Browse 182,820 skills across 14 categories.
Use when a skill isn't triggering as expected, before adding a new skill (to check for a name collision), during periodi...
Pre-install security scanner for AI agent skills. 7.5% of 14,706 skills are malicious. Audit before you trust.
Audit all available Claude skills across user and project scopes — inventory them, map routing and overlap, score each o...
skill-auditor — Use when auditing, reviewing, or grading Hermes skills for quality. Checks trigger phrases, exact comman...
Audit a SKILL.md (15 checks).
Audit skill files against quality standards. Use ONLY within Manager Pattern workflow via TaskList. Receives taskId, rea...
Audits SKILL.md files ("audit this skill", "review my skills", "score this SKILL.md") and writes a scored report with co...
Audit existing skills (global and project-level) for agent-friendliness, consistency, and best practices. Use when asked...
Audits skills in this repo for consistency, API drift, and structural gaps. Produces a prioritized report grouped by sev...
Comprehensive security auditor for OpenClaw skills. Checks for typosquatting, dangerous permissions, prompt injection, s...
Pre-install skill quality auditor. 10-point security and quality scan before installing any third-party skill.
审查自定义 Claude Code Skills 的质量与规范性。 检查 SKILL.md 渐进式披露、行数、frontmatter、参考文件链接、目录结构等。 触发词：审查skill、检查skill质量、skill audit、revie...
The authoring gate for new skills. Routed to when the user invokes /new-skill "<gap>". Five gated phases — gap evidence,...
Guide for creating new Claude Code skills following best practices. Use when the user asks to create a new skill, agent...
Meta-skill para criar, editar, avaliar e otimizar skills do kit. Use quando adicionar nova skill, refatorar skill existe...
Integrate a CAFleet-orchestrated Director/member team into a new skill, with role files, broker coordination and supervi...
Draft new Allbert skills from natural-language requirements and submit them through install quarantine.
Create or update an AIDE skill in .aide/skills with valid frontmatter and a concise workflow.
Author and structure practical Robium skills without unnecessary context or ceremony.
Draft a well-formed new skill (a SKILL.md scaffold, optionally with scripts/references) from a described recurring need,...
Meta-skill for creating and improving agent skills. Use when designing new skills, refining existing skills, or understa...
Rules for SKILL.md files that trigger, fit, and are proven. Use when creating a SKILL.md, rewriting its description, spl...
Guide creating Claude Code skills with TDD and persuasion principles. Use for new skill development.
Conventions for writing or editing a SKILL.md in this repo — horizontal rules, bold usage, line wrapping, spelling, nega...
Create or update project-specific skills in this repo. Use when asked to make new skills, modularize workflows, or build...
Writes and revises agent skills so they trigger at the right moments and give usable instruction when they do. Use this...
Author or revise SKILL.md files, concise discovery metadata, topic routers and references within catalog budgets.
Guide for creating and auditing DAAF skills (SKILL.md). Covers frontmatter, metadata vocabulary, progressive disclosure,...
When you notice a reusable multi-step task worth saving, or the user asks you to save, change, or delete a skill.
Engineer one new or updated AI Skill in this Skills repository from concrete use cases through canonical source, minimal...
Author SKILL.md: frontmatter, structure, writing principles.
Improve skills using concise instructions, portable resources and real evaluation. Triggers on "write a skill", "写技能".
Guidelines for writing Agent Skills that comply with the agentskills.io specification. WHEN: "create a skill", "new skil...
"Guide for creating Claude Code skills that mirror library documentation. Covers sync strategies, SKILL.md structure, an...
Design and development best practices for Claude Code skills, MCP tools, and AI agent capabilities. Use when creating sk...
Guidelines for writing effective AI agent skills
Use when creating, reviewing, or improving first-party agent skills in this repo. Apply whenever a user asks to add a sk...
Design, improve, and evaluate reusable agent skills with high-quality SKILL.md files, precise trigger descriptions, prog...
Use this skill when creating, editing, or reviewing an Unreal Engine Agent Skill, a named bundle of instructions registe...
Use when a lesson must become a skill, here or in a profile.
创建、设计、修改、重构和验证 AgentDock Skill 时使用；负责 Agent Skills 兼容的 SKILL.md、可移植核心、引用、辅助脚本、测试、安全边界和本地真实验证。
Use when creating or revising a GameStudio-CodexKIT skill, resolving ambiguous skill triggers, auditing provenance or li...
Write, validate and evaluate Agent Skills against the open standard: description design that triggers reliably, progress...
Design new reusable AI skills with clear triggers, workflow, guardrails, and output contracts.
Create new Agent Skills from learned patterns and workflows. Use when you have developed a repeatable workflow, coding p...
The Apple/Swift-and-this-catalog layer for authoring or reviewing a SKILL.md, on top of superpowers:writing-skills. Use...
Audit or govern Codex skills, external skill intake, prompt packets, or skill-like guidance for routing, placement, prom...
The bar a SKILL.md must clear before it ships in this lacquer — tight trigger-oriented frontmatter, single responsibilit...
Turn raw PM content into a compliant, publish-ready skill. Use when creating or updating a repo skill without breaking s...
Keyword-based automatic skill detection and activation system for Claude conversations
Update a skill or prompt using lessons learned from a file's Git history
Skills auto-load based on keywords and context:
Checks that proposed skills follow repository and release policies. Use during CI and skill-batch review.
Scans proposed skill changes and reports for likely credentials or sensitive literals. Use before committing a batch or...
Author an eval for an existing skill from its REAL usage history, not its spec. Mine invocations from the brain's conver...
Validates and improves agentic skills by running isolated executor agents against test briefs, scoring confusion, fixing...
CLI tool for querying AWS Knowledge MCP Server
AWS Polly TTS CLI for text-to-speech synthesis
Trigger-based workflow dispatcher for AXEL core operations. Receives explicit trigger from command and dispatches to mat...
Test skill B from test-pack for unit testing.
Skill B from experimental directory
Use when doing task B.
A fake skill for testing
The official Skill Base CLI client. Use the `skb` (Skill Base CLI) command to search, install (single skill or collectio...
Skill Base server deployment guide. Covers starting the Skill Base server (npx skill-base), Docker configuration, port m...
Design lightweight benchmarks for agent skills and skillsets. Use when Codex is asked to prove whether a skill improves...
A minimal valid skill.
Lightning-fast BM25 full-text search for files
Call help() or help("page.click") to print signatures and uncommon options
Skill Bonds Registry
Bootstrap new skills quickly from natural language descriptions. Use when you need to create a new skill fast, generate...
Protects a skill broker from overload while preserving clear errors and bounded retries. Use when many agents can query...
Discover, browse, and compare agent skills from repositories. Shows new skills, updates, and helps users find relevant s...
Designs and builds a new Claude Code skill folder from a blank page in your own house style, surveying existing skills f...
Canonical Runx skill-authoring implementation. Use for designing, creating, updating, improving, or adding harness cover...
Use when turning a repeated procedure or SOP into a skill, or deciding whether a step should stay a prompt, become a ski...
Generate new Claude Code skills from requirements through guided questions and pattern selection
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from...
Build correct, consistent Agent Skills (create/update/delete/add content) using validated templates, safe defaults, and...
Scaffold a new SKILL.md.
Creates and refines Claude Code skills via structured workflows with YAML frontmatter, typed folders, and depth-gated LO...
Multi-agent research-and-curation pipeline that builds or refreshes a technology skill for the domain-expert marketplace...
Builds, validates, packages, tests, and optimizes deployment-ready Skill files (SKILL.md + references/ + scripts/ + agen...
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,...