В каталоге 183 730 навыков в 14 категориях.
Skill Builder — Meta-Skill — Institutional capability and runbook for skill-builder.
Create Claude Code skills with best practices, structure, validation, and testing. Use when designing or refining skills...
Create, structure, and optimize skills for the FTC Metrics project. Use when creating a new skill, improving an existing...
Interviews the user about a repeatable task and turns the answers into a ready-to-import iHub skill: a SKILL.md with val...
Author a new Claude Code skill the right way, from choosing the storage tier (project, shared library, or user-global) t...
Use when creating skills, converting docs/repos/PDFs to skills, installing external skills, auditing skill quality or se...
Use this skill when creating new Claude Code skills from scratch, editing existing skills to improve their descriptions...
Create new Claude Code skills with proper SKILL.md format, frontmatter, and best practices. Use when building, scaffoldi...
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory org...
Use when automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create sk...
Author a new processkit skill end-to-end — use-case interview, frontmatter, body sections, Gotchas, and trigger-phrase g...
Scaffold a new ralvaskills skill per SPECS.md — SKILL.md skeleton, optional STACK/RECIPES, folder placement, SPECS updat...
Use when creating new skills, optimizing existing skills, or auditing skill quality. Guides skill development following...
Builds a new Claude Code skill from scratch through a relentless, evidence-based interview that walks the skill's design...
Meta-skill. Turns a repeated workflow (or "make this into a skill" / "turn what we just did into a skill") into a correc...
当 harness 需要新的可复用能力、现有 skill 需要优化，或用户批准的 evolution proposal 需要修改 skill 时，在 .agents/skills 下创建或更新本地 Codex skill。
Universal guide for creating production-ready Claude Code skills for any project. Includes 6-step workflow (understand,...
Specialized guide for creating Claude Code skills for Dr. Sophia AI medical system. Includes healthcare integration patt...
Create effective, reusable skills from real-world experience for promotion to Master Alex
Use when doing task C.
A fake skill for testing
Run isolated calibration and drift evaluations for PyPI-distributed XRefKit Skills. Use when installed Skill packages ex...
This skill should be used when the user wants to find the right looplia skills for a task,match requirements to availabl...
Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for ex...
Categorize and display available skills. Use when listing or selecting skills.
Build a bounded Agent Skill catalog across explicit discovery scopes and report collisions before loading instruction bo...
Audit installed and source-controlled Codex skill catalogs for duplicates, drift, stale metadata, placeholder text, risk...
Generate dynamic skill catalogs with network diagrams to visualize Alex's capabilities and track learning progress.
Use when a task looks project- or domain-specific and no listed skill covers it - Android/Compose/Kotlin/KSP/Room/Gradle...
Catholic liturgical CLI tool
Orchestrate multi-skill workflows with prompt-based skill chaining. Define sequential or parallel skill invocations usin...
Ordered sequences of individual audit skills to execute for different audit depth levels ensuring comprehensive, systema...
Validate skill/command file format and structure
Prismstack 的品質審查 meta-skill。三個 mode： - design：規劃階段 7 問快速判斷（候選 skill 該不該建） - review：完成後 15 維度 + 6 雷區掃描（skill 品質夠不夠） - pac...
Validate Claude Code skills against Anthropic guidelines. Use when user says "check skill", "skillcheck", "validate SKIL...
Validate Claude Code skills against the agentskills specification. Catches structural, semantic, and naming issues befor...
Check the references in all the skill files
Use this skill when the user wants to check, test, or optimize a skill. Covers: testing whether a skill's description tr...
Read-only checkup of installed agent skills across Claude Code and Codex: broken links or files, same-name copies that d...
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pag...
Audit or simplify skills while preserving technical knowledge, quality requirements, and clear decision boundaries.
Audit installed skills for duplicate ownership, stale triggers, prompt cost, and safe deletion.
Audits installed Agent Skills for duplicates, unused candidates, loaded roots, oversized descriptions, and prompt cost....
系统性清理本地 skills — 识别无用/低使用率 skill，分类禁用或删除
CLI for Skill Recordings Support Agent platform. Use when investigating support issues, debugging workflows, inspecting...
Guides creation of high-quality Agent Skills with domain expertise, anti-pattern detection, and progressive disclosure b...
Generates or Refactors the physical file structure based on a Blueprint or Audit Report.
Generate and run unit and integration tests using pytest (Python) or Jest (JavaScript) with fixtures, mocks, and async s...
Find installed skills that share a name, shadow each other or overlap so much in description that the wrong one gets pic...
Evaluate skill quality, find the weakest dimension, and apply directed improvements. Also tracks usage to spot idle or r...
> Compiler: manual (bootstrap)
Validates that the generated skill adheres to the Antigravity Folder Structure and Blueprint requirements.
Audit reusable plugin skills, project-local .codex skills, AGENTS.md, nested instructions, context cost, stale guidance,...
Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt stri...
Visualize whether skills
Measure whether a skill, rule or agent definition is actually followed. Use when a rule's or skill's real adherence is i...
DAG-based multi-skill orchestration with dependency resolution.
File concatenation with glob patterns guide
Create, edit, evaluate, and package agent skills. Use when building a new skill from scratch, improving an existing skil...
Skill Connectivity Hub
Use when consuming optimization artifacts.
Convert repeated tasks into versioned skills, track performance gaps, and iteratively polish through Git version control...
Generates evolution contracts for skills, defining what can be updated, what must remain stable, and how to extract know...
Validate an Agent Skill package and choose the right instruction, capability, or lifecycle primitive before implementati...
Guides contributors to design, polish, and submit high-quality skills for AL Copilot Skill Collection. Use when creating...
{{cookiecutter.project_description}}
AL Copilot capability development for Business Central. Use when implementing PromptDialog pages, AI generation features...
Use when reviewing, shipping, or regression-testing a SKILL.md and you hold one or more captured trajectories where that...
Claude Codeスキルの作成・レビュー。新規スキルの設計ガイド、既存スキルの品質チェック、ベストプラクティスに基づく改善提案を行う。
Create, fix, and validate skills for AI agents. Use when user says 'create a skill', 'write a skill', 'build a skill', '...
Analyze git history and codebase patterns to automatically generate SKILL.md files that teach Claude your team's develop...
[Skill Management] Create new Claude Code skills or scan/fix invalid skill headers. Triggers on: create skill, new skill...
Generates a new Betty Framework Skill directory and manifest. Use when you need to bootstrap a new skill in the Betty Fr...
Use when the user wants to capture a real repo's working patterns as a reusable skill — analyzes the local git log and d...
Analyze git history and instincts to auto-generate a learned skill
Create and validate Claude Code skills with proper structure, checklists, and validation scripts. Use when creating a ne...
[スキル作成] 新しいスキルを壁打ち→テンプレ生成→登録確認まで
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to cre...
Create new Claude Code skills following project patterns and best practices. Use when building new skills, extracting re...
Design-first test creation workflow with validation
Used to create a new skill. Used when a user wants to create a new skill
Guide for creating Agent Skills: structure, best practices, and SKILL.md format for Claude Code, Codex, Gemini CLI, and...
Use this skill when the user asks to create a new skill, custom command, or wants to know how skills work in Claude Code...
Guide for creating standards-compliant skills with templates, references, and validation. All content must be in English...
Create or refactor Agent Skills following the agentskills.io specification. Use when creating new skills, converting pro...
Plan and create Claude Code skills/commands/agents with guided wizards and background agents aligned to v0.5 guidelines....
> Meta-skill: This skill explains how to create other skills.
Complete comprehensive guide for creating, managing, and optimizing Claude Code Skills. Reference documentation covering...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an exist...
Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the S...
Step-by-step guide for creating your own Codex skills, from deciding whether a skill is the right tool to writing the SK...
スキル改善・新規作成を、skill-creator検証からskill_list更新まで一貫実行する指示書。単一/複数スキルの処理順、成果物の完全性、言語規則、確認手順を明文化する。Anchors:• 18-skills.md / 適用: ス...
Create new Claude Code skills following SOTA compact design patterns (v3.2)
Create, edit, improve, tidy, review, audit, or restructure AgentSkills and SKILL.md files.
Guide for creating effective agent skills. This skill should be used when users want to create a new skill (or update an...
Create new skills for the POS following Anthropic's established patterns. Use when users want to create a new skill, upd...
Built-in skill for creating, managing, and discovering AgentForge skills. Allows agents to generate new skills from natu...
Write or restructure a skill's SKILL.md, frontmatter, and bundled resources. For evals or trigger benchmarking, use the...