Skills — le catalogue de compétences de vos agents
Chaque skill est une capacité prête à l'emploi (GitHub, PDF, analyse d'images, marketing…) que votre agent charge et utilise de façon autonome. Installez en un clic depuis votre portail.
Discover all inbound links (backlinks) to a domain, subdomain, or GitHub repo, then classify each as "ours" (we created/control the source) vs "organic" (someone else). Use when the user asks to find/audit backlinks or inbound links to a site, check who links to a domain or a GitHub repo, separate self-made links from organic ones, or refresh an inbound-links graph. Wraps four sources (GitHub repo referrers, a list of URLs you found, the backlinks.sh Common-Crawl API, and a Google Search Console CSV export) behind one classify-and-report CLI. Two of the four need no account at all; the one opt
Researches GitHub repos/users/orgs and Chrome Web Store extensions via the Crawlora API — search, profiles, contributors, releases, trending, and extension detail/reviews/permissions — returning clean JSON. Use when the user wants a repo or developer's GitHub profile/stats, what's trending on GitHub, or a Chrome extension's details, permissions, or reviews.
Weixin Bot (github.com). Use this skill for ANY Weixin Bot request — reading, creating, and updating data. Whenever a task involves Weixin Bot, use this skill instead of calling the API directly.
从 agent 工作区推送文件到 GitHub 时的隔离检查与安全推送。触发:用户说「上传到 GitHub」「推到 GitHub」「创建 GitHub 仓库」「备份项目到 GitHub」等,且当前工作目录位于 OpenClaw workspace(~/.openclaw/workspace/)或任何被 git init 过的父级目录内。
Use when turning approved plans, specs, PRDs, or Epics into trackable GitHub Issues.
ClawMate 文件管理 + 预览 + 反馈闭环 + 项目管理。支持文件搜索预览、feedback 处理、项目初始化与前期梳理(Phase I-V)。GitHub: https://github.com/updatedb/clawmate
Search GitHub for repositories, code, issues, or projects matching the user's query. Use when the user asks to use GitHub for this purpose.
Internationalize the user-facing language layer of a GitHub repository, including its repository description, repository topics, README files, release notes, changelogs, and other explicitly selected documentation, with English as the default and any user-requested locales as mirrors. Use when a user asks to translate, localize, add language mirrors, or check cross-locale parity for a GitHub repository. Confirm the exact document and metadata scope when it is not explicit, identify existing locales, preserve facts, code, commands, links, images, and structure, and provide local Markdown plus G
Review a public repository release across version and tag consistency, final build artifacts, archives, secrets and internal material, third-party licenses, production response headers, and GitHub Release attachments. Use when the user asks to publish, create a tag or Release, verify a launch, or run the complete public-release gate, adapting checks to the project's configuration.
End-to-end pull-request flow with a review gate — reviews the branch BEFORE publishing (code-review skill's branch scope if installed; blockers must be fixed or explicitly waived), pushes with user approval, creates one PR per repo for multi-repo work items with house defaults from config (title pattern, target branch, required reviewers, auto-complete, work-item link), cross-references sibling PRs with deploy-order coupling, verifies every setting after creation, and reports the URLs. Detects the provider from the git remote (Azure DevOps via the azure-devops skill, GitHub via gh). Use this s
Fully autonomous end-to-end run of ONE defined task with no human gates — a work item (Azure DevOps or GitHub id, or inline text) becomes a verified working tree plus an evidence-backed report, and every question that would have been asked becomes a logged assumption with its blast radius. Puts every applicable skill in this library to work on observable predicates, and stops dead before any commit, push, or PR. Hard stops only for a destructive or irreversible step, missing access, an architectural or unimplementable spec, or three failed fixes on one behavior. Use this skill whenever the use
Pull GitHub profiles, repos, READMEs, releases, issues and comments, run GitHub search, and get composite intelligence - a repo dossier, a user's activity velocity, reaction-ranked top issues, and public commit emails. 13 endpoints, structured JSON.
Open GitHub in the user's Brave browser and take the user to GitHub's main page. Reuse an existing GitHub tab/session when possible. Use when the user asks to open, visit, or go to Open GitHub.
Quickly open-source a local skill to GitHub (primary) and optionally clawhub.com. Workflow: slug pre-check, fork to opensourceskills, strip internal info, normalize SKILL.md, generate LICENSE/README, init git, push to GitHub with configurable token source, and optionally publish to clawhub. Use when the user says "open-source this skill", "把这个 skill 开源", "发到 github", "publish skill publicly", or "把本地 skill 发开源". Hard rules: never modify the original skill in place, never auto-add force/yes flags, never write tokens to git/remote/memory, and ask the user at decision points.
Every call the team records is collected into the cadence layer each morning, scribed into a log entry, and — once a claim repeats — promoted into the context knowledge layer, as one reviewable pull request against your GTM repo. Triggers: "our call recordings never make it into the knowledge base", "turn our call transcripts into context", "keep our context updated from sales calls", "we relearn the same objection every quarter", "scribe yesterday's calls into the repo every morning", "replace the GitHub Action that summarizes our meetings". Cargo CDK, defineAgent, harnessSlug claudeCode, rep
Give your AI agents and automations their own GitHub (App) identity. Authenticate using GitHub Apps so every commit, PR, and action is attributed to the bot — not your personal account. Supports multiple profiles for running several GitHub Apps (e.g. one per client/org) from the same machine.
支持 Bing/Baidu 通用搜索、知乎中文问答社区、小红书生活方式社区、GitHub代码仓库、 arXiv学术论文、199it互联网数据、东方财富财经资讯、智联招聘、前程无忧等多源搜索【按需持续增加】。 从多个平台搜索内容,实现统一搜索和内容提取,帮助AI Agent获取全网信息。 只要涉及获取网络信息——无论是搜索资讯、调研主题、查找资料、提取文章、多源对比—— 都应立即调用。即使用户未明确说"搜索",只要需要网络信息支撑,自动使用本skill。
Convert Word (.doc, .docx), PowerPoint (.ppt, .pptx), Excel (.xls, .xlsx), OpenDocument (.odt, .ods, .odp), RTF, EPUB, CSV, and PDF files to GitHub-Flavored Markdown. Use when a task needs the contents of an office document, spreadsheet, presentation, ebook, or PDF you cannot read directly.
Drive a self-hosted gitrakz instance — the tool that syncs a GitHub user's activity into local SQLite, renders a filterable timeline and derived work sessions, and runs deterministic programmatic templates that export to CSV/PDF/JSON. Install or run it with Docker, then query its bearer-protected REST API under /api/v1 (owners, repos, timeline, sessions, sync + sync status, templates CRUD, LLM template generation, run, export) — or drive the same capabilities as MCP tools over streamable HTTP (/mcp) or stdio (`gitrakz mcp`). Use when the user wants to set up gitrakz, trigger or check a GitHub
吸星大法 / Skill Consolidator:扫描并整理本地已安装的 AI Agent skills / rules / commands(WorkBuddy、Trae、Cursor、Claude Code、Windsurf、Cline、Continue、Roo Code、GitHub Copilot、OpenAI Codex 等),检测同名冲突、功能重叠、触发词冲突与版本差异,生成整理报告与分类索引。当用户输入 /吸星大法 或 /skill-consolidator、请求整理/清理/查看 skills(如"帮我整理 skill"、"skills 冲突了"、"organize my skills"),或在安装新 skill 之前评估冲突时自动调用。Scans and consolidates installed AI Agent skills, detects conflicts and overlaps, generates cleanup reports and categorized indexes.
大模型 Token 成本节约工具。在请求到达大模型之前自动压缩 prompt 和上下文,减少 60-95% 的 token 消耗,直接降低 API 成本。支持 Claude/OpenAI/Gemini 等主流模型,提供代理模式、CLI 包装、Python SDK 和 MCP Server 四种接入方式。内置一键安装脚本、企业内网适配方案、压缩效果对比报告、场景专项配置(法律/医疗/金融/代码)、模型更新指南,以及可选的数据上报功能(可随时关闭,首次使用引导用户选择)。基于开源项目 headroom(https://github.com/chopratejas/headroom,MIT License)封装,已注明来源与许可证。
场景驱动+关键词双模式技能发现工具。当用户用自然语言描述场景/需求(如"我想做一个海报""帮我分析股票"),或明确说"安装技能/find skills/找个skill"时,自动从官方内置、本地已安装、SkillHub、虾评、GitHub、ClawHub 六层联合搜索并推荐最合适的技能,支持一键安装。已完全替代官方原 find-skills 插件。
Sanitize and verify public GitHub contributions
AI科技资讯深度追踪与分析工作流。每日自动采集AI前沿动态、GitHub热门项目,生成3000-5000字技术深度文章并发布到公众号。