AI Skills Hub - Browse 180,000+ Agent Skills

Automatically process invoices (发票) from PDFs/images to Excel spreadsheets using AI vision recognition. Use this skill when users mention "发票", "invoice", "处理发票", "识别发票", "提取发票", or need to convert invoice files to Excel format.

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.

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.

Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation. Use when user asks to "post to X", "tweet", "publish to Twitter", or "share on X".

Generates images using official OpenAI and Google APIs via AI SDK. Supports text-to-image, reference images, aspect ratios, and quality presets. Use when user asks to "generate image with API", "use official API for images", "create image with OpenAI/Google", or needs API-based generation instead of browser-based.

Fetch any URL and convert to markdown using Chrome CDP. Supports two modes - auto-capture on page load, or wait for user signal (for pages requiring login). Use when user wants to save a webpage as markdown.

Browser automation for visual verification. **Self-check UI before delivering.**

Decorative JSON animations for UI feedback and polish. Use for loading spinners, success/error checkmarks, empty state illustrations, animated icons. Just plays and loops - no interactivity. For reactive/stateful animations use Rive instead. Lightweight and SSR-compatible.

State-driven interactive animations with built-in state machines. Use when animations must REACT to user input (hover, click, drag), have multiple states/transitions, or respond to data values (progress bars, counters). Ideal for animated buttons, toggles, checkboxes, characters. For simple play/loop animations use Lottie instead.

Use when creating CLAUDE.md files, updating existing CLAUDE.md, validating CLAUDE.md structure, or auto-fixing CLAUDE.md issues. Load for setting up project instructions, global guidelines, local overrides, or modular rules. Handles global (~/.claude/CLAUDE.md), project (.claude/CLAUDE.md), local (CLAUDE.local.md), and rules (.claude/rules/*.md) with smart project detection and template generation.

Create, update, or run Ansible playbooks and inventory in this repo for multi-node changes (ansible/). Use for node bootstrap, package installs, or cluster-wide config updates.

Operate Temporal workflows in this repo: start/list/inspect workflows, fetch history, debug nondeterminism, reset/cancel/terminate, and check task queues via Temporal CLI.

Deploy Python agents to AWS Bedrock AgentCore. Use when deploying agents to AWS, setting up serverless agent hosting, configuring AgentCore components (Runtime, Gateway, Memory, Identity, Policy), or troubleshooting deployment errors.

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.

Comprehensive developer workflow guide for PikaCSS monorepo maintenance, including package architecture, implementation patterns, testing strategies, and release procedures.

中文写作助手，支持启发式写作引导和文章审校。使用场景：(1) 启发模式 - 用户说「帮我写日记」「不知道写什么」「帮我构思」「写点什么」「记录一下」「今天想写」时触发；(2) 审校模式 - 用户说「帮我改文章」「检查一下」「润色」「帮我改改」「校对一下」「看看文章」时触发。支持文章类型：日记、周记、月记、游记、TIL 技术记录、通用文章。

Use when working with Alibaba Cloud DevOps (Yunxiao/云效), including Codeup code review (MR/PR), release tags, or Projex tasks.

个人 Git 工作流，遵循 conventional commits 和语义化版本。用于创建提交、PR 和发布版本。当用户说「帮我提交」「commit」「提交代码」「创建 PR」「发布版本」「打 tag」「写 commit message」「推代码」时触发。

Use when reviewing WordPress PHP code for performance issues, auditing themes/plugins for scalability, optimizing WP_Query, analyzing caching strategies, or detecting anti-patterns in database queries, hooks, object caching, AJAX, and template loading.

Use when developing WordPress (Gutenberg) blocks: block.json metadata, register_block_type, attributes/serialization, supports, dynamic rendering (render.php), deprecations/migrations, InnerBlocks, viewScript/viewScriptModule, and @wordpress/scripts build workflows.

Creating and optimizing Claude Code Skills including activation patterns, content structure, and development workflows. Use when creating new skills, converting memory files to skills, debugging skill activation, or understanding skill architecture and best practices.

Interacting with Linear issues, projects, and teams. Use when creating issues, updating issues, querying issues, managing projects, working on tasks, discussing backlogs, or any interaction with Linear.

Comprehensive guide for implementing Supabase Realtime features with best practices, scalable patterns, and migration strategies. Use when building realtime features in Supabase applications including messaging, notifications, presence, live updates, collaborative features, or migrating from postgres_changes to broadcast. Covers client setup, database triggers with realtime.broadcast_changes, RLS authorization, naming conventions, and performance optimization.

Model Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.

Expert guidance for writing proper Svelte 5 code with runes-based reactivity. Use when writing Svelte 5 components, migrating from Svelte 4, or troubleshooting Svelte 5 syntax. Covers $state, $derived, $effect, $props, $bindable, event handling, snippets, TypeScript integration, and common pitfalls.

This skill should be used when users need to lint, format, or validate Python code using the Ruff command-line tool. Use this skill for tasks involving Python code quality checks, automatic code formatting, enforcing style rules (PEP 8), identifying bugs and security issues, or modernizing Python code. This skill should be invoked PROACTIVELY whenever Python code is written or modified to ensure code quality.

This skill should be used when users need to create, configure, or render Quarto documents (.qmd files). Use this skill for generating reports, analysis documents, or presentations with HTML or Typst output formats, integrating code chunks (Python, R, Stata), and troubleshooting rendering issues.

This skill should be used when users need to format, clean, lint, or validate Markdown files using the markdownlint-cli2 command-line tool. Use this skill for tasks involving Markdown (including Quarto Markdown `.qmd`) file quality checks, automatic formatting fixes, enforcing Markdown style rules, or identifying Markdown syntax issues.

Orchestration hub for Microsoft Graph API across Microsoft 365 services. Use for Graph API integrations, querying Microsoft 365 data, and building applications that interact with Azure AD.

Interacts with the FreeAgent accounting API to manage invoices, contacts, projects, expenses, timeslips, and other financial data. Use when the user needs to retrieve, create, update, or analyze FreeAgent accounting information via the API.

Generates comprehensive synthetic fine-tuning datasets in ChatML format (JSONL) for use with Unsloth, Axolotl, and similar training frameworks. Gathers requirements, creates datasets with diverse examples, validates quality, and provides framework integration guidance.

Integrate Plaid API for bank account connections and transaction syncing. Use when implementing financial data access, bank linking, or transaction imports in TypeScript/Bun applications.

Use when creating a new skill, updating an existing skill, or learning skill best practices. Load for extending Claude's capabilities with specialized workflows, tool integrations, or domain expertise. Covers skill anatomy, progressive disclosure (98% token savings), and the critical description-as-trigger pattern.

浏览器自动化与网页交互工具包。支持使用 Playwright 进行网页自动化、数据采集、UI 交互（如点击、填表、抢购/抢福袋）、自动测试及截图。适用于需要模拟用户行为操作任何本地或远程网页的场景。

Guide for adding new agents to the ADK pipeline. Use when creating a new LlmAgent, SequentialAgent, or ParallelAgent, or when extending the pipeline with additional processing stages.

Guide for creating custom ADK tools. Use when adding new function tools, working with ToolContext, saving artifacts, or integrating external APIs into the agent pipeline.

Build StateGraph workflows with SpoonOS. Use when creating multi-step workflows, conditional routing, parallel execution, checkpointing, or multi-agent orchestration.

TypeScript library for NEAR Protocol blockchain interaction. Use this skill when writing code that interacts with NEAR Protocol, including viewing contract data, calling contract methods, sending NEAR tokens, building transactions, creating type-safe contract wrappers, integrating wallets (Wallet Selector, HOT Connect), managing keys, testing with sandbox, meta-transactions (NEP-366), and message signing (NEP-413).

Systematic debugging toolkit for AI agentic workflows in customer support. Use when diagnosing issues with AI agents including wrong responses, tool/function calling problems, conversation loops, stuck states, or performance/latency issues. Works with any framework (LangChain, custom agents, Claude API) and accepts conversation logs, API logs, tool execution logs, and agent configurations.

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.

Moltbook social network integration for SHRIMP Oracle

const encoding = detectEncoding(path); if (encoding !== 'UTF-8') { return { valid: false, error: `E002: Invalid encoding (${encoding})` }; }

update nexus, sync nexus, check for updates, upgrade nexus.

Create and manage Google Slides presentations. Load when user mentions 'google slides', 'slides', 'presentation', 'create presentation', 'add slide', or references creating/editing slide decks.

Read, create, and manage Google Calendar events. Load when user mentions 'google calendar', 'calendar', 'schedule', 'meeting', 'event', 'appointment', 'book time', 'check availability', 'find slots', 'free time', or references scheduling/calendar operations.

Read, send, and manage Gmail emails. Load when user mentions 'gmail', 'email', 'send email', 'check email', 'inbox', 'draft', or references sending/reading emails.

Manage Google Drive files and folders. Load when user mentions 'google drive', 'drive', 'upload file', 'download file', 'share file', 'create folder', or references cloud file storage operations.

send slack message, search slack, list channels, upload to slack.

Shared resource library for Slack integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, authentication) and scripts used by slack-connect and individual Slack skills.

slack, connect slack, slack message, send to slack.

langfuse help, langfuse reference, langfuse --help, show langfuse operations, list langfuse skills.

SHARED RESOURCES - DO NOT LOAD DIRECTLY. Contains Langfuse API client, config checker, and reference documentation. Used by langfuse-connect and all operation skills.

Log a call engagement in HubSpot CRM. Load when user says 'log call', 'record call', 'add call', 'call made'. Requires title, optional body and duration.

Search deals in HubSpot CRM by name or amount. Load when user says 'search deals', 'find deal', 'lookup deal', 'deals over $X', 'search for [deal]'.

Get associated records in HubSpot CRM. Load when user says 'get associations', 'linked records', 'contacts on deal', 'company contacts', 'related records', 'who is on this deal'.

Update an existing deal in HubSpot CRM. Load when user says 'update deal', 'edit deal', 'change deal stage', 'move deal', 'close deal'. Requires deal ID.

List deals from HubSpot CRM. Load when user says 'list deals', 'show deals', 'show pipeline', 'get deals', 'hubspot deals'. Returns paginated deal list.

Update an existing contact in HubSpot CRM. Load when user says 'update contact', 'edit contact', 'modify contact', 'change contact'. Requires contact ID.

Search contacts in HubSpot CRM by email, name, or company. Load when user says 'search contacts', 'find contact', 'lookup contact', 'search for [name]'.

Shared resource library for HubSpot integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, authentication) and scripts used by hubspot-connect and individual HubSpot skills.

List call engagements from HubSpot CRM. Load when user says 'list calls', 'show calls', 'call history', 'hubspot calls'. Returns logged call records.

Phase ACT (build) - Implémente task-by-task

Cut a new release (build, sign, notarize, publish to GitHub)

This skill sets up a complete two-agent development system based on the "Effective Harnesses for Long-Running Agents" research. It creates initializer-agent (for project planning) and coding-agent (for incremental implementation), along with enforcement hooks and progress tracking infrastructure. Use when users ask to "set up two-agent system", "install agent harness", "configure Opus delegation", or want to implement the two-agent architecture pattern.

Required when creating SKILL.md files for Claude Code agents. Specializes prompt-engineering TDD with agent-specific requirements: frontmatter format, persuasion principles, 500-line limit, progressive disclosure, quality gates. Triggers: 'create a skill', 'write a skill', 'new SKILL.md', 'create agent documentation'.

Create OpenCode plugins using the @opencode-ai/plugin SDK. Use for building custom tools, event hooks, auth providers, or tool execution interception. Use proactively when developing new plugins in .opencode/plugin/ or ~/.config/opencode/plugin/. Examples: - user: "Create a plugin to block dangerous commands" → implement tool execution before hook with blocking logic - user: "Add a custom tool for jira" → design tool schema and implementation using SDK context - user: "Show toast on file edit" → react to file edit events and display status message - user: "Build a custom auth provider" → implement auth flow for new model provider - user: "Intercept git commits" → add hook to validate commit messages before execution

Request code review for uncommitted changes. Use when asking for review of AI-generated code, reviewing git diff, or when user says "review my changes", "let me review", or "I want to check the changes".

Search real-world code examples across millions of GitHub repositories using grep.app. This skill should be used when looking for implementation patterns, API usage examples, library integration patterns, or production code references. Supports literal code search, regex patterns, and filtering by language/repo/path.

Global Knowledge Graph for codebase analysis. This skill should be used when searching for code definitions (functions, classes, methods), finding references to symbols, understanding code structure, analyzing import usage, generating repository maps, or performing impact analysis before refactoring. Supports TypeScript, JavaScript, Python, Java, and more.

Dynamic problem-solving through structured sequential thoughts. Use when breaking down complex problems, planning multi-step solutions, analyzing ambiguous requirements, debugging intricate issues, exploring design alternatives, or tackling problems where the full scope is unclear. Enables thought revision, branching, and iterative refinement.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Searches across your Notion workspace, synthesizes findings from multiple pages, and creates comprehensive research documentation saved as new Notion pages. Turns scattered information into structured reports with proper citations and actionable insights.

Playwrightを使用してローカルWebアプリケーションとのインタラクションおよびテストを行うためのツールキット。フロントエンド機能の検証、UIの動作デバッグ、ブラウザスクリーンショットのキャプチャ、ブラウザログの表示をサポート。

Control headless Chrome via Cloudflare Browser Rendering CDP WebSocket. Use for screenshots, page navigation, scraping, and video capture when browser automation is needed in a Cloudflare Workers environment. Requires CDP_SECRET env var and cdpUrl configured in browser.profiles.

Use when the user asks for "fresh eyes", an independent review, or a second opinion on code, commits, plans, or files.

Run TypeScript compiler type-checking (tsc --noEmit) to validate type safety and catch type errors. Works with any TypeScript project. Returns structured output with error counts, categories (type/syntax/import errors), and affected files. Used for quality gates and pre-commit validation.

Check if pull request already exists for current branch to support workflow resumption and prevent duplicate PR creation

Unity C# fundamental patterns including TryGetComponent, SerializeField, RequireComponent, and safe coding practices. Essential patterns for robust Unity development. Use PROACTIVELY for any Unity C# code to ensure best practices.

Integrate with Asana for task management. Use when user references Asana task IDs, asks to read/update/create Asana tasks, sync task status, fetch task details, search tasks, list projects, manage subtasks, or create tasks with standardized templates. Supports full CRUD operations on tasks and projects.

Guide for assistant-ui library - AI chat UI components. Use when asking about architecture, debugging, or understanding the codebase.

Structured ADR creation in MADR format. Triggers: ADR, Architecture Decision, 決定記録, 技術選定, アーキテクチャ決定, design decision, 技術的決定, 設計判断, deprecation, 非推奨化, process change, プロセス変更

Use Storybook to document UI states and design decisions as portable artifacts (stories + MDX docs) that engineers and QA can review. Use when: (1) exploring a component library interactively, (2) capturing canonical UI states for design guidance, (3) providing evidence and references in Beads task comments. This skill is tool-focused and does not assume Storybook is installed in the repo.

Create new slash commands for DevAgent workflows. Use when you need to create a new command file in .agents/commands/ and symlink it to .cursor/commands/ for Cursor IDE integration. This skill handles the complete command creation workflow including file generation, symlink creation, and structure validation.

Manage Gmail - send, read, search emails, manage labels and drafts. Use when user wants to interact with their Gmail account for email operations.

Create complete Claude Skills from a short brief, with templates and checks.

Upload images to ImageKit from file paths or clipboard, returning the CDN URL for easy sharing and embedding

Systematic hardware debugging guide for Arduino/ESP32/RP2040 circuits. Use when user reports: circuit not working, components getting hot, no power, intermittent failures, unexpected behavior, sensor not responding, LED not lighting, motor not spinning. Guides through power checks, continuity testing, signal tracing, and component isolation using multimeter techniques.

Extracts key specifications from component datasheet PDFs for maker projects. Use when user shares a datasheet PDF URL, asks about component specs, needs pin assignments, I2C addresses, timing requirements, or register maps. Downloads and parses PDF to extract essentials. Complements datasheet-parser for quick lookups.

Converts static web or Next.js projects into ArcBlock blocklets using provided DID. Analyzes project structure, generates configuration files, and validates setup. Requires blocklet DID as parameter.

3. Document type needs special handling ("photo", "duplex") → Override only specific params needed ```

WebSocket real-time updates, SSE broadcasting, event buffering

LLMのパフォーマンス、信頼性、制御性を本番環境で最大化するための高度なプロンプトエンジニアリング技術をマスターします。プロンプトの最適化、LLM出力の改善、または本番環境プロンプトテンプレートの設計時に使用します。

Implements Clix event tracking (Clix.trackEvent) with consistent naming, safe

Audits deep link contracts and routing behavior. Use when validating

Implements Clix user identification and user properties (setUserId,

Helps developers configure API-triggered campaigns in the Clix console and

運用ランブックの作成・保守スキル。本番システムの障害対応、トラブルシューティング手順、 リカバリーワークフロー、運用知識の共有を標準化し、信頼性の高いシステム運用を実現する。

自動化スクリプト（Bash/Python/Node）の設計・実装・運用を支援するスキル。 冪等性、エラーハンドリング、ログ設計、CI/CD統合の指針を整理します。

NextAuth.js v5の設定とカスタマイズパターンを専門とするスキル。 OAuth 2.0プロバイダー統合、データベースアダプター、セッション戦略、コールバック実装、型安全なセッション管理を提供する。

環境分離とアクセス制御スキル。開発・ステージング・本番環境の厳格な分離、 環境間Secret共有の防止、最小権限原則の徹底を提供します。