AI Skills Hub - Browse 180,000+ Agent Skills

Grokipedia article workflow - fetch, verify, submit corrections using browser automation

Share a skill publicly to the Enterprise-Crew-skills GitHub repo. Strips personal/security info, generates a README, and updates the repo index.

DBOS TypeScript SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing TypeScript code with DBOS, creating workflows and steps, using queues, using DBOSClient from external applications, or building applications that need to be resilient to failures.

View markdown files with calm, book-like reading experience via HTTP server. Use for long-form content, documentation preview, novel reading, report viewing, distraction-free reading.

Test voxtype in Docker containers. Use for testing builds, verifying packages work on different distros, or isolating test environments.

Validate voxtype binaries for CPU instruction contamination. Use when checking release binaries for AVX-512 or GFNI instruction leaks that would crash on older CPUs.

Run regression tests for voxtype releases. Use before major releases to verify core functionality, CLI commands, and configuration handling.

Generate TypeScript types from Go source code with cross-package type resolution. Use when you need to sync Go struct definitions to TypeScript interfaces, convert Go const blocks to TypeScript union types, or maintain type safety between Go backends and TypeScript frontends.

Provides guidance for property-based testing across multiple languages and smart contracts. Use when writing tests, reviewing code with serialization/validation/parsing patterns, designing features, or when property-based testing would provide stronger coverage than example-based tests.

Scans Cosmos SDK blockchains for 9 consensus-critical vulnerabilities including non-determinism, incorrect signers, ABCI panics, and rounding errors. Use when auditing Cosmos chains or CosmWasm contracts. (project, gitignored)

Audit Solana programs for security vulnerabilities using Blueshift patterns. Use when reviewing smart contract security, finding exploits, implementing defensive patterns, or learning common Solana attack vectors. Covers both Anchor and Pinocchio/Native implementations.

Production-ready memory and persistence patterns for LangGraph agents. Covers checkpointers (InMemory, SQLite, PostgreSQL), cross-thread memory stores with semantic search, conversation history management, and memory cleanup strategies. Use when building agents that need conversation continuity, user-specific memories across sessions, or production-grade state persistence.

Monitor, debug, and trace LangGraph agents with LangSmith. Covers tracing setup, custom spans, cost tracking, and production debugging. Use when building agents that need observability, debugging complex workflows, or monitoring production deployments.

Test and evaluate LangGraph agents systematically. Covers dataset creation, custom evaluators, LLM-as-judge patterns with Gemini, and automated benchmarking. Use when building evaluation pipelines, comparing model versions, or measuring agent quality.

This skill should be used when the user asks to "create a feature branch", "start a new feature", "sync my branch", "sync with main", "update from main", "create a PR", "create a pull request", "ship a feature", "merge and clean up", "handle merge conflicts", "resolve conflicts in git-town", "create stacked branches", "work on dependent features", "configure git-town", "set up git-town", "use git-town offline", "manage git workflow", or mentions git-town commands (hack, sync, propose, ship, continue, undo, kill).

Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.

建立符合本地架構的新 skill。Use when creating new skills, "建立 skill", "create skill", "新增 skill", "寫一個 skill". Follows local conventions with Integrations, Verification, and Handoff sections.

發佈週報到 Substack。Use when publishing weekly digest to Substack, running publish script. Triggers on "publish-substack", "發佈到 Substack", "publish to substack", "發佈週報".

Create website sitemap with page structure and section selection. Use at project start to define pages, routes, and shadcnblocks sections for each page. Outputs docs/sitemap.md. Triggers on "sitemap", "page structure", "website structure", "create pages".

Add Framer Motion micro-animations to page sections. Includes section reveals, staggered lists, hover effects, and performance optimization. Use after section-backgrounds for each page.

Define brand styling for website projects. Updates globals.css with CSS color variables (oklch format), typography (h1-h6, p, a, blockquote), and container styles. Use at the start of a project after sitemap is created. Requires primary, secondary, and accent colors plus font choice.

根据主题自动生成Remotion动画脚本、TTS语音，并同步时长。当用户要求生成动画脚本、创建视频脚本、或生成关于某主题的动画时触发。

Generate Playwright scripts that record short demo videos (WebM) of any web app's core user flows.

Skill for creating dashboards and calculated fields in Google Looker Studio (formerly Data Studio). Use when the user: - Needs help with formulas or calculated fields in Looker Studio - Wants to connect Looker Studio to PostgreSQL/Supabase - Needs to create visualizations or dashboards - Asks about function syntax (CASE, IF, DATETIME, etc.) - Wants to convert timezones or format dates - Needs to blend data from multiple sources

Designs and outputs n8n workflow JSON with robust triggers, idempotency, error handling, logging, retries, and human-in-the-loop review queues. Use when you need an auditable automation that won’t silently fail.

PR 코드 리뷰 코멘트를 체계적으로 해결하는 skill. 사용자가 (1) PR 리뷰 코멘트 해결을 요청하거나, (2) 코드 리뷰 피드백을 반영하려고 하거나, (3) "리뷰 코멘트", "PR 코멘트", "코드 리뷰" 관련 수정을 언급할 때 사용. 1 코멘트 → 1 작업 → 1 테스트 → 1 커밋의 원칙으로 진행하며 진행 상황을 YAML로 추적.

Create and configure Claude Code hooks for customizing agent behavior. Use when the user wants to (1) create a new hook, (2) configure automatic formatting, logging, or notifications, (3) add file protection or custom permissions, (4) set up pre/post tool execution actions, or (5) asks about hook events like PreToolUse, PostToolUse, Notification, etc.

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. Now with automatic session recovery after /clear.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Create complex illustrations using only one HTML `<div>` element and pure CSS. Based on Lynn Fisher's "A Single Div" technique.

Market Oracle for prediction market intelligence - Polymarket and Kalshi research, probability assessments, market sentiment analysis, and arbitrage opportunity identification. Use when users want to research prediction markets, analyze betting odds, or find market inefficiencies. Costs $0.03 USDC per request via x402 protocol on Base network.

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).

Expert on Plaid accounts and account management. Covers account data retrieval, balance checking, account types, multi-account handling, and account webhooks. Invoke when user mentions Plaid accounts, account balance, account types, or account management.

Expert on Plaid Auth product for bank account authentication and verification. Covers account and routing number retrieval, account ownership verification, balance checks, and integration patterns. Invoke when user mentions Plaid Auth, ACH verification, bank account verification, or routing numbers.

Expert on EAS Build cloud service for building iOS and Android apps. Covers build configuration, credentials management, custom builds, CI/CD integration, and troubleshooting. Invoke when user mentions EAS Build, cloud builds, app compilation, build workflows, or iOS/Android binary creation.

Debug and test backend API endpoints using the request CLI tool. Use when the user wants to test an API endpoint, debug a backend handler, check API responses, or investigate server-side issues.

Dump all Hyvä CMS components from active modules. This skill should be used when the user wants to list all CMS components, view available components, debug component configurations, or see the merged components.json output. Trigger phrases include "list cms components", "dump components", "show all components", "view cms components", "components.json dump".

Utility skill to detect Magento development environment and determine command wrapper. This skill should be used by other skills that need to execute shell commands in the Magento environment. It detects Warden, docker-magento, DDEV, and local environments and provides the appropriate command wrapper.

Generate responsive image code for Hyvä Theme templates using the Media view model. This skill should be used when the user wants to render images in a Hyvä template, create responsive picture elements, add hero images, product images, or any image that needs responsive breakpoints. Trigger phrases include "render image", "add image to template", "responsive image", "picture element", "hero image", "responsive banner", "image for mobile and desktop", or "banner image".

Manage Apple Notes via deterministic local scripts (create, append, list, search, export, and edit). Use when a user asks OpenClaw to add a note, list notes, search notes, or manage note folders.

创建高质量 MCP（Model Context Protocol）服务器的指南，使 LLM 能够通过精心设计的工具与外部服务交互。在构建 MCP 服务器以集成外部 API 或服务时使用，无论是 Python (FastMCP) 还是 Node/TypeScript (MCP SDK)。

GitHub Actions の使用量を確認し、月次レポートを表示する。

World of Darkness 20th Anniversary toolkit for Vampire (V20), Werewolf (W20), Mage (M20), Wraith (Wr20), Changeling (C20), Demon (D20). Creates characters, locations, items, organizations, weapons. Triggers: WoD, Vampire, Kindred, clan, ghoul, Garou, tribe, Gift, caern, Tradition, Technocracy, Sphere, rote, Arcanoi, Kithain, Art, spirit, Umbra, crossover, weapon stats, firearm, melee, ranged, Demon, Fallen, House, Lore, evocation, Earthbound, thrall, pact, apocalyptic form, Faith, Torment, relic, ritual, Ankida, form customization.

Tests, validates, explains, benchmarks, and applies regular expression replacements using the re-x CLI tool. Use when generating regex patterns, debugging regex matches, checking cross-language portability, detecting ReDoS vulnerabilities, or applying regex-based find-and-replace to files.

Create a new Claude Code skill. Use when the user wants to create a skill, make a skill, add a custom skill, or set up skill files.

Advanced web search + scraping with no API key. Search via DuckDuckGo (instant answers), Bing (scraping), or all sources. Scrape pages for text, links, images, tables. Full HTML parsing with BeautifulSoup. Use for research, content extraction, web automation, and data gathering without Brave API or rate limits.

Deploys a VirtualMCPServer configuration locally for manual testing and verification

Control Arduino/ESP32 hardware — GPIO, servos, sensors, cameras

Debug and troubleshoot Home Assistant integration issues. Use when the user mentions "error", "debug", "not working", "unavailable", "traceback", "exception", "logs", "failing", or needs help diagnosing problems with a Home Assistant integration. Also triggers on "ConfigEntryNotReady", "UpdateFailed", "entity not found", or stack traces from Home Assistant.

Create personalized training plans for 5K, 10K, Half Marathon, and Marathon races. Use when the user requests a training plan for any of these distances, wants to prepare for a race, or asks for a structured running program. This skill generates comprehensive markdown training plans that include race goals, training paces, phased progression, and week-by-week workout schedules.

Render beautiful Mermaid diagrams as SVG or ASCII art using the beautiful-mermaid library. Supports 15+ themes, 5 diagram types (flowchart, sequence, state, class, ER), and ultra-fast rendering. Use this skill when: 1. User asks to "render a mermaid diagram" or provides .mmd files 2. User requests "create a flowchart/sequence diagram/state diagram" 3. User wants to "apply a theme" or "beautify a diagram" 4. User needs to "batch process multiple diagrams" 5. User mentions "ASCII diagram" or "terminal-friendly diagram" 6. User wants to visualize architecture, workflows, or data models

IMPORTANT: This skill defines how documentation is structured and written in this project. Always use this skill when the user references any docs folder/path or asks anything about documentation. Trigger on ANY of these: - User references a docs path (@docs/, docs/data/, etc.) with any question - Questions about docs: "what is this", "tell me about", "explain", "summarize", "entails", "contains", "overview" - Exploring/analyzing doc structure or content - Creating, modifying, or organizing documentation files - Questions about frontmatter, markdown conventions, folder structure, settings.json - How to write documentation for this project When in doubt about a docs-related question, USE THIS SKILL.

Generate Excalidraw JSON format diagrams for documentation, architecture diagrams, flowcharts, entity relationships, and visual explanations. Use when users request Excalidraw diagrams, .excalidraw files, visual diagrams for docs, architecture visualizations, flowcharts, or when converting ASCII art/placeholder diagrams to proper Excalidraw format.

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

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

Audit-ready iteration workflow for KV-cache eviction experiments: validate run artifacts (summary.json/logs.jsonl), classify result_type/claim_scope, enforce causal-claim gates, and automatically write/update labbook logs (MASTER_LOG.md, daily/YYYY-MM-DD.md, INDEX.md) with fixed schemas. Use when running or tuning KV eviction/compression experiments and needing reproducible, reviewer-grade logging + next-step patch plan.

Minimal Chrome DevTools Protocol tools for browser automation and scraping. Use when you need to start Chrome, navigate pages, execute JavaScript, take screenshots, or interactively pick DOM elements. Triggers include "browse website", "scrape page", "take screenshot", "automate browser", "extract DOM", "web scraping".

Import file nội bộ (video, image, audio) vào project, tự động đổi tên và cập nhật resources.json.

Tạo ảnh minh họa, creative content bằng Google Gemini API. Hỗ trợ tạo chuỗi ảnh (sequence) cho story.

Requires proof before marking work complete — no "trust me, it works"

Extract formatting from existing Word documents and generate new documents with the same format but different content. Use this skill when users need to create multiple documents with consistent formatting, replicate document templates, or maintain corporate document standards across different content.

提案書・調査結果から最終報告書の骨子（章立て・スライド構成・想定アウトプット）を設計するスキル。「報告書骨子を作成して」「章立てを設計して」「レポートの構成を作って」などのリクエスト時に使用。論点構造を報告書の章にマッピングし、プロジェクト種類（技術動向・市場調査・インタビュー中心・DD等）に応じた構成を設計する。

Validates implemented work against spec requirements with empirical evidence

エイトハンドレッド（800）社のブランドデザインに沿ったPowerPointプレゼンテーションを作成するスキル。「800風のスライドを作成」「エイトハンドレッドのデザインでプレゼンを作って」「800社のテンプレートでPPTX作成」などのリクエスト時に使用。ダークグリーン(#1B3928)をメインカラーとし、Meiryo UIフォント、クリーンでミニマルなレイアウトを特徴とする。

How to use the logging system and debug the 10K Scorekeeper app.

Use when working with leagues, league rules, members, invites, or role permissions

Hot reload development on iPad/iPhone from Windows using Expo Go.

Step-by-step guide to creating USDC deposits on USDCtoFiat, with live platform and market data

クライアントの与件情報と打ち合わせメモから、意思決定に直結する調査プロジェクト提案書（スライド骨子/Markdown）を一発で作成するスキル。「提案書を作成して」「提案書を作って」「プロポーザルを作成して」などの依頼、または与件ファイル（例：与件.md）を指定して提案書作成を依頼された場合に使用する。単なる章立てではなく、調査の観点・仮説・参入障壁や供給構造・会議転用可能なアウトプットまで落として提案する。インプットや指示からデプスインタビューが必要と推測できる場合のみ、インタビュー前提の設計を含める。

Three-layer evaluation for agentic systems — component testing, trajectory evaluation, and outcome evaluation with LLM-as-Judge. Includes golden trajectories, the Four C's, and the evaluation flywheel. Use when building test suites for agents.

Comprehensive guide to the file-based routing system used in this project. Use this skill when you need to create new pages, understand URL mapping, or handle navigation logic using unplugin-vue-router.

Multi-language code standards for OpenCode system code (JavaScript, Python, Shell, JSON/JSONC) with language detection routing, universal patterns, and quality checklists.

Automate creation of Azure DevOps workload identity federation service connections. Use this when users need to create or delete Azure service connections with workload identity federation for secure OIDC-based authentication between Azure DevOps pipelines and Azure resources.

Use fstar.exe to verify F* code and interpret the errors reported

Use fstar.exe to verify Pulse code and interpret the errors reported

按照 iOS 项目的 SnapKit 约束编码规范进行开发。

This skill should be used when verifying code and document quality before commits or pull requests. It runs linters for Markdown, JSON, and Python files in the project.

阶跃星辰语音合成 Skill，用于将文本转换为自然语音。

Create, update, and manage WhatsApp message templates. Use for tasks like "Create a new coupon template" or "Check why my template was rejected".

Cloudflare CLI - manage DNS records, purge cache, and control Workers routes.

OpenClaw skill for designing Telegram Bot API workflows and command-driven conversations using direct HTTPS requests (no SDKs).

Reorganize a messy local branch into focused, atomic commits before sharing. Use when user says "decompose branch", "clean up commits", "reorganize my branch", or wants to restructure local work.

Comprehensive Apache Kafka skill for building event-driven architectures from hello world to professionstal production systems. Provides guidance on Kafka setup, topic management, producer/consumer implementation, stream processing, security, monitoring, and best practices for scalable event streaming platforms.

Write or modify bashio-based shell scripts for the Home Assistant add-on. Use when editing run.sh, adding new features to the entrypoint script, or debugging the add-on's runtime behavior.

Set up Vast.ai CLI — configure API key, verify installation, set up SSH keys, and check account. Use when the user needs to get started with Vast.ai or is having authentication issues.

Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, or manage issue workflows. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", or any GitHub issue management task.

Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities with bundled resources. Generates SKILL.md files with proper frontmatter, directory structure, and optional scripts/references/assets folders.

Use when building financial, trading, or payment systems in Rust. Covers money handling, financial calculations, rounding, decimal precision with rust_decimal and BigDecimal, currency newtypes, ledger, journal entry, reconciliation, idempotency, ACID transactions, regulatory compliance, immutable transaction records, audit trails, checked arithmetic, and double-entry patterns.

Use when working with multibyte strings, UTF-8 encoding, character encoding conversion, locale-aware formatting (dates, numbers, currencies), transliteration, pluralization, or internationalization. Covers mb_strlen, mb_substr, mb_strtolower, mb_strtoupper, mb_detect_encoding, mb_convert_encoding, iconv, grapheme functions, emoji handling, unicode processing, locale-aware sorting, ICU library, intl extension (Collator, NumberFormatter, IntlDateFormatter, MessageFormatter, Transliterator, Normalizer), currency formatting, date formatting, transliteration, string normalization (NFC, NFD, NFKC, NFKD), and the UTF-8 input-to-output pipeline.

Create atomic, well-formatted git commits following conventional commit standards with emoji indicators.

This skill should be used when the user asks to "brainstorm", "discuss an idea", "explore options", "think through a problem", "/brainstorm", or mentions wanting to talk through a development idea, issue, or new functionality before planning. Facilitates highly interactive dialogue to reach a simple, YAGNI-compliant solution written to .agents/brainstorms/.

Use the 'erigon seg step-rebase' command to change the step size of an existing datadir. Use when the user wants to rebase segments or modify step sizes.

Run the Erigon segment retire command to build, merge, and clean snapshot files. Use this for snapshot publication readiness preparation.

Comprehensive reference for LLM agents to navigate and work with Odoo documentation. Use when working with Odoo-related documentation tasks like finding installation guides, locating application documentation, searching developer tutorials/reference materials, understanding documentation structure, and assisting with queries about Odoo features, development, and maintenance. This skill provides organized domain-based references and search strategies for efficiently locating information across the entire Odoo documentation tree.

Claude 블로그(claude.com/blog) 콘텐츠를 스크래핑하여 영어-한국어 병렬 읽기 서비스용 콘텐츠로 변환. 사용 시점: (1) claude.com/blog URL이 제공될 때, (2) Claude 블로그 글을 콘텐츠로 만들어달라는 요청 시, (3) "이 글 스크래핑해줘" 같은 요청에 claude.com/blog URL이 포함될 때. Playwright로 전체 본문, 이미지를 추출하고 meta.yaml, en.md, ko.md 형식으로 생성.

Google 블로그(blog.google) 콘텐츠를 스크래핑하여 영어-한국어 병렬 읽기 서비스용 콘텐츠로 변환. 사용 시점: (1) blog.google URL이 제공될 때, (2) Google 블로그 글을 콘텐츠로 만들어달라는 요청 시, (3) "이 글 스크래핑해줘" 같은 요청에 blog.google URL이 포함될 때. Playwright로 전체 본문, 이미지, YouTube 비디오를 추출하고 meta.yaml, en.md, ko.md 형식으로 생성.

Claude Code 문서(code.claude.com/docs) 콘텐츠를 스크래핑하여 영어-한국어 병렬 읽기 서비스용 콘텐츠로 변환. 사용 시점: (1) code.claude.com/docs URL이 제공될 때, (2) Claude Code 문서를 콘텐츠로 만들어달라는 요청 시, (3) "이 문서 스크래핑해줘" 같은 요청에 code.claude.com/docs URL이 포함될 때. Playwright로 전체 본문, 코드 블록을 추출하고 meta.yaml, en.md, ko.md 형식으로 생성.

Troubleshoot Datadog API authentication issues (401/403 errors), understand API keys vs app keys, and configure correct regions. Use when hitting auth errors or setting up Datadog API access.

Renames messy files into consistent, searchable patterns with previews, conflict checks, and reversible logs.

This skill should be used when questions or tasks involve Bittensor, including explaining Bittensor concepts (subnets, metagraph, Yuma Consensus, TAO token), using btcli commands, developing miners or validators, creating subnets, understanding the whitepaper, working with the Bittensor SDK, or troubleshooting Bittensor-related issues. Use this skill for both conceptual questions and practical development tasks on the Bittensor network.