AI Skills Hub - Browse 180,000+ Agent Skills

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

X/Twitter CLI for reading, searching, posting, and engagement via cookies.

Four-phase debugging methodology with root cause analysis. Use when investigating bugs, fixing test failures, or troubleshooting unexpected behavior. Emphasizes NO FIXES WITHOUT ROOT CAUSE FIRST.

vox.ai 한국어 음성 에이전트 system prompt를 설계/작성/리팩터링한다. 템플릿, 런타임 변수 주입({{...}}), 필러 옵션, Character normalization(Spoken/Written), 도구/무음 액션, 테스트/운영 베스트 프랙티스가 필요할 때 사용한다.

Manage changelogs using Changie. Provides tools to initialize, add change fragments, batch releases, and merge version notes.

视频转 Markdown 技能。从在线视频（YouTube、Bilibili 等）提取语音内容， 生成带时间戳的字幕文本和结构化 Markdown 文档。当用户需要视频总结、 视频笔记、提取视频内容、分析视频要点时使用此技能。 支持长视频处理，输出包含完整字幕和结构化要点。

创建高效技能的指南。当用户想要创建新技能（或更新现有技能）以扩展 Copilot 的能力时，应使用此技能，包括专业知识、工作流程或工具集成。

查询天气信息的技能。获取指定城市的当前天气、温度、湿度、风速，并提供穿衣和出行建议。 当用户询问天气、气温、是否下雨、穿什么衣服、出行建议等问题时使用此技能。 支持中英文城市名称查询。

Comprehensive guide for MEXC Spot V3 API (REST & WebSocket with Protocol Buffers) including trading, market data, and user data streams. Triggers on tasks involving MEXC API integration, crypto trading bots, market data streams, or wallet operations.

Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.

Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features

Professional stock price tracking, fundamental analysis, and financial reporting tool. Supports global markets (US, KR, etc.), Crypto, and Forex with real-time data. (1) Real-time quotes, (2) Valuation metrics (PE, EPS, ROE), (3) Earnings calendar and consensus, (4) High-quality Candlestick & Line charts with technical indicators (MA5/20/60).

R targets package for pipeline workflows. Use for creating reproducible, Make-like data analysis pipelines.

R tinytex package for LaTeX distribution. Use for installing and managing a lightweight LaTeX distribution for PDF rendering.

R reticulate package for Python integration. Use for calling Python from R, importing Python modules, and data exchange.

Guidelines for calculating grades, averages, and Abitur projections (FOBOSO).

Generate comics and manga with AI. Use when user wants to create comics, manga, graphic novels, or sequential art with custom layouts, characters, and styles.

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.

対話形式で新しいスキルを作成するウィザード

Load when task involves semiconductor device data, IV/CV curves, wafer measurements, reliability testing, or statistical process control.

calculating Cp/Cpk, building control charts, analyzing wafer maps, or performing lot acceptance.

parsing CSV/Excel measurement files, inspecting file structures, or ingesting raw semiconductor data via pandas.

determining valid comparisons between measurements, normalizing by device geometry, or grouping data by lot/wafer/die conditions.

analyzing stress testing data, degradation trends, NBTI/HCI/TDDB, or projecting device lifetime.

Guidelines and reference documentation for the Semantic Engine (SMQ to SQL, SQL to SMQ, Parser, Composer, Model Manager).

Call the local clawbot_codex finance HTTP API for stock quotes, structured stock analysis (A股/美股), and policy/tech hot topics. Use whenever the user asks to query prices, analyze a stock, summarize market hot topics, or wants evidence-linked news/announcements; respond using API results instead of re-implementing logic.

Read, search, and send email via IMAP/SMTP. Use when you need to check email from non-Gmail accounts (Proton Mail, Outlook via IMAP, any standard mail server). Supports Proton Mail Bridge on localhost.

Text-to-Speech service using Doubao (Volcano Engine) API with 200+ voices, interactive voice selection, and multilingual support

扫描并检测 Flutter 代码中的视觉规范违规项（硬编码颜色、圆角、间距），确保 UI 代码符合设计系统规范

Template Diff Summary

when using Vercel CLI tool or managing Vercel deployments

创建高效技能的中文指南。当用户想要创建新技能（或更新现有技能）以扩展 Claude 的能力时，应使用此技能。适用于需要专业知识、工作流程或工具集成的场景。

Use chdb (embedded ClickHouse) to evaluate and validate ClickHouse SQL syntax without a running server. Use for SQL syntax validation and testing.

Create basic Salvo web applications with handlers, routers, and server setup. Use when starting a new Salvo project or adding basic HTTP endpoints.

Modal へのデプロイを実行するスキル。スキルアップロードとアプリデプロイを順番に実行し、作業ログに記録します。

Three.js 3Dゲーム・ビジュアライゼーション生成スキル。CDN + ES Modules形式でのコード生成、最新API (r170+) のベストプラクティス、非推奨APIの回避、物理エンジン(cannon-es/Rapier)連携、モバイルジョイスティック実装に対応。使用タイミング：(1) Three.jsを使った3Dゲームやビジュアライゼーションの生成、(2) 物理エンジンを使った動的なシーン、(3) モバイル対応のゲームコントローラー実装

必須環境変数が設定されているか確認するスキル。起動前のチェックやトラブルシューティングに使用します。

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

GitHub IssueからGit worktreeを作成し、tmuxセッション内で別のpiインスタンスを起動してタスクを実行します。並列開発に最適。

Build full-stack React applications using React Router's framework mode. Use when configuring routes, working with loaders and actions, handling forms, handling navigation, pending/optimistic UI, error boundaries, or working with react-router.config.ts or other react router conventions.

Internationalization best practices for React Router framework mode using remix-i18next. Use when setting up locales, middleware, resource routes, or language switching.

Digital FTE Competitive Exam Tutor for SPSC, PPSC, and KPPSC provincial public service commission exams. Use this skill bundle when students need exam preparation help including diagnostic assessments, adaptive practice tests, progress tracking, weak area identification, Exam Readiness Index (ERI) calculation, and personalized study plans. Supports the complete exam preparation lifecycle from initial diagnosis to exam readiness.

Creates an audit log entry for a practice session. Use this skill at the end of every practice session for debugging, analytics, and audit trail purposes. Records session metadata, duration, and key events. Optional skill for compliance and troubleshooting.

The approval-workflow skill handles the human approval process for items that require review before activation or publication. It moves items between needs_action/ and done/ folders, updates their status, and triggers notifications.

Evaluates a set of student answers against correct answers. Use this skill after a student completes any test or assessment. Returns per-question results and aggregate statistics. Pure computation skill with no file operations or side effects.

Generates professional test case documents based on project requirements (PRDs, Test Plans). Use when the user requests a list of test cases, test scenarios, or a formal test specification. Strictly requires source documentation to avoid hallucination.

Workflow for maintaining the LUSENA Shopify Dawn theme. Use when making substantial theme changes (Liquid/JSON/CSS/JS, templates, theme settings, cart/PDP UX) to ensure changes are validated, committed, and documented in docs/THEME_CHANGES.md.

Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks AeonSage to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

Display HTML content on connected AeonSage nodes (Mac app, iOS, Android).

Sync plan files from specs/{plan-name}/{plan-name}-plan.md to Jira. Creates/updates/closes subtasks under an epic. Use when user asks to sync a plan to Jira.

Create, evaluate, and improve Claude Code skills. Use when working with SKILL.md files, debugging skill activation, or building new skills.

Fetch URLs and extract only relevant content via intent. Triggers: URL OR URL + intent, smart-fetch, what does this page say about.

士業・専門家（税理士、行政書士、診断士、弁護士、ITコンサル等）向けのWebサイトを、複数のClaude Codeエージェントで並列構築するためのオーケストレーションスキル。

The **Maestro Worker Skill** is a set of CLI commands that Claude can use **from inside a session** to update task status and progress.

Use when about to claim work is complete, fixed, or passing. REQUIRES running verification commands and confirming output before making any success claims. Evidence before assertions, always.

Use when starting feature work that needs isolation from current workspace. Creates isolated git worktrees with smart directory selection and safety verification.

You help users extract structured data from documents using the renamed.to AI extraction service.

Organize files in a directory — rename, extract data, and split PDFs in a single workflow. Use when the user wants to clean up a messy folder of documents.

Split PDF documents by content or topic using AI. Use when the user wants to break apart multi-document PDFs, split scanned batches, or separate PDF sections.

Rename files intelligently using AI content analysis. Use when the user wants to rename files based on their content, batch rename documents, or organize file names.

Platform Engineer and Azure Container Apps Specialist. Use for container orchestration, Dapr configuration, scaling policies, infrastructure setup, and platform operations.

Build CLI applications using React. Use when creating terminal UIs, handling keyboard input, or building interactive command-line tools with React components. Supports flexbox layouts, text styling, focus management, and accessibility.

This skill should be used when the user asks to "set up", "get started", "first time setup", "configure VPK", "install dependencies", "generate ASAP credentials", "configure environment", "start dev servers", "fix ASAP errors", or wants to set up a new VPK project from scratch.

This skill should be used when the user asks to "sync with VPK", "pull updates", "push changes", "contribute back", "pull orphan branch", "update from VPK", "get latest VPK", "contribute feature branch", or wants to keep their prototype in sync with upstream VPK.

Filter apartment posts by criteria

INPUT: {thought}

Manage Trello boards, lists, and cards from OpenClaw/Clawd.

Use when the user asks to translate a skill, documentation, or any text from English to Spanish.

Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.

Unified search API across Google, Amazon, Yelp, OpenTable, Walmart, and more. Use when searching for products, local businesses, restaurants, shopping, images, news, or any web search. One API key, many engines.

Review and onboard skills staged in pending/ folders (shared and per-user).

CLI to manage emails via IMAP/SMTP. Use for listing, reading, writing, replying, forwarding, searching, and organizing emails. Activate when user asks about email, inbox, messages, or wants to send/read mail.

Read, write, edit, and format Excel files (.xlsx). Create spreadsheets, manipulate data, apply formatting, manage sheets, merge cells, find/replace, and export to CSV/JSON/Markdown.

Gmail OAuth2 access without app passwords. Check, search, read, and send Gmail messages using OAuth2 authentication.

Gmail, Calendar, Drive, Docs, Sheets — NO Google Cloud Console required. Just OAuth sign-in. Zero setup complexity vs traditional Google API integrations.

综合性股票技术分析工具，小白友好。采用混合数据源（Yahoo Finance + Alpha Vantage MCP），提供通俗易懂的分析报告、买卖点建议、Excel持仓管理。支持港股本地计算、ATR动态止损、KDJ随机指标、MACD/RSI背离检测、OBV量能分析、斐波那契支撑阻力位、K线形态识别（锤子线/吞没/十字星）、趋势形态识别（双底/头肩/三角形）。支持飞书多维表格同步。当用户请求股票分析、技术指标、交易建议、持仓分析时激活。

Play Zork and other Z-machine games via Discord chat using the Z-Machine API

Delegate code implementation/review/debugging/alternatives to Claude Code via a JSON bridge script. Multi-turn via SESSION_ID.

Run GUT unit tests for Godot projects. Use when: (1) Running unit tests, (2) Verifying code changes, (3) TDD development, (4) CI/CD testing.

Validate Godot GDScript files using gdlint, gdformat, gdradon, and LSP diagnostics. Use when users want to: (1) Check code quality after making changes, (2) Validate before committing, (3) Run code metrics analysis, (4) Run export validation, (5) Get real-time LSP diagnostics. Uses command-line tools directly and MCP tools for LSP integration.

Solidity smart contract development guidelines. Covers NatSpec documentation, naming conventions, file layout, and code style. Use when writing, reviewing, or refactoring Solidity contracts, or when the user asks about Solidity best practices, contract structure, or NatSpec.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies. Dispatch one agent per problem domain.

Use when receiving code review feedback. Requires technical evaluation, not performative agreement. Verify before implementing, push back if wrong.

GitHub操作の統合スキル。issue操作、PR操作、レビュースレッド操作を提供。 使用ケース:（1）リポジトリ情報取得、（2）issue取得/作成/更新、（3）PR作成（事前チェック統合）、 （4）レビューコメント取得、（5）スレッド返信、（6）スレッド解決、 （7）PRのCI状態取得、（8）ワークフローのログ取得

Build WhatsApp automations with Kapso workflows: configure WhatsApp triggers, edit workflow graphs, manage executions, deploy functions, and use databases/integrations for state. Use when automating WhatsApp conversations and event handling.

Connect WhatsApp to your product with Kapso: onboard customers with setup links, detect connections, receive events via webhooks, and send messages/templates/media. Also manage WhatsApp Flows (create/update/publish, data endpoints, encryption). Use when integrating WhatsApp end-to-end.

CRITICAL: Use for Makepad layout system. Triggers on: makepad layout, makepad width, makepad height, makepad flex, makepad padding, makepad margin, makepad flow, makepad align, Fit, Fill, Size, Walk, "how to center in makepad", makepad 布局, makepad 宽度, makepad 对齐, makepad 居中

Scans Substrate/Polkadot pallets for 7 critical vulnerabilities including arithmetic overflow, panic DoS, incorrect weights, and bad origin checks. Use when auditing Substrate runtimes or FRAME pallets.

Generates Mermaid diagrams from a text description. Invoke when user asks to draw/visualize flows, architecture, sequences, or state machines in Mermaid.

Split media files (video/audio) into audio segments by duration with silence-aware cut points using FFmpeg. Use when users need to segment long recordings, podcasts, lectures, or videos into chunks. Supports batch processing and any FFmpeg-compatible format.

Set up an evolutionary optimization experiment using the openevolve framework. Generates `config.yaml`, `evaluator.py`, and `initial_program.py` based on a user's optimization problem.

Recursive Skill Improvement for modes-of-reasoning reference files. Improves density, clarity, and actionability of reasoning mode documentation.

Compile a PRD or RFC into CCP-grounded outputs (anti-cousin by default) using the Idea Compiler pipeline, with explicit model routing and reproducible run manifests.

Generate memes using the memegen.link API with Unicode support. Fuzzy template matching finds the best meme for your prompt. Supports popular meme templates and custom images.

A guide for incrementally migrating UIKit apps to SwiftUI, ensuring the app remains functional throughout the process. Covers converting ViewControllers, migrating data, and adopting modern SwiftUI patterns.

Calculate memory budget for an E.O. configuration

A mental framework for understanding, explaining, and reasoning about any ML/DL algorithm by decomposing it into two core threads: forward (data→prediction) and backward (learning/correction). Covers ALL ML families: deep learning (Dense, CNN, RNN, Transformer, Attention), classical ML (KNN, SVM, Decision Tree, Random Forest, Naive Bayes, Linear/Logistic Regression), unsupervised (K-Means, PCA, DBSCAN), and ensemble methods (Bagging, Boosting, Stacking). Use when asked to explain any ML algorithm, layer, or architecture — or when answering ML/DL interview questions, teaching, debugging model behavior, or building intuition. Triggers: ML/DL explanation, algorithm analysis, interview prep, "how does X work", model walkthrough, gradient flow, teaching/tutoring.

Creates and updates agent commands/prompts for agentic platforms including Claude Code, GitHub Copilot, Cursor, Windsurf, and Gemini CLI. Use when creating slash commands, agent prompts, or custom commands, or when user mentions agent commands, prompts, command generation, or platform-specific agents.

This skill should be used when the user wants to manage Railway deployments, view logs, or debug issues. Covers deployment lifecycle (remove, stop, redeploy, restart), deployment visibility (list, status, history), and troubleshooting (logs, errors, failures, crashes, why deploy failed). NOT for deleting services - use environment skill with isDeleted for that.

spec/ディレクトリのYAML仕様書をレビューする。サブコマンドで対象を指定。