Agent skills directory

Synchronize skill documentation. Use after creating or modifying any skill. Updates SKILLS-INDEX.md with the full skills...

Use when a repo skill fails, produces errors, gives wrong instructions, or references stale information. Also use when a...

Use to audit Agent Skills catalogs or installed skill roots for metadata and doc-link issues; optionally apply conservat...

Grades agent skills by scoring agent conversations against efficiency and code-quality rubrics, then drafts concrete ski...

Use when the user wants their agent setup graded from real conversation history, asks which installed skills are actuall...

Document conversion routing with dual invocation support

Documentation expert for Claude Skills showcase website. Maintains skill-to-website sync, manages tag taxonomy and badge...

Auto-generate comprehensive documentation from skills in multiple formats (PDF, HTML, EPUB, Markdown). Converts skills t...

Download and install Claude Code skills from various sources. Supports GitHub repositories, compressed archives (.zip, ....

DriftGuard Security Scanner+ is a local-first security drift scanner for repos, OpenClaw skills, and AI agent tools. Use...

Audit and safely remediate a cross-runtime Skill ecosystem spanning Codex, Claude Code, Loom, VibeGuard, Spellbook, and...

編輯現有 skill 的內部結構。精確修改 gotchas、scoring、forcing questions 等特定部分。 Trigger: 用戶說「改這個 skill」、「調 scoring」、「加 gotcha」、「改 forcing...

Use when creating, modifying, or refactoring Claude Code skills that require structured multi-agent review and quality v...

Use when asked to draft, revise, or review an agent skill specification so frontmatter alone routes correctly and the bo...

ElevenLabs text-to-speech CLI tool guide

Author and maintain Agent Skills: routing metadata, body content, bundled references and scripts, evaluation, and distri...

Guide for enhancing and improving existing skills based on conversation analysis and usage feedback. This skill should b...

Full enhancement pipeline for an existing Lattice skill — rewrites a molecule or atom to modern-capable-model grade: res...

Upgrade existing agent skills end-to-end with deterministic edits, stronger trigger wording, cross-assistant portability...

AI-powered enhancement of skill SKILL.md files. Use to transform basic templates into comprehensive, high-quality skill...

Audit, stress-test, and improve Codex or Claude skills using source-backed patterns, pressure questions, progressive dis...

AL project estimation for Business Central. Use when estimating development effort, creating cost models, SWOT analysis,...

Optimize existing AI agent skills with a dual-loop workflow for activation tuning and execution quality. Use when improv...

Measure whether a skill helps a named task or needs revision or removal. Use when: a bounded routing or coding evaluatio...

Evaluate skill performance against test cases

Test a pipeline stage's skill file by running the stage WITH and WITHOUT the skill on the same input, comparing outputs,...

Evaluate skills: trigger testing, A/B benchmarks, structure validation, head-to-head bake-offs.

Evaluate all workspace-hub skills for structural validity, content quality, cross-reference integrity, and registry cons...

Skill quality evaluation assistant. Trigger when users ask to evaluate a skill, review a skill package, explain a score,...

Test, evaluate, harden, and optimize Codex skills from SKILL.md folders, run traces, eval prompts, failure reports, and...

Use when creating, editing, reviewing, or deciding whether to keep a Claude Code skill - builds a small eval harness (ha...

Run benchmark evaluations for any skill. Reads evals/evals.json from the target skill, spawns parallel with-skill and wi...

Create or update behavior evals (evals.json) for a skill. Invoked by skill-creator. Mode 1 (TDD): creates evals from a s...

Create trigger evals and run description optimization for a skill. Generates should-trigger/should-not-trigger queries,...

Evaluate any agent skill against a merged framework — Anthropic's Claude Code best practices plus Matt Pocock's writing-...

Use this skill when designing, running, interpreting, or reporting Agent Skill evaluations, selecting cases or judges, a...

Проверять выбор и наблюдаемое поведение навыков на реалистичных положительных, отрицательных и аварийных сценариях. Испо...

离线评估调用方提供的 Skill 执行记录，检查输出结构定义、期望子集、重复输出确定性、错误和耗时预算并执行最低得分门禁，适用于技能发布前回归验收。

Evaluates agent skills against Anthropic's best practices. Use when asked to review, evaluate, assess, or audit a skill...

AL event-driven architecture for Business Central. Use when creating EventSubscribers, IntegrationEvents, BusinessEvents...

Git-versioned agent memory — agents that never make the same mistake twice.

Use when running, reviewing or changing coco's self-evolution cycle: the 30-day loop that observes how skills are actual...

Skill 经验进化管理器。在对话结束时分析用户反馈，提取最佳实践和解决方案，持久化到 evolution.json 并缝合到 SKILL.md。支持三层架构（上游层、全局层、项目层）实现跨项目经验管理。当用户说"复盘"、"记录经验"、"保...

Global evolution system for ship-faster skills. Uses hooks to capture context, failures, and session summaries, then gen...

Self-evolving skill lifecycle with three triggers: post-execution fix, degradation detection, and periodic metric review...

Self-evolving skill system. Skills are scored after execution (0-100) on 5 dimensions. Score 90+ over 5 runs = crystalli...

Analyze, evolve, and rollback skills based on usage patterns. Use when evolving skills, improving skill definitions, upd...

Track skill changes, improvements, and evolution over time. Task-based operations for version tracking, change documenta...

Evolve skills iteratively based on usage tracking and feedback. Use for skills used repeatedly, when failure rate exceed...

gotcha/learned 관찰에서 스킬 개선점을 추출하여 autoresearch로 연결하는 자기 개선 루프. 축적된 오답노트와 성공 패턴을 스킬에 매핑 → 체크리스트 자동 생성 → autoresearch 실행. m...

Discover, security-vet, and install GitHub Copilot skills and extensions from public repositories with explicit provenan...

Export Claude skills. Use to generate documentation of all available Claude Skills.

Export a specific skill from ~/.claude/skills/ into a versioned git repository. Use when the user says "export skill X",...

Extract patterns from coding agent sessions to improve existing skills or create new ones. Use after completing a work s...

Analyze task trajectories to propose reusable SKILL.md candidates from successful patterns

Meta-skill that extracts reusable skill patterns from conversations and generates standard SKILL.md files.

自动化工厂，将 GitHub 仓库转换为标准化的 AI Skill。当用户提供 GitHub URL 并希望"打包"、"封装"或"创建 Skill"时使用此工具。支持自动获取仓库元数据、生成标准目录结构、注入生命周期管理所需的扩展元数据。

Meta-skill for creating complete, production-ready Claude skills from scratch or by migrating existing prompts/GPTs. Gen...

Create new skills with proper structure and YAML frontmatter. Use when building new slash command skills, ensuring consi...

Create, refactor, package and validate a reusable workspace skill with precise routing, <=100-line entrypoint and local...

Create new skills with proper structure and YAML frontmatter. Use when building new slash command skills, ensuring consi...

Generate improvement reports for skills or CLI packages you authored. Use when ending a session where you worked on your...

Use to identify missing instructions in another skill based on its output.

This skill should be used when the user asks to "fetch skill", "install skill", "search for a skill", or when a hook out...

Find and install skills from SkillsMP marketplace (skillsmp.com). Use when users want to discover new skills, search for...

Find the right Affitor skill for your goal. Triggers on: "which skill should I use", "find me a skill", "what skills are...

Full-featured Agent Skills management: Search 35+ skills, install locally, star favorites, update from sources. Supports...

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is th...

Use when the user asks to find, search, or discover a skill that is not already installed. Does not handle updating or p...

벤더링된 android/kotlin/compose 스킬을 자연어로 검색해 적재적소 스킬을 찾는다. spec/plan 작성이나 TEAMYG-Android 구현 중 "어떤 스킬 써야 하지", "recomposition...

Proactively discover, install, and create Claude skills for specialized tasks. AUTOMATICALLY activates when encountering...

Find the right skill for a capability. Load when a user or skill needs to check if a skill exists for a given task, when...

Navigation aid for the processkit skill catalog — maps natural-language cues and task types to the right skill. Read thi...

Use when someone asks whether a skill already exists for a task, what skill they should use, whether an existing skill c...

Use when asked which skills or plugins are actually being used, before installing or pruning skills, or on a periodic li...

Check for relevant skills before starting any task. Triggers on task start, new requests, beginning work, or implementat...

[Skill Management] Fix the agent skill based on `logs.txt` file.

Generate a production-ready AbsolutelySkilled skill from any source: GitHub repos, documentation URLs, or domain topics...

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...