В каталоге 183 730 навыков в 14 категориях.
Use when measuring whether a skill-concierge gate-threshold change helped real skill usage or adoption — "did the new ga...
Pattern for shipping a human-only USAGE.md alongside a complex Claude Code skill, so users learn how to invoke the skill...
Audit installed Claude skills: flag unused, spot duplicates, generate deactivation checklist. Reduces context noise from...
扫描本机 Claude Code 和 Codex 的会话日志，统计哪些 skill 有本地调用证据、哪些在本机无证据（已安装但日志无痕迹，不等于从未使用）、调用排行、月度趋势、项目分布，输出终端表格和 Markdown 报告，可导出 CSV...
Validate any Lattice SKILL.md against all tier conventions — atoms, molecules, and refiners. Catches structural errors,...
Validates and reviews skills against the Agent Skills specification. Checks YAML syntax, naming conventions, description...
Skill Validation GF(3) - SLAVE (-1)
Ensure Claude Code skills meet quality standards through validation operations for structure, content, patterns, and pro...
Validates skills against production-level criteria with 9-category scoring. This skill should be used when reviewing, au...
Validate skills against Anthropic best practices for frontmatter, structure, content, file organization, hooks, MCP, and...
离线校验 Skill Manifest v2、工具 Schema、权限、资源预算、触发冲突和评测配置，适用于技能校验、清单校验或技能包发布前检查场景。
vector rag gui
Local RAG with Ollama and FAISS
Security audit for AI agent skills before installation. Scans SKILL.md files, hooks, scripts, and MCP configs for prompt...
Referenz-Skill für die Deinstallation, Deaktivierung und Reaktivierung von Community-Skills, die über den Kanzlei-Builde...
Validate and quality-check skill implementations.
Security-first vetting for OpenClaw skills. Use before installing any skill from ClawHub, GitHub, or other sources. Chec...
Vet an agent skill before installing it — read the SKILL.md and any scripts for the red-flag patterns (credential access...
Render TikTok-style animated pill captions onto short-form videos using MoviePy + PIL. Takes a base MP4, a captions JSON...
List every skill in this repo with its name and one-line description, read live from skills/*/SKILL.md frontmatter. Use...
Generate interactive HTML visualizations of the skills collection, codebase structure, or dependency graphs. Uses D3.js...
Expert web designer for responsive, mobile-first websites. Specializes in landing pages using Astro, Tailwind CSS, and C...
Demonstrates how skills can bundle data files and configuration templates. Use when needing structured data, templates,...
A test skill with full YAML frontmatter for testing frontmatter parsing
Demonstrates how skills can reference external documentation files. Use when you need to load guidelines, best practices...
A skill with references, metadata, and all optional fields.
A template for skills that include executable code for deterministic operations.
Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Use when asked to "cr...
Write skills to the library's quality bar — trigger-rich descriptions, checkable rules, self-improvement loop, token-lea...
Create and improve Claude Code skills. Use when drafting new skills, writing SKILL.md files, improving skill description...
Create and improve agent skills following the Agent Skills specification. Use when asked to create, write, or update ski...
Draft gate for writing or substantially revising a skill or agent definition. Use when making or revising a skill (skill...
Expert assistant for authoring Claude Code skills. Creates SKILL.md files with proper YAML frontmatter, validates naming...
Use when deciding 'should this be a skill or a rule?', creating/improving/reviewing agent skills, SKILL.md frontmatter,...
Creates effective Claude Code skills following best practices. Use when the user asks to create a skill, write a SKILL.m...
Create new Claude Code skills following best practices including optimal descriptions, progressive disclosure, proper st...
Create/scaffold/init a project-local agent skill under `.agents/skills` in an ordinary repository; defer to repository i...
Use when creating, reviewing, or refining Agent Skills for this repository
Use this skill when the task involves coding-agent interpretability, hidden states, residual streams, linear probes, lat...
Report the zero cut — temporary automatic skills are cut, and `all` cuts every skill summon.
This skill enables the agent to automatically answer Gmail messages on behalf of a client. The agent drafts and (when th...
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutor...
Create comprehensive marketing content for themes, plugins, and web products. Generates organized folder structure with...
> Steganography reconnaissance and steganalysis. Detects hidden payloads in image, audio, video, and document carriers...
Skill for AI agent capabilities
Execute approved sprint plans with test-driven development, continuous linting, progress tracking, and pause points. Use...
Backend expert guidance for API/DB/Security/Architecture
Execute high-density analysis on complex ideas/tasks. Move from 'Vague' to 'Verified' by producing: constraints -> core...
Async via cask, end turn immediately; use only when user explicitly delegates to Codex (ask/@codex/let codex/review); NO...
Async via oask, end turn immediately; use only when user explicitly delegates to OpenCode (ask/@opencode/let opencode/re...
Performs comprehensive frontend quality assurance reviews using browser automation. Systematically tests UI elements, di...
Claude can interact with {{SKILLNAME}} to help you manage and automate tasks. {{DESCRIPTION}}
{{extendeddescription}}
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, ne...
Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks...
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots...
Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel re...
Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the u...
Optimize an existing SKILL.md from a usage-intent description with SkillAdam. Use when a user asks to test, improve, pat...
SkillAlchemy — One thought conceived, one goal achieved. Accept any idea or distillation target and produce an installab...
Build, run, troubleshoot, or extend SkillBar, the codex-goated-skills macOS menu bar manager. Use when Codex needs to wo...
Manage Skillcaddy source acquisition, source updates, migrations, project skill links, and the Web/TUI CLI. Use for disc...
Measure whether the user's Claude Code or Codex skills actually trigger in their real setup, next to all their other ins...
Agent skill imported from AMAP-ML/SkillClaw
Create, design, and package Clawdbot skills. Use when asked to "make/build/craft a skill for X", or when extracting ad-h...
Operate skilld CLI for Skill discovery, use, installation, inspection, updates, authentication, configuration, restorati...
Designs and verifies skilld CLI output, terminal pickers, and full-screen flows. Use for terminal colours, loading feedb...
Mine local agent transcripts into redacted workflow-pattern evidence and recommend at most five automation specs as an e...
Run and interpret SkillEvaluator for agent skills. Use for any skill benchmark or eval - validating or scoring a SKILL.m...
Generate production-grade Agent Skill packages through a structured 7-step pipeline: requirement analysis, architecture...
Route any user request, error, code, or URL to the right skill action—recommend existing skills, suggest improvements, o...
Intelligent skill router and creator. Analyzes ANY input to recommend existing skills, improve them, or create new ones....
Use when creating, improving, finding, or auditing agent skills - the user says 'create a skill', 'do I have a skill for...
Mine AI research insights and generate professional LaTeX reports for creta.mx (Center for Research on Economics and Tec...
Creates Claude subagents equipped with curated skills for solving problems within DAG workflows. Use when designing a sp...
Generate comprehensive Spanish README.md documentation for Svelte 5 projects with Mermaid diagrams. Use when art-vandele...
Local Issue, pull-request, and Wiki workbench for agent skills. Use when a user asks what skill problems, Issues, PRs, r...
Mandatory interception workflow for a reproducible defect encountered while any Agent is using a skill. Invoke this befo...
Run the additional paper-compatible optimization workflow with a frozen benchmark repository. Use only when the user ask...
SkillHub 每日推荐 - 扫描 skillhub.cn 全站 Top100 + 7 大分类各 Top20（共 240 个 Skill）， 基于用户痛点精准推荐高价值 Skill，支持 IMA/飞书/Obsidian 多通道存储。 触发...
Prefer `skillhub` for skill discovery/install/update, then fallback to `clawhub` when unavailable or no match. Use when...
Capture this session's repeatable process into a reusable skill. Call at end of a process you want to automate.
Turn something you just did into a reusable skill and register it in the resolver. Use when the user says "skillify this...
When you want to create, adapt, or update a Claude Code skill in one of your sibling repos (list your own repos in ~/.co...
Use when the user wants to turn a script, repeated workflow, runbook, or hard-won procedure into a reusable agent skill,...
Turn a transcript summary into a reusable Claude skill. Researches the topic and creates a skill file.
Auto-create new skills from repetitive workflows. When you notice yourself doing the same multi-step process repeatedly,...
Codify the most recent successful /scrape flow into a permanent browser-skill on disk. Future /scrape calls with the sam...
Turn a repeatable workflow from the current session into a reusable OMC skill draft
Codify the most recent successful /scrape flow into a permanent browser-skill on disk. (gstack)
Create a reusable, self-healing, self-evolving global skill — either from the current conversation context OR from a pla...
Turn a repeatable workflow into a reusable local SKILL.md with explicit steps, criteria, and safe defaults.
Manage Claude Code environments using natural language. Use this skill when: - User wants to add, deploy, or manage Clau...
Use when a user wants to set up, configure, run, or learn SkillOpt — the text-space skill optimizer that trains agent sk...
Use when the user asks about Microsoft SkillOpt, optimizing or training agent skill documents with reflective loops, eva...
Reference-only OpenClaw adaptation of SkillOpt-Sleep. Use it to study or port the contributed DeepSeek wrapper, not as a...
Use when the user wants their Claude agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dre...
Run `gbrain skillpack-check` to produce an agent-readable JSON health report for the gbrain install. Wraps `gbrain docto...
Create a reusable SkillPack from a successful completed task. Use when the user wants to convert a one-off research, cod...
Use when changing, testing, or automating skillpack-forge.