Agent Skills 是什么?
Agent Skills 是供 AI Agent 按需加载的可复用能力包,通常由 SKILL.md、操作说明、工作流、脚本和可选资源组成。任务与 Skill 描述匹配时,Agent 会读取相应内容来完成特定工作。
发现 Claude Skills、Codex Skills 与通用 Agent Skills,查看安装命令、源码仓库、用途和安全信息。
larksuite / cli
飞书云文档(Docx / Wiki 文档):读取和编辑飞书文档内容。当用户给出文档 URL 或 token,或需要查看、创建、编辑文档、插入或下载文档图片附件时使用。文档中嵌入的电子表格、多维表格、画板,先用本 skill 提取 token 再切到对应 skill。当用户给出 doubao.com 的 /docx/ 或 /wiki/ URL/token 时,也应直接使用本 skill;路由依据是 URL 路径模式和 token,而不是域名。不负责文档评论管理,也不负责表格或 Base 的数据操作。当用户明确要操作飞书思维笔记时,也使用本 skill。
larksuite / cli
飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、评论/权限/订阅、标题、版本和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。
mattpocock / skills
Compact the current conversation into a handoff document for another agent to pick up.
larksuite / cli
飞书会议纪要(Note)直查:已知 note_id 时查询纪要详情、展示类型、关联文档 token,并读取 unified 原始逐字记录。当用户已持有 note_id,或从文档显式 vc-node-id 获得 note_id 时使用。不负责会议/日程/妙记定位、文档标题搜索或 Docx 正文读取。
anthropics / skills
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
lllllllama / ai-paper-reproduction-skill
Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.
lllllllama / rigorpilot-skills
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted training, optional repository analysis, and optional paper-gap resolution, enforces conservative patch rules, records evidence assumptions deviations and human decision points, and writes the standardized `repro_outputs/` bundle. Do not use for paper summary, generic environment setup, isolated repo scanning, standalone command execution, silent protocol changes, score chasing, or broad research assistance outside repository-grounded reproduction.
lllllllama / rigorpilot-skills
Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.
lllllllama / rigorpilot-skills
Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with command, config, seed, log, checkpoint, status, and metric evidence written to standardized `train_outputs/`. Do not use for environment setup, exploratory sweeps, speculative idea implementation, or end-to-end orchestration.
firecrawl / cli
Download an entire website as local files — markdown, screenshots, or multiple formats per page. Use this skill when the user wants to save a site locally, download documentation for offline use, bulk-save pages as files, or says "download the site", "save as local files", "offline copy", "download all the docs", or "save for reference". Combines site mapping and scraping into organized local directories.
关于 Agent Skills 与安全安装的常见问题
Agent Skills 是供 AI Agent 按需加载的可复用能力包,通常由 SKILL.md、操作说明、工作流、脚本和可选资源组成。任务与 Skill 描述匹配时,Agent 会读取相应内容来完成特定工作。
Claude Skills 是适用于 Claude Code 或其他 Claude Agent 工作流的 Skills。安装后,Claude Code 会根据 Skill 描述在相关任务中加载 SKILL.md;安装前仍应检查指令、脚本、依赖和权限范围。
Codex Skills 是可由 OpenAI Codex 加载的 Agent Skills,用于补充特定领域知识、操作步骤和工具工作流。通常可以从源码仓库安装到 Skills 目录,随后由 Codex 在匹配任务中按需使用。
开放的 SKILL.md 形式可用于或适配 Claude Code、OpenAI Codex、Cursor、GitHub Copilot、Gemini CLI、VS Code 等编码 Agent。不同产品的安装目录、触发规则和资源支持可能不同。
应把 Skill 当作代码审查:安装前检查 SKILL.md、脚本、依赖、所需权限和源码仓库。安全徽章可以作为参考,但不代表绝对安全;涉及 Shell、网络或密钥时尤其要使用最小权限。
系统按规范化后的源码仓库和 Skill 标识去重。同一个 Skill 被多个目录或 awesome 列表收录,或同时兼容 Claude 与 Codex 时,只合并来源和兼容信息,不创建重复记录。