AI Skills Hub - Browse 180,000+ Agent Skills

Integrate skills capability into a TuringCoder project by bootstrapping AGENTS.md, .turing_coder_rules symlink, .agent/skills layout, and preinstalling find-skills and skill-creator.

AI-powered web app creation agent via natural language. Use when the user wants to create web apps or web3 applications. Supports creating apps from text descriptions, checking build status, viewing deployed URLs, managing credits, and listing projects. Apps are automatically deployed to minidev.fun with custom subdomains.

Gather and cache SLURM cluster information (partitions, GPUs, memory, QOS limits). Generates a readable summary doc on first run; returns the cached doc on subsequent runs.

Convert a PDF into a fake phone-scanned PDF using a vendored local script. Use when the user asks to make a PDF look scanned, photocopied, noisy, skewed, or low-quality while preserving multipage output.

Validates pipeline code (nodes, tools, graphs) against DeepRead's LangGraph patterns. Use when creating or modifying pipeline nodes, tools, or graphs.

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields, Instructions for searching arXiv papers using Python script and shell tool. Read SKILL.md to learn the workflow.

Deploy applications and websites to Vercel using the bundled `scripts/deploy.sh` claimable-preview flow. Use when the user asks to deploy to Vercel, wants a preview URL, or says to push a project live on Vercel.

Splunk Observability Cloud APM APIを使用してサービストポロジー、トレース、サービスメトリクス（エラー率・レイテンシ・スループット）を取得・分析するためのスキル。デバッグ時の問題特定、サービス依存関係の調査、環境別のサービス比較に使用。トレースID、サービス名、APM、依存関係、トポロジー、エラー率、レイテンシ、スループットなどのキーワードで起動。

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Add a repository to a workspace (clones if needed, creates worktree)

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.

You are a **Search Intent Research Specialist** who translates buyer pain points into actionable keyword research WITHOUT relying on SEO tools.

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

조선왕조실록(sillok.history.go.kr) 기사를 검색어 또는 TSV 파일 기반으로 크롤링하여 구조화된 JSON으로 저장. 원문과 국역을 함께 수집. "크롤링" + "실록" 키워드 조합 시 사용.

승정원일기(sjw.history.go.kr) 기사를 검색어 또는 날짜 범위로 크롤링하여 구조화된 JSON으로 저장. 한문 원문과 ITKC 국역을 함께 수집. "크롤링" + "승정원일기/승정원" 키워드 조합 시 사용.

네이버 뉴스 라이브러리(newslibrary.naver.com)의 1920~1999년 한국 주요 일간지 기사를 키워드 검색, 상세 필터 검색, 날짜 범위 열람 방식으로 크롤링하여 구조화된 JSON으로 저장. "크롤링" + "뉴스라이브러리/네이버뉴스/뉴스" 키워드 조합 시 사용.

한국고전종합DB(db.itkc.or.kr) 문집을 검색어 또는 서지ID 기반으로 크롤링하여 구조화된 JSON으로 저장. 원문과 국역을 함께 수집. "크롤링" + "문집/한국문집총간/ITKC" 키워드 조합 시 사용.

Operate consensus.tools end-to-end (post jobs, create submissions, cast votes, resolve results) using the local-first board. Hosted boards are optional and coming soon.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Conduct systematic literature reviews using a structured workflow. Use when starting a new research project, surveying a field, or documenting related work for a paper.

Plan optimal work schedules around bills and cashflow constraints while minimizing workdays

VChart图表库专家助手，支持问题诊断、配置生成、图片/Figma设计稿还原等场景，基于结构化知识库提供精确的图表开发解决方案

安全的git提交辅助。指定文件提交、输入验证、防止意外全量提交。关键词: commit, 提交, git commit, 安全提交

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Publishes markdown files as GitHub Gists using the gh CLI, automatically detecting and embedding referenced local images and GIFs. Use when asked to publish, share, or create a gist from a markdown file.

Converts multiple HTML files into a single PDF using pandoc. Use when asked to merge HTML pages into PDF, create a PDF book from HTML, or fix PDF generation issues.

Convert any document format TO Markdown. Supports 14 formats (PDF, DOCX, XLSX, PPTX, HTML, CSV, EPUB, MSG, and more) via unified CLI. Use when Claude needs to read or extract text from non-Markdown files.

Incremental planning artifact validator. Validates individual planning docs and story JSON without running the full doctor suite. Faster feedback during the planning phase.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Donate to charities onchain via Endaoment. Use when the user wants to donate crypto to charity, make a charitable contribution, give to nonprofits, support a cause, or donate to a 501(c)(3). Supports Base, Ethereum, and Optimism. Handles USDC donations directly or swaps ETH/tokens to USDC automatically.

Set your primary ENS name on Base and other L2s. Use when user wants to set their ENS name, configure reverse resolution, set primary name, or make their address resolve to an ENS name. Supports Base, Arbitrum, Optimism, and Ethereum mainnet.

Privacy and shielded transactions on Base via Veil Cash (veil.cash). Deposit ETH into a private pool, withdraw/transfer privately using ZK proofs. Manage Veil keypairs, check private/queue balances, and submit deposits via Bankr. Use when the user wants anonymous or private transactions, shielded transfers, or ZK-based privacy on Base.

0) 上传封面图获取 thumb_media_id（必需） - 本地： - node ./scripts/wechat_mp_publish.mjs upload-thumb --file ./cover.jpg - URL： - node ./scripts/wechat_mp_publish.mjs upload-thumb --url "https://example.com/cover.jpg"

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Autonomous skill generation agent that picks up community ideas, uses evolved builder tools to produce Agent Skills, and publishes them back to the Skill Soup ecosystem.

Implement and review frontend interfaces for React + Vite + Tailwind projects using a controlled workflow (requirement analysis, state/API contract definition, component-based implementation, and lint/build verification). Use this when the user requests to create, modify, refactor, or review the UI, handle responsiveness, or optimize user experience and maintainability without breaking the existing workflow. Not for backend API logic, desktop PyQt UI, or deployment infrastructure changes.

(EN) Implement and review backend APIs for the Spreadsheet Compare FastAPI project using a clear workflow (router design, validation, error handling, integration with core modules, verification). Use when users request to create/edit/refactor/review API endpoints, handle upload/compare/sheets/analyze flows, or standardize the frontend-backend contract. Not for frontend UI implementation, desktop PyQt UI, or release deployment workflow. (VI) Triển khai và review backend API cho project FastAPI của Spreadsheet Compare theo quy trình rõ ràng (router design, validation, error handling, tích hợp với core modules, kiểm chứng). Dùng khi người dùng yêu cầu tạo mới/sửa/refactor/review endpoint API, xử lý luồng upload/compare/sheets/analyze, hoặc chuẩn hóa contract giữa frontend và backend. Không dùng cho frontend UI implementation, desktop PyQt UI, hoặc quy trình phát hành (release deployment).

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.

버그, 테스트 실패, 예상치 못한 동작 발생 시 수정 전 반드시 사용. 4단계 근본 원인 분석 프로세스.

SAP HANA Machine Learning Python Client (hana-ml) development skill. Use when: Building ML solutions with SAP HANA's in-database machine learning using Python hana-ml library for PAL/APL algorithms, DataFrame operations, AutoML, model persistence, and visualization. Keywords: hana-ml, SAP HANA, machine learning, PAL, APL, predictive analytics, HANA DataFrame, ConnectionContext, classification, regression, clustering, time series, ARIMA, gradient boosting, AutoML, SHAP, model storage

Generate a comprehensive file system index with directory tree, file sizes, and modification dates. Use when re-indexing files, updating file index, exploring directory structure, or when user says "re-index files".

HTML 슬라이드를 PowerPoint(PPTX) 파일로 변환. PPTX 생성, 편집, 썸네일 생성이 필요할 때 사용.

Create or update Databricks pipeline specs and generated bundle resources in this data-platform repository. Use when users ask to add, edit, or validate a pipeline under specs/pipelines, generate Python pipeline resources with just build-pipeline-resource, enforce naming {domain}_{source}_{layer}_{asset}, and keep catalog=domain plus schema=source mapping.

Cross-Layer Check

Integración con la API Digital Trust de GCloudFactory: autenticación OAuth2 client_credentials y operaciones core (case-files, evidencias, reportes, sign-file, webhooks) en entornos INT/PRE. Úsalo cuando necesites construir, probar o depurar llamadas a `/api/v1/private/*` de Legal App Factory.

Automate a real Google Chrome instance via the Chrome DevTools Protocol (CDP) and control it with `agent-browser --cdp PORT` for headed web workflows (login + navigation + screenshots + extraction) while keeping your normal Chrome profiles safe using `--user-data-dir` isolation. Use when agent-browser says “Browser not launched”, when you need a stable headed browser session, or when you want repeatable, low-frequency website automation without any risk-control bypass (captcha/fingerprinting evasion).

Install, configure, and use the CloudBrowser.ai MCP server (@cloudbrowser/mcp-server) over STDIO (Claude Desktop, Cursor, MCP Inspector, IDE MCP clients) or HTTP/JSON-RPC (n8n, Make, OpenAI Agents, custom clients). Use when generating MCP config JSON, setting CLOUDBROWSER_API_TOKEN, running the server with --transport stdio/http, calling tools/list or tools/call, or troubleshooting auth/token/JSON-RPC issues.

Operational reference for Codex inside an Exegol container (high-signal paths, inventories, and bundled services).

Provides Bitbucket Stash (Bitbucket Server) integration knowledge for PR reviews. Use when reviewing PRs from Stash, fetching PR metadata via REST API, handling already-merged PRs, or resolving deleted branch refs. Automatically loaded when the review-pr command runs.

This skill should be used when the user asks to "install howl", "set up the statusline", "configure howl", "enable the HUD", or "install the statusline binary". It downloads the Howl binary and configures Claude Code to use it.

新規ドキュメントを採番して作成し、テンプレ適用とリンク整備を行う

Send and manage WhatsApp messages via WAHA HTTP API. Use when the user wants to send WhatsApp messages (text, image, video, voice, file), read chats/messages, manage contacts, groups, or sessions. Triggers on: 'send a WhatsApp message', 'check my WhatsApp chats', 'send image on WhatsApp', 'WhatsApp group', 'WhatsApp session', or any WhatsApp-related task.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Text-to-speech and speech-to-text using fal.ai audio models. Use when the user requests "Convert text to speech", "Transcribe audio", "Generate voice", "Speech to text", "TTS", "STT", or similar audio tasks.

Runs CodeQL static analysis for security vulnerability detection using interprocedural data flow and taint tracking. Applicable when finding vulnerabilities, running a security scan, performing a security audit, running CodeQL, building a CodeQL database, selecting query rulesets, creating data extension models, or processing CodeQL SARIF output. NOT for writing custom QL queries or CI/CD pipeline setup.

Automated technical debt detection. Scans for file size violations, any usage, duplicated code, TODO/FIXME markers, lint suppressions, and unused dependencies.

Upscale and enhance image resolution using AI. Use when the user requests "Upscale image", "Enhance resolution", "Make image bigger", "Increase quality", or similar upscaling tasks.

Generate production-ready fal.ai workflow JSON files. Use when user requests "create workflow", "chain models", "multi-step generation", "image to video pipeline", or complex AI generation pipelines.

Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.

Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.

fal.ai Platform APIs for model management, pricing, usage tracking, and cost estimation. Use when user asks "show pricing", "check usage", "estimate cost", "setup fal", "add API key", or platform management tasks.

Interactive Archon integration for knowledge base and project management via REST API. On first use, asks for Archon host URL. Use when searching documentation, managing projects/tasks, or querying indexed knowledge. Provides RAG-powered semantic search, website crawling, document upload, hierarchical project/task management, and document versioning. Always try Archon first for external documentation and knowledge retrieval before using other sources.

Create, format, and publish WeChat Official Account (微信公众号) articles with consistent styling and cover images. Use when user wants to write, format, or publish a 公众号 article, generate a cover image for 公众号, or push content to WeChat draft box.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Fetch a Confluence page via local API script and generate a concrete implementation plan for the current repository. Use this when the user provides a Confluence link and asks how to implement the spec in the current repo.

Quickly test Scalekit authentication setup end-to-end before writing integration code using the dryrun tool. Use when you need to validate Scalekit configuration, test authentication flows, verify credentials, or troubleshoot auth setup. Works with Full Stack Auth (FSA) and Modular SSO modes.

Publish tweets and Twitter threads using Tweepy. Use when the user wants to post content to Twitter, including short tweets or long-form text that needs to be split into threaded replies. Handles automatic text splitting at natural boundaries (paragraphs, sentences) and thread creation. Trigger when user mentions "tweet", "post to Twitter", "publish to Twitter", "Twitter thread", or similar requests.

Edit Ono's reference image with Google Gemini (Imagen 4 Fast) and send selfies to messaging channels via OpenClaw

Enhanced web and package repository search using SearXNG instance

THOR Lite is a free scanner with reduced features compared to full THOR. This skill handles Lite-specific guidance, limitations, and workarounds.

| Hotkey | Function | Confirmation | |--------|----------|--------------| | `F8` | Extract current chat | No | | `Ctrl+F8` | Export contacts | No | | `Win+F8` | Backup all visible chats | No (read-only) | | `Ctrl+Shift+F8` | Search and extract | Prompt for keyword |

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use ACE-Step API to generate music, edit songs, and remix music. Supports text-to-music, lyrics generation, audio continuation, and audio repainting. Use this skill when users mention generating music, creating songs, music production, remix, or audio continuation.

Use for materials analysis tasks in pymatgen.analysis: phase/Pourbaix/chemical-potential diagrams, reactions, structure matching, surfaces/interfaces, local environments, diffraction, elasticity, magnetism, and related analyses.

OpenMX (openmx) workflows with emphasis on OpenMX v3.9: write and validate input .dat files (System.Name, Atoms.SpeciesAndCoordinates, scf.Kgrid, Band.kpath), run SCF/geometry optimization/band/DOS/NEB/ESM/SOC(+U)/unfolding/Wannier90/NEGF examples, and interpret outputs (.out/.scfout/restart). Trigger this skill whenever the user mentions OpenMX/openmx.

Criação, edição e revisão de scripts RouterOS (.rsc) com foco em idempotência, segurança e boas práticas. Use quando for necessário gerar, ajustar ou importar arquivos .rsc para MikroTik: (1) criar novas configurações via script, (2) editar scripts existentes com correções seguras, (3) revisar riscos e políticas de execução, (4) validar com import dry-run e captura de erros.

This skill validates a Longhorn developer workspace after initialization. It checks toolchain readiness (Go version, Docker daemon, Dapper/make availability), git remote configuration, and workspace hygiene before development begins.

Evaluate a project's compliance with an RFC or standard. Use when asked to assess, audit, or check implementation against RFC specifications, IETF standards, W3C specs, or similar technical standards. Applies Postel's Law—be conservative in what you send, be liberal in what you accept.

Use when Codex needs to run PaperBanana-style multi-agent academic illustration workflows from method context and figure caption, especially for reference retrieval, planning, style refinement, visualization, iterative critic loops, and scorecard evaluation across faithfulness, conciseness, readability, and aesthetics.

TypeScript SDK patterns for Opik. Use when working in sdks/opik-typescript.

Local development environment setup and commands. Use when helping with dev server, Docker, or local testing.

Playwright E2E test generation workflow. Use when generating automated tests in tests_end_to_end/.

Java backend patterns for Opik. Use when working in apps/opik-backend, designing APIs, database operations, or services.

Detect malicious patterns in AI Agent skills — 13 detectors for backdoors, credential theft, data exfiltration, and supply-chain attacks. Based on SlowMist's ClawHub threat intelligence (472+ malicious skills). Pure Python, zero dependencies.

OpenSink integration tools for OpenClaw agents. Includes session management and activity logging for audit trails and observability, with more integrations coming. Use when the agent needs to log actions, track progress, or interact with OpenSink's agent platform.

Coach ReScript beginners through implementing this repo's small, ordered tasks in tmp/issues (1 issue = 1 feature + 1 test). Use when the user wants hands-on ReScript learning via issue-driven development, needs help choosing the next tmp/issues file, wants ReScript syntax/FFI/test guidance while coding an issue, or wants incremental review/hints without the full solution dump.

This skill should be used when the user asks to "query open data", "find datasets", "search for data on OpenDataSoft", "get data about" a topic, "explore datasets", "export data", asks questions about public data (population, weather, transport, environment, etc.), or needs to combine data from multiple datasets. Provides workflow guidance for the OpenDataSoft MCP server tools.

Add a new script module to this repo (scripts/ID/) with a bash entrypoint, usage docs, and a per-script script.toml that registers smoke/integration tests for the TOML-driven test runner. Use when creating or modifying modules, extending the container/CI test environment, or debugging how tests are discovered and executed in one shared bash session per script.

Print files on Mac or Linux using the `lp` command with sensible defaults.

Telegram User API via Telethon. Create groups, send messages, manage members, and more — all through the user's own Telegram account (not a bot). Use when you need to create Telegram groups, look up existing groups, send messages as the user, add/remove members, or manage group settings. Requires Telethon session authentication.

Run bot acceptance tests to validate MCP tools work correctly from a real AI agent's perspective. Use when testing PRs, detecting regressions, or verifying tool changes end-to-end with Claude/Gemini CLIs.

Ralph loop creation and refinement. Transforms vague prompts into well-structured autonomous development loops with PROMPT.md, TODO.md, guardrails, and completion criteria. Use when user wants to set up overnight/autonomous coding runs.

Store and retrieve agent memories using OpenSink Sinks. Use when the agent needs to remember something persistently, recall past decisions/context/facts, search memories, or when the user says "remember this" and you want durable cloud-backed memory. Also use to list or browse stored memories.

Master Lightswind UI integration. Use when adding, configuring, and troubleshooting Lightswind components. Includes "perfect usage" guidelines for imports, theming (lightswind.css), and animations. The library is pre-installed in `frontend/src/components/lightswind`.

Send emails via Gmail with preview and confirmation. Use when the user wants to send an email, mentions Gmail, needs to email attachments, or wants to send invoice emails.

Universal patterns for Convex components including installation, configuration, and usage. Use when working with Rate Limiter, Aggregate, Workpool, Workflow, or any Convex component from the ecosystem.

Core authentication patterns for Convex backends. Use when implementing auth checks in functions, storing users in database, creating auth helpers, or debugging auth issues. Works with any auth provider (Clerk, WorkOS, Auth0, etc.).

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Guide for creating official TPMJS tools using the blocks CLI. Use when a user wants to create a new tool for the TPMJS registry, add a tool to packages/tools/official/, implement an AI SDK v6 tool, define a block in blocks.yml, validate a tool with `pnpm blocks run`, or publish a tool to npm with the tpmjs keyword.