General AI agent skills

926 skills in the archive. Read a skill’s instructions or open its original repository.

• To Questionnaire

  by @mattpocock

  Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

• Wait What

  by @mattpocock

  Stop. That last message did not land: re-pitch it.

• Get Search View Results

  by @microsoft

  Get the current search results from the Search view in VS Code

• React Sync

  by @vercel

  Build local React changes in the bundle variants consumed by Next.js, sync them into a local Next.js checkout, and test the resulting integration. Use when working on React changes that need validation in Next.js, or when asked…

• Cuda Index Width

  by @pytorch

  Choose 32-bit vs 64-bit index math in PyTorch CUDA kernels. Use when fixing large-tensor indexing overflows, deciding whether to use int64_t, canUse32BitIndexMath, CUDA_KERNEL_LOOP_TYPE, or AT_DISPATCH_INDEX_TYPES, and when…

• Add Uint Support

  by @pytorch

  Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types,…

• Plan Change

  by @ruvnet

  Turn a feature request into a minimal, file-level implementation plan before any code.

• Simplified English

  by @paperclipai

  Write user-facing comments, plans, and documents in ASD-STE100 Simplified Technical English — short, unambiguous sentences with approved words and one meaning each — so readers understand them the first time.

• Archify Review

  by @tt-a1i

  Review Archify issues, PRs, or code through value, cost, and impact to support evidence-based maintenance decisions. Use for issue triage, change reviews, and code quality assessments.

• Init Project

  by @ruvnet

  Initialize a new Ruflo project with MCP tools, hooks, and agent configuration. Use when setting up Ruflo in a fresh repo, or when the user says "init ruflo", "set up ruflo", or asks how to bootstrap the MCP server, hooks, and…

• Browser Extract

  by @ruvnet

  Extract structured data via stored browser-templates or one-shot DOM queries, with mandatory AIDefence PII + prompt-injection gates before content reaches the model

• Adr Verify

  by @ruvnet

  Read back adr-patterns + adr-edges namespaces, surface dangling refs / supersede cycles / status mismatches; exit 1 on cycles

• Browser Record

  by @ruvnet

  Open a named, traced browser session into an RVF cognitive container with a ruvector trajectory recording every action

• Wasm Gallery

  by @ruvnet

  Browse, publish, and install WASM agents from the community gallery

• Cherry Assistant Guide

  by @CherryHQ

  从当前安装包查询 Cherry Studio 产品信息并排查运行问题。当用户询问功能、路由、快捷键、Provider、语言、Agent、频道、定时任务、Code CLI、当前版本，或报告运行错误、连接失败、配置异常并需要诊断时触发。

• Cherry Skill Marketplace

  by @CherryHQ

  当用户明确要求搜索、安装、查看、卸载或创建 Skill，或内置 Skill / 工具出现能力缺口、无法完成当前任务时触发。通过 `mcp__skills__search_skills` 搜索并用 `mcp__skills__install_skill` 安装；已安装 Skill 的查看和删除通过产品清单导航到 Skills UI；没有合适结果时调用内置 `skill-creator` 创建并验证自定义 Skill，再继续原任务。普通任务仍先尝试内置能力。

• Skills Manager

  by @CherryHQ

  搜索、安装和协调创建 Claude Code Agent Skills。当用户想要搜索技能、安装工具、创建自定义 Skill，或者说"find a skill"、"搜索技能"、"帮我做个 skill"、"create a skill"时触发。也适用于用户说"有没有做 X 的工具"、"我想扩展 Agent 能力"，或当前能力不足需要先查找可复用方案的场景。

• Issue Reporter

  by @CherryHQ

  只在用户明确要求提交 GitHub Issue、GitHub Bug Report 或 GitHub Feature Request 时使用。用户只说“提交问题”“提交反馈”“上报 bug”“这是个 bug”或描述功能建议但未点名 GitHub 时不得触发，必须改用 cherry-studio-feedback 并默认提交飞书。

• Faq Collector

  by @CherryHQ

  将成功解决的用户问题收录到 FAQ 知识库。问题解决后自动判断是否收录。也可以在用户说"收录到 FAQ"、"记录这个问题"、"add to FAQ"时手动触发。

• Cli Anything 3mf

  by @HKUDS

  3MF mesh geometry editor — detect and resize cylindrical holes, repair meshes, compare 3D printing files. Works with BambuStudio and PrusaSlicer 3MF files.

• Cli Anything Intelwatch

  by @HKUDS

  Zero friction. Full context. Competitive intelligence, M&A due diligence, and OSINT directly from your terminal. Uses Node.js/npx.

• Cli Anything Godot

  by @HKUDS

  Agent-native CLI for Godot project management, scenes, exports, and script execution.

• Defuddle

  by @kepano

  Extract clean Markdown from HTML pages with Defuddle CLI.

• Memory Reflect

  by @vectorize-io

  Answer questions about history, habits and past decisions by reasoning over Hindsight memory. Use when asked what was decided about something, how something is usually done, what changed over time, or what is known about a topic.

• Memory Retain

  by @vectorize-io

  Save what was learned to Hindsight long-term memory. Use when a task finishes, when the user states a fact, decision or preference, and when you discover something a later run or another Bot would need.

• Add App Clip

  by @sickn33

  Add an iOS App Clip target to an Expo app. Use when the user mentions App Clip, AASA, apple-app-site-association, appclips, smart app banner, or wants to ship a lightweight iOS Clip invoked from a URL alongside their parent app.

• Advogado Especialista

  by @sickn33

  Advogado especialista em todas as areas do Direito brasileiro: familia, criminal, trabalhista, tributario, consumidor, imobiliario, empresarial, civil e constitucional.

• Advogado Criminal

  by @sickn33

  Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.

• Create Agent

  by @vectorize-io

  Create a new Hindsight-powered subagent with long-term memory. Use when the user wants a specialized agent that learns and remembers across sessions.

• Cqrs Implementation

  by @wshobson

  Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.

• Hud

  by @Yeachan-Heo

  Configure HUD display options (layout, presets, display elements)

• Omc Doctor

  by @Yeachan-Heo

  Diagnose and fix oh-my-claudecode installation issues

• Install Openviking Memory

  by @volcengine

  Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture…

• Weather

  by @volcengine

  Get current weather and forecasts (no API key required).

• Solo

  by @anthropics

  Work on one hard mathematics problem in this session yourself, with no sub-agents: reason in stages, record each settled step in a notes file so that nothing written is lost if a response is cut off, and end with a…

• Example Command

  by @anthropics

  An example user-invoked skill that demonstrates frontmatter options and the skills/<name>/SKILL.md layout

• Ctf Sandbox

  by @zhaoxuya520

  Thin PRIMARY for CTF / AWD / 靶场 multi-type orchestration. Hands off to the sidecar CTF-Sandbox-Orchestrator. Use when the user says CTF, AWD, 靶场, or 比赛题 and no more specific pwn/APK/IDA route already won.

• Make Plan

  by @agentscope-ai

  For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via list_agents and chat_with_agent, emphasizing that the plan is executed by the requester, not by…

• Computer Use

  by @agentscope-ai

  Use computer_use for live Windows or macOS GUI work that structured tools cannot complete. Discover an approved app and window, act from fresh observations, and verify every requested result.

• Professional Media Prompts

  by @agentscope-ai

  为 Creator 编译制作级视觉资产图、电影分镜图和参考生视频 Prompt。适用于 角色身份板/设定图、关键帧或多宫格分镜、短片动作节拍、R2V/I2V/T2V 提示词， 尤其适合要求角色一致性、镜头语言、参考图职责、Seedance 时间段或声音设计的 任务。不用于纯素材剪辑、只查询模型参数，或只评价已经生成的成片。

• Steve Jobs Perspective

  by @alchaincyf

  史蒂夫·乔布斯(Steve Jobs)的思维框架与表达方式。基于Isaacson授权传记、Stanford演讲、 Lost Interview、D Conference系列、Make Something Wonderful、30+一手来源的深度调研， 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用乔布斯的视角分析产品、审视决策、提供反馈。 当用户提到「用乔布斯的视角」「乔布斯会怎么看」「Jobs模式」「steve…

• Sun Yuchen Perspective

  by @alchaincyf

  孙宇晨（Justin Sun / 孙割）的思维框架与行为逻辑。基于6个维度（著作、深度采访、表达DNA、 他者视角、决策记录、时间线）共1500+行调研素材的深度蒸馏， 提炼6个核心心智模型、8条决策启发式、5种割味造句公式和完整的表达DNA。 用途：作为思维顾问，用孙宇晨的视角分析营销策略、注意力经济、危机公关、叙事操控、蹭热点方法论。 割味十足的角色扮演——自大、暴论、碰瓷、数字轰炸、成功学底色。…

• Zhang Yiming Perspective

  by @alchaincyf

  张一鸣（字节跳动/TikTok创始人）的思维框架与表达方式。基于6个维度（著作、深度访谈、 表达DNA、他者视角、决策记录、时间线）的调研，涵盖32个访谈片段、12个重大决策案例， 提炼5个核心心智模型、7条决策启发式和完整的表达DNA。 用途：作为思维顾问，用张一鸣的视角分析产品、组织、全球化、人才和个人成长问题。 当用户提到「用张一鸣的视角」「张一鸣会怎么看」「一鸣的思路」「zhang yiming perspective」时使用。…

• Zhangxuefeng Perspective

  by @alchaincyf

  张雪峰的思维框架与表达方式。基于5本著作、15+篇权威媒体深度采访、 30+条一手语录、11个关键决策记录和完整人生时间线的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用张雪峰的视角分析教育选择、职业规划、阶层流动等问题。 当用户提到「用张雪峰的视角」「张雪峰会怎么看」「张雪峰模式」「雪峰视角」时使用。 即使用户只是说「帮我用张雪峰的角度想想」「如果张雪峰会怎么说」「切换到张雪峰」也应触发。

• Munger Perspective

  by @alchaincyf

  查理·芒格的思维框架与表达方式。基于《穷查理宝典》、伯克希尔/Daily Journal股东会、 USC/哈佛演讲、访谈记录、外部批评等50+来源的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用芒格的视角分析问题、审视决策、提供反馈。 当用户提到「用芒格的视角」「芒格会怎么看」「芒格模式」「munger perspective」时使用。 也适用于：投资决策审视、认知偏误检查、跨学科思考训练、逆向思考练习。…

• Recipe Create Gmail Filter

  by @googleworkspace

  Create a Gmail filter to automatically label, star, or categorize incoming messages.

• Recipe Organize Drive Folder

  by @googleworkspace

  Create a Google Drive folder structure and move files into the right locations.

• Recipe Review Meet Participants

  by @googleworkspace

  Review who attended a Google Meet conference and for how long.

• Recipe Find Large Files

  by @googleworkspace

  Identify large Google Drive files consuming storage quota.

• Recipe Review Overdue Tasks

  by @googleworkspace

  Find Google Tasks that are past due and need attention.

• Recipe Collect Form Responses

  by @googleworkspace

  Retrieve and review responses from a Google Form.

• Add Atomic Chat Tool

  by @nanocoai

  Add Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.

• Add Ollama Tool

  by @nanocoai

  Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.

• Manage Mounts

  by @nanocoai

  Configure which host directories agent containers can access. View, add, or remove mount allowlist entries. Triggers on "mounts", "mount allowlist", "agent access to directories", "container mounts".

• Hardware

  by @sipeed

  Read and control I2C and SPI peripherals on Sipeed boards (LicheeRV Nano, MaixCAM, NanoKVM).

• Smart Search

  by @jackwener

  基于 opencli 命令的智能搜索路由器。当用户想要使用 OpenCLI、CLI 或 API 搜索、查询、查找或研究信息时，尤其是涉及指定网站、社交媒体、技术资料、新闻、购物、旅游、求职、金融或中文内容时，务必使用此 skill

• Baoyu Compress Image

  by @JimLiu

  Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "optimize image", "convert to webp", or reduce image file size.

• Create Control Manifest

  by @Donchitos

  Flat must-do/never-do rules sheet per system and layer, extracted from Accepted ADRs. ADRs explain why; this is actionable.

• Wtf

  by @EveryInc

  Explain the last message, or a supplied file, link, or passage, in plain language a person follows on the first read. Use when the user invokes wtf because they did not follow something. Use ce-explain to investigate how or why…

• Token Efficiency

  by @SuperClaude-Org

  Activate ultra-compressed output mode for maximum token efficiency. Use when context is running low, user requests brevity, or dealing with large-scale operations.

• Troubleshoot

  by @SuperClaude-Org

  Systematic troubleshooting with root cause analysis. Use when users report errors, bugs, or unexpected behavior. Never retry without understanding why.

• Ctx Doctor

  by @mksglu

  Run context-mode diagnostics. Checks runtimes, hooks, FTS5, plugin registration, npm and marketplace versions. Trigger: /context-mode:ctx-doctor

• Review Ui States

  by @every-app

  Enumerate and screenshot every UI state a PR adds or changes. Use when asked to show, capture, or screenshot the UI states of a PR or branch.

• Review Simplify

  by @every-app

  Review a PR for code that can be deleted or simplified. Use when asked to review for simplicity or unnecessary edge-case overengineering.

• P7

  by @tanweai

  P7 Senior Engineer mode — solution-driven execution under P8 supervision. Use when user says 'P7模式', '方案驱动', or when spawned as sub-task executor by P8. Produces: implementation plan + code + 3-question self-review, delivered…

• P9

  by @tanweai

  P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when coordinating 3+ parallel agents. Produces: Task Prompts (六要素) + P8…

• Pua Ja

  by @tanweai

  お前のAIを詰めろ。日本企業の詰め文化と体系的デバッグ方法論で全ての手段を尽くさせる。トリガー条件：(1) タスク失敗2回以上または同じアプローチの微調整ループ; (2)「解決できません」と言おうとする・手動対応を推奨・未検証で環境を原因帰属; (3) 受け身——検索しない・ソースを読まない・指示待ち; (4) ユーザーの不満：'もっと頑張れ'、'なんでまた失敗したの'、'なんとかしろ'。全タスクタイプ適用。初回失敗や既知修正の実行中はトリガーしない。

• Yes

  by @tanweai

  SB Leader 夸夸模式 — ENFP 型领导，懂情绪有节奏。底层行为不变（三条红线、方法论），旁白从施压变成共情+鼓励+偶尔戏谑吐槽。Triggers on: '/pua:yes', '夸夸模式', '唠嗑模式', '情绪价值', 'yes', '夸我', '鼓励模式'.

• Pua Reap Orphans

  by @tanweai

  PUA reap-orphans alias for Codex. Codex subcommand mapping for Claude Code /pua:reap-orphans style usage; invoke with $pua-reap-orphans.

• Pua Cancel Loop

  by @tanweai

  PUA cancel loop alias for Codex. Codex subcommand mapping for Claude Code /pua:cancel-loop style usage; invoke with $pua-cancel-loop.

• Pua Team Status

  by @tanweai

  PUA team status alias for Codex. Codex subcommand mapping for Claude Code /pua:team-status style usage; invoke with $pua-team-status.

• Pua Teardown All

  by @tanweai

  PUA teardown alias for Codex. Codex subcommand mapping for Claude Code /pua:teardown-all style usage; invoke with $pua-teardown-all.

• Pua Offline

  by @tanweai

  PUA offline alias for Codex. Codex subcommand mapping for Claude Code /pua:offline style usage; invoke with $pua-offline.

• Pua Survey

  by @tanweai

  PUA survey alias for Codex. Codex subcommand mapping for Claude Code /pua:survey style usage; invoke with $pua-survey.

• Pua Loop

  by @tanweai

  PUA Loop alias for Codex. Codex subcommand mapping for Claude Code /pua:loop style usage; invoke with $pua-loop.

• Pua Mama

  by @tanweai

  PUA mama alias for Codex. Codex subcommand mapping for Claude Code /pua:mama style usage; invoke with $pua-mama.

• Pua Kpi

  by @tanweai

  PUA KPI alias for Codex. Codex subcommand mapping for Claude Code /pua:kpi style usage; invoke with $pua-kpi.

• Pua Off

  by @tanweai

  PUA off alias for Codex. Codex subcommand mapping for Claude Code /pua:off style usage; invoke with $pua-off.

• Pua P10

  by @tanweai

  PUA P10 alias for Codex. Codex subcommand mapping for Claude Code /pua:p10 style usage; invoke with $pua-p10.

• Pua Pro

  by @tanweai

  PUA Pro alias for Codex. Codex subcommand mapping for Claude Code /pua:pro style usage; invoke with $pua-pro.

• Pua Yes

  by @tanweai

  PUA yes alias for Codex. Codex subcommand mapping for Claude Code /pua:yes style usage; invoke with $pua-yes.

• Pua On

  by @tanweai

  PUA on alias for Codex. Codex subcommand mapping for Claude Code /pua:on style usage; invoke with $pua-on.

• Pua P7

  by @tanweai

  PUA P7 alias for Codex. Codex subcommand mapping for Claude Code /pua:p7 style usage; invoke with $pua-p7.

• Pua P9

  by @tanweai

  PUA P9 alias for Codex. Codex subcommand mapping for Claude Code /pua:p9 style usage; invoke with $pua-p9.

• Pua Ja

  by @tanweai

  日本語の生産性コーチングモード。明示的な依頼、反復失敗、受け身、検証不足、品質不満のときに、構造化トラブルシューティングと証拠ベースの完了確認を促す。

• Mama

  by @tanweai

  妈妈唠叨模式 — 中国式妈妈提醒风格的生产力 coaching。底层行为仍是结构化排障、证据优先、完成质量检查。

• Good Skill Complex

  by @larksuite

  A very complex description that spans multiple lines and contains weird chars: !@#$%^&*()

• Good Skill

  by @larksuite

  This is a properly formatted skill.

• Good Skill Minimal

  by @larksuite

  Minimal valid description

• Lark Approval

  by @larksuite

  飞书审批：查询和处理审批待办/已办/实例，搜索可发起审批定义、查看定义详情并发起原生审批实例。当用户要处理审批任务、查看审批实例、搜索或发起审批时使用。审批待办不是飞书任务；非审批类待办走 lark-task。不负责创建审批定义；三方审批定义不走原生提单。

• Lark Suite

  by @larksuite

  飞书/Lark 聚合能力入口：管理飞书/Lark 产品能力（<!-- LARK_SUITE_KEYS -->等）。当 doubao.com 及其子域名承载飞书资源时也使用本入口，不要回退到 WebFetch。当用户需求涉及上述飞书业务域时使用。

• Lark Skill Maker

  by @larksuite

  创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。

• Lark Vc Agent

  by @larksuite

  仅当用户或上游配置显式指定 lark-vc-agent 时使用，相关请求统一交由 lark-meeting 技能处理。

• Lark Minutes

  by @larksuite

  仅当用户或上游配置显式指定 lark-minutes 时使用，相关请求统一交由 lark-meeting 技能处理。

• Lark Note

  by @larksuite

  仅当用户或上游配置显式指定 lark-note 时使用，相关请求统一交由 lark-meeting 技能处理。

• Lark Vc

  by @larksuite

  仅当用户或上游配置显式指定 lark-vc 时使用，相关请求统一交由 lark-meeting 技能处理。

• Redux

  by @vercel-labs

  Redux adapter for json-render's StateStore interface. Use when integrating json-render with Redux or Redux Toolkit for state management via @json-render/redux.

• Xstate

  by @vercel-labs

  XState Store adapter for json-render's StateStore interface. Use when integrating json-render with @xstate/store for state management via @json-render/xstate.

• Zustand

  by @vercel-labs

  Zustand adapter for json-render's StateStore interface. Use when integrating json-render with Zustand for state management via @json-render/zustand.

• Jotai

  by @vercel-labs

  Jotai adapter for json-render's StateStore interface. Use when integrating json-render with Jotai for state management via @json-render/jotai.