AI Skills Hub - Browse 180,000+ Agent Skills

Data transformation utilities for JSON, CSV, XML, YAML, and Markdown. Parse, convert, query, and transform data between formats with JQ-like filtering support.

Windows 窗口截图工具，使用 Win32 API 捕获物理分辨率截图。

Configure and manage GitHub MCP server with 1Password token management. Use when working with GitHub repositories, issues, pull requests, and workflows.

Cron障害の調査・復旧。「Cronが失敗してる」「データが欠損してる」「ワークフロー調査して」「バックフィルして」で使用する。

Design and implement progressive disclosure for LLM features to reduce token usage and cost. Use when building multi-step AI calls (rank then expand then finalize), enforcing structured JSON outputs, applying token budgets, caching, and fallbacks—especially for front-end products like "职径导航" that generate job recommendations and career paths.

Automate MT4 (MetaTrader 4) backtesting workflows including single and parallel backtesting, report parsing, SL Hunting, MDD Date Search, Param QC and Spread Boundary finding.

Implement @data-client Managers for global side effects - websocket, SSE, polling, subscriptions, logging, middleware, Controller actions, redux pattern

Use @data-client/react hooks - useSuspense, useQuery, useCache, useLive, useDLE, useSubscription, useController for fetch/mutations, DataProvider, AsyncBoundary, useLoading, useDebounce

Test @data-client/react with renderDataHook - jest unit tests, fixtures, interceptors, mock responses, nock HTTP mocking, hook testing, component testing

Creates, modifies, and validates skills following best practices. Use when creating new skills, modifying existing skills, or validating skill structure.

轻量级笔记 CLI - 通过 Daily Note 后端创建、获取、更新、删除和搜索笔记

Manages project knowledge using ByteRover context tree. Provides two operations: query (retrieve knowledge) and curate (store knowledge). Invoke when user requests information lookup, pattern discovery, or knowledge persistence. Developed by ByteRover Inc. (https://byterover.dev/)

Use the RSSaurus command-line client (Go binary `rssaurus`) to interact with https://rssaurus.com from the terminal: authenticate (`rssaurus auth login/whoami`), list feeds/items, print item URLs for piping, open URLs, and perform triage actions (mark read/unread, bulk mark-read, save/unsave). Use when asked to automate RSSaurus tasks from CLI, debug token/config issues, or demonstrate command usage.

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.

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).

Interact with Moltbook social network for AI agents. Post, reply, browse, and analyze engagement. Use when the user wants to engage with Moltbook, check their feed, reply to posts, or track their activity on the agent social network.

Execution Ledger and Policy Gate for Neobot System Governance

Professional Polymarket trading skill. Supports balance checking, market discovery (Token ID lookup), and real-money execution (BUY orders) for both EOA and Magic Link (Email) accounts.

하이퍼캐주얼 게임 개발 전문 스킬. Voodoo, Habi, ABI 스타일 1-2주 프로토타입에 최적화. DI 프레임워크 없이 System+Manager 패턴, ObjectSystem 기반 풀링, GC-free Update 패턴 제공. 모바일 빌드 사이즈 최적화(ASTC, Strip, Managed Stripping) 포함. 사용 시점 - (1) 하이퍼캐주얼 게임 개발, (2) 빠른 프로토타입 제작, (3) 모바일 성능/빌드 사이즈 최적화, (4) CPI 테스트용 게임 제작, (5) Unity, hypercasual, 하이퍼캐주얼, 프로토타입, CPI, mobile game, prototype 키워드 언급 시

MARA 프로젝트의 6-Layer Agent Pipeline 아키텍처를 점검하고 검증하는 스킬. Use when: (1) 새로운 Agent 추가 시 아키텍처 적합성 검증, (2) AGENT.md 품질 리뷰, (3) Layer 간 의존성 분석, (4) Input/Output 스키마 검증, (5) 전체 시스템 구조 점검. Triggers: "아키텍처 리뷰", "architecture review", "Agent 검증", "시스템 점검", "Layer 분석", "AGENT.md 검토", "의존성 분석", "스키마 검증"

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

搜索Qveris工具库，获取万千世界所有的工具

使用 Serper API 进行 Google 搜索、学术搜索、图片搜索等

执行Qveris工具，获取万千世界所有数据

查询同花顺iFind财务报表数据

Run the current main branch as the baseline for experiment comparison

Search local files using macOS Spotlight (mdfind). Fast indexed search across PDFs, Office docs, and plain text. Use when user asks to find files by content ("search my documents for X"), locate documents on topics ("find my resume", "tax forms"), or needs to discover files without knowing exact path. Triggers on phrases like "search Downloads for", "find PDFs about", "locate documents containing".

Automate Chrome browser interactions via JSON passed to a Node.js CLI. Use when you need to navigate websites, fill forms, click elements, extract data, or run end-to-end browser tests. Automatic screenshots on every action. Supports accessibility snapshots for resilient element targeting.

Convert Jenkins pipelines (Jenkinsfiles) to GitHub Actions workflows. Use when migrating CI/CD from Jenkins to GitHub Actions, converting a Jenkinsfile, or when user mentions Jenkins pipeline migration.

영상 또는 오디오 파일에서 무음 구간과 필러 단어를 자동으로 제거하여 편집된 파일을 생성합니다.

Remove Gemini AI watermark (diamond shape in bottom-right corner) from images. Use this for Gemini-generated images.

Analyze disk space and find cleanable files. Use when user wants to clean disk, free up space, find large files, analyze disk usage, or asks about what's taking up space. Triggers on requests like "clean my disk", "free up space on C:", "find large files", "what's using my disk space", "disk cleanup".

Create property listing scrapers with proxy support and error resilience

Import Excel/CSV data into the database with validation

Add scripts to the consolidated nightly job runner

Create and test Alembic database migrations safely

ClawType — The MBTI for AI Agents. Discover your agent personality type through a 32-question self-assessment test.

プロンプトから、またはこのテンプレートを複製することで、GitHub Copilot 用の新しいエージェントスキルを作成できます。「スキルを作成」​​「新しいスキルを作成」​​「スキルのスキャフォールディング」を求められた場合、またはバンドルされたリソースを使用して特殊な AI 機能を構築する場合に使用します。適切なフロントマター、ディレクトリ構造、およびオプションの scripts/references/assets フォルダを含む SKILL.md ファイルを生成します。

Interact with the Jules CLI to manage asynchronous coding sessions. Use this skill sparingly for complex, isolated tasks that benefit from a remote VM.

Keeps the file structure honest. No stale paths. No broken references. No "I swear that file was here yesterday."

Baixa processos do PJE via API REST. Use com /baixar-pje ou /baixar-converter.

This skill should be used when the user wants to "create a skill for the team", "add a command to .agents/", "create an agent", "understand .agents/ architecture", "explain how to create components", "what's the difference between skills and commands", or needs guidance on creating skills, commands, or agents within the .agents/ system, with automatic synchronization across all platforms.

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

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

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Use when working with Lean 4 (.lean files), writing mathematical proofs, seeing "failed to synthesize instance" errors, managing sorry/axiom elimination, or searching mathlib for lemmas - provides build-first workflow, haveI/letI patterns, compiler-guided repair, and LSP integration

テキスト、ファイル、Webサイト等の内容から、講演・プレゼンテーション用のPowerPoint資料（.pptx）を作成します。テンプレート指定、スピーカーノートの自動生成に対応しています。

Create and maintain AGENTS.md / CLAUDE.md snippet indexes that route tasks to the correct dotnet-skills skills and agents (including compressed Vercel-style indexes).

Cache Playwright browser binaries in CI/CD pipelines (GitHub Actions, Azure DevOps) to avoid 1-2 minute download overhead on every build.

Read and analyze arXiv papers directly within Claude Code. Use when the user asks to read, summarize, or analyze an arXiv paper, or when working with paper URLs from arxiv.org.

Core security functions for signing, verifying, and attesting to the safety of AI agent skills and code.

Use the Netlify CLI (netlify) to create/link Netlify sites and set up CI/CD (continuous deployment) from GitHub, especially for monorepos (multiple sites in one repo like Hugo sites under sites/<domain>). Use when Avery asks to deploy a new site, connect a repo to Netlify, configure build/publish settings, set environment variables, enable deploy previews, or automate Netlify site creation.

Turn a source image (or multi-color mask image) into a 3D-printable bas-relief STL by mapping colors (or grayscale) to heights. Use when you have an image from an image-gen skill (nano-banana-pro, etc.) and want a real, printable model (STL) via a deterministic pipeline.

Create RFQ-ready 2D DXF (and optional SVG preview) files from a strict, validated JSON spec derived from a natural-language design prompt. Use for sheet/plate parts (waterjet/laser/router) like mounting plates, gussets, brackets, hole patterns, and slots.

Render an STL to a PNG from a nice, consistent 3D angle ("Blender-ish" default perspective) with a solid color.

Convexでの開発パターンとベストプラクティス

Expand and analyze URLs using Google Gemini 2.5 Flash URL Context API. Efficiently fetches, summarizes, and extracts information from up to 20 URLs per request with grounding metadata and source citations.

Blender 5.x MCP integration with 52+ tools for 3D modeling, materials, physics, animation, and rendering

High-performance WebAssembly graphics with JavaScript interoperability for web applications.

Provides Typer templates, handles registration, and ensures consistency. ALWAYS use this skill when adding or modifying CLI commands. Use when user requests to add/create/implement/build/write a new command (e.g., "add edit command", "create search feature") OR update/modify/change/edit an existing command.

Generate pytest tests for Typer CLI commands. Includes fixtures (temp_storage, sample_data), CliRunner patterns, confirmation handling (y/n/--force), and edge case coverage. Use when user asks to "write tests for", "test my CLI", "add test coverage", or any CLI + test request.

Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts.

Enforces best-practice standards for commits and pull requests. Use this skill before creating any PR to ensure work is world-class and ready for public scrutiny.

Use when creating or editing skills for ai-coding-config repo

Run verification commands and confirm output before claiming success

Set up automated cleanup of dead git worktrees and merged branches. Use when user wants to automate worktree/branch cleanup, schedule daily git maintenance, clean up stale branches on wake/login, or set up launchd automation for git hygiene.

Detect and resolve TypeScript/JavaScript circular import dependencies. Use when: (1) "Cannot access 'X' before initialization" at runtime, (2) Import returns undefined unexpectedly, (3) "ReferenceError: Cannot access X before initialization", (4) Type errors that disappear when you change import order, (5) Jest/Vitest tests fail with undefined imports that work in browser.

基于用户提供的主题Prompt，借助OpenAI DALL-E、Google Nano Banana等大模型生成图片，支持选择图片风格和图片参数（分辨率、宽高比）。当用户要求生成图片时使用。

Git worktree guide for parallel Claude development. Use when running multiple Claude instances, parallel feature work, or avoiding branch switching. Triggers on "worktree", "parallel Claude", "multiple instances", "parallel development".

Auto-loads during /verify or when validating compositions

Use this skill to track institutional investor ownership changes and portfolio flows using 13F filings data. Analyzes hedge funds, mutual funds, and other institutional holders to identify stocks with significant smart money accumulation or distribution. Helps discover stocks before major moves by following where sophisticated investors are deploying capital.

Screen US stocks using William O'Neil's CANSLIM growth stock methodology. Use when user requests CANSLIM stock screening, growth stock analysis, momentum stock identification, or wants to find stocks with strong earnings and price momentum following O'Neil's investment system.

NetGraph contributor development workflow. Use when: setting up dev environment, running tests or lint, fixing CI failures, running performance benchmarks, troubleshooting venv issues, or asking about make targets. For running scenarios and interpreting results, use netgraph-dsl instead.

NetGraph scenario DSL for defining network topologies, traffic demands, failure policies, and analysis workflows in YAML. Use when: creating or editing .yaml/.yml network scenarios, defining nodes/links/groups, writing link rules with patterns, configuring selectors or blueprints, setting up traffic demands or failure policies, running scenarios and interpreting results, debugging DSL syntax or validation errors, or asking about NetGraph scenario structure.

Verify AI agent identity and reputation via ERC-8004 on-chain registries

Interact with Moltbook social network for AI agents. Post, reply, browse, and analyze engagement. Use when the user wants to engage with Moltbook, check their feed, reply to posts, or track their activity on the agent social network.

Intervals.icu API for wellness, activities, power curves, and fitness metrics.

Build production-ready AI agents in TypeScript using Google Agent Development Kit (ADK). Use when creating agentic TypeScript/JavaScript applications with LlmAgent, workflow agents (SequentialAgent, ParallelAgent, LoopAgent), custom agents (BaseAgent with runAsyncImpl), FunctionTool with Zod schemas, MCP and OpenAPI tools, multi-agent orchestration, session and state management (outputKey, app/user/temp prefixes, CallbackContext), callbacks and guardrails, testing and evaluation, backend frameworks (Express, Hono), or deploying to Cloud Run or containers. Triggers on "build an agent TypeScript", "ADK TypeScript", "ADK TS", "@google/adk", "multi-agent system TypeScript", "agentic application TypeScript", "Gemini agent TypeScript".

Debugs Kubernetes RBAC and permission issues including Forbidden errors, ServiceAccount permissions, Role/RoleBinding, and ClusterRole/ClusterRoleBinding problems. Use when seeing permission denied, forbidden errors, or ServiceAccount access issues.

Debugs Kubernetes pod failures including CrashLoopBackOff, OOMKilled, ImagePullBackOff, init container failures, and CreateContainerConfigError. Use when pods crash, restart repeatedly, fail to start, or show container errors.

Retrieves Kubernetes container logs with various patterns including multi-container pods, previous container logs, init containers, and label-based aggregation. Use when checking application logs, debugging crashes, or analyzing container output.

Debugs Kubernetes pod scheduling issues including pods stuck in Pending, node affinity/anti-affinity problems, taints and tolerations, insufficient node resources, and PodDisruptionBudget blocking. Use when pods won't schedule, stuck in Pending, or node placement issues.

Show epic dependency graph and execution order. Use when asking 'what's blocking what', 'execution order', 'dependency graph', 'what order should epics run', 'critical path', 'which epics can run in parallel'.

Manually trigger plan-sync to update downstream task specs after implementation drift. Use when code changes outpace specs.

Install OpenClaw plugins and skills from npm or ClawHub. Provides install_plugin, install_skill, and list_installed tools for managing extensions in the Cloudflare Worker environment.

Upscale low-resolution images using Real-ESRGAN (2x or 4x). Use when users want to increase image resolution, sharpen blurry images, or "enhance" photos.

Fetches historical price data, financial statements, and real-time market metrics using Python (yfinance) or web search. Use when the user asks for stock prices, historical data, financial metrics, beta, or Treasury rates.

Reads .docx Word files and extracts full content or paragraph/table lists. Invoke when user asks to read, parse, or summarize .docx documents.

Reads .doc Word files and extracts full content or paragraph/table lists. Invoke when user asks to read, parse, or summarize .doc documents.

Reads .pptx PowerPoint files and extracts full content or slide content lists. Invoke when user asks to read, parse, or summarize .pptx documents.

Teach chromatography process design - cut time optimization and multi-parameter optimization. Builds on /teach-chromsep fundamentals.

Run pySCENIC pipelines (GRN→regulons→AUCell) and summarize regulon activity per cluster/condition for scRNA-seq. Use when running pySCENIC on AnnData/loom, generating GRN/regularons/AUC, or producing DM vs Ctrl (or other group) reports with plots and tables.

Use when receiving code review feedback - before implementing suggestions, especially if feedback seems unclear or technically questionable. Requires technical verification and honest evaluation, not performative agreement.

Integrate CopilotKit frontend tools with Mastra agents for AI assistants that can directly manipulate React state. Use when setting up popup/sidebar chat interfaces with browser-executable tools for forms, content editors, or interactive UIs.

Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.

Create and convert PowerPoint presentations from Markdown using Marp. Use when the user wants to generate slides, manage themes, or convert MD to PPTX/PDF.

Views CircleCI pipelines, workflows, jobs, and output. Use when investigating CI failures or checking pipeline status.

當使用者要開新專案並複製本專案的文件治理模式（.cursor/rules、.cursor/skills、docs 結構）時使用。觸發語包含：開新專案、複製治理、scaffold 新專案、建立新專案並套用治理、不需要手動開目錄與複製。

Use this skill when the user asks to research information from NotebookLM, needs context from uploaded documents, or wants to leverage RAG (Retrieval-Augmented Generation) for coding tasks.