.
Audit which Claude Code skills you actually invoke. Use when the user wants to find dead/unused skills, hallucinated ski...
Research libraries, APIs, and patterns using searchGitHub and Exa tools. Finds real-world implementations and saves stru...
Runtime security monitor for active OpenClaw skills. Watches file access, network calls, and shell commands. Flags anoma...
Guide to all available PM Superpowers skills, recommended workflows, and how to get the most out of the plugin. Trigger...
이 레포에서 새 스킬을 작성하거나 기존 스킬을 수정할 때 사용하는 가이드. "스킬 만들어줘", "새 skill 추가", "SKILL.md 작성", "스킬 구조", "스킬 수정해줘", "스킬 가이드", "descrip...
Skill navigator and guide -- automatically scans all installed skills and slash commands, then explains them in the user...
Harden skills with contracts, forbidden actions and quality gates. Use when the user requests skill hardener or invokes...
Bulletproof skills using Test-Driven Development. Use when creating discipline-enforcing skills, testing existing skills...
Harmonize a repository's skill portfolio across catalog and user-installed skills.
Meta-skill for extracting and creating reusable Claude Code skills from past work sessions. Analyzes git history, code p...
Show skill portfolio health dashboard with charts and analytics
Diagnose and repair the TOS ecosystem itself. Use to check ecosystem health (every skill + shared engine), explain why s...
Scan the skill library for dangling references and build a per-skill health table.
プロジェクト プロジェクトのスキルシステムガバナンスを自動検証するスキル。 GOVERNANCE.md 規則遵守状況をチェックし、ヘルスレポートを生成する。 **自動化された監査項目**: - MANIFEST.json 保有有無 - 依...
Ecosystem health audit. Reports staleness, never-run skills, manifest/directory drift. Distinct from structural-lint sib...
Report the human-led converge band at low or med, and the discovery parameters it describes.
Report the model-led explore band at high, xhigh, or max, and the discovery parameters it describes.
Report the ultra crown rung, where the caller chooses convergence or exploration and a depth per gap.
Report the zero cut — temporary automatic skills are cut, and `all` cuts every skill summon.
Explicitly request the best-matching skill for a concrete capability gap into this session without installing it.
Use when the user wants to find NEW external skills for a project, build a skill stack from external registries, or comp...
Audit and maintain a skill bundle so every bundled asset is reachable from SKILL.md or its directory's INDEX.md. Use whe...
Translate SKILL.md and README.md files into multiple languages for sharing skills internationally
One line — used in CLAUDE.md system-reminder and the skill catalog.
Mine Claude Code session logs for skill idea candidates. Use when running the weekly skill generation pipeline to extrac...
Execute general implementation tasks following a plan. Invoke for non-Lean implementation work.
Import skills from the skills library at ~/.claude/skills/ into a project's CLAUDE.md files, automatically matching skil...
Improve a skill via a test-fix-retest loop — static checks, targeted fixes, keep or revert on score change.
Use when a Codex skill has validation failures or warnings that need an approved test-fix-retest cycle.
Improve a skill using a test-fix-retest loop. Runs static checks, proposes targeted fixes, rewrites the skill, re-tests,...
Read accumulated session logs for a skill, synthesize numbered improvement proposals with rationale and session evidence...
Improve rule or skill file without changing the content
Complete feedback loop from observability insights to skill updates. Use when analyzing enhanced telemetry patterns and...
A systematic process for detecting skill gaps during development, automatically updating the skill registry, and continu...
This skill should be used when the user asks to "apply skill improvements", "update skill from plan", "execute improveme...
Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards. Use when improv...
Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.
Research and improve Claude skills with current best practices. Triggers on requests to improve skills, update skills, r...
Iteratively reviews and fixes Claude Code skill quality issues until they meet standards. Runs automated fix-review cycl...
Runs an autonomous review-and-fix improvement loop over a Claude Code skill until a review comes back clean, with a cros...