AI Skills Hub - Browse 180,000+ Agent Skills

Bump version in Cargo.toml using cargo-version-info bump command

Set up Git worktrees with environment isolation. Use when creating worktrees, managing port conflicts between worktrees, copying .env files to worktrees, or isolating Claude settings per worktree. Handles PORT_OFFSET calculation, file copying, database isolation, and IDE configs.

Automatically read large Figma pages frame-by-frame when the page is too large to read at once. This skill should be used when (1) get_design_context or get_figjam fails due to page size being too large, (2) the user provides a Figma page URL or nodeId and requests code generation, or (3) the user explicitly asks to read an entire Figma page or all frames.

将Markdown文章转换为美化的HTML格式，适配微信公众号发布。应用专业CSS样式、代码高亮、优化排版。当用户说"美化这篇文章"、"转换为HTML"、"优化公众号格式"、"生成公众号HTML"时使用。

从 AI 产品经理视角撰写微信公众号文章。涵盖 AI 产品拆解、场景解决方案、效率提升实战、产品方法论、行业观察。当用户说"写一篇关于XXX的文章"、"分析一下XXX产品"、"聊聊XXX"时使用。

Token-efficient library documentation fetcher using Context7 MCP with 86.8% token savings through intelligent shell pipeline filtering. Fetches code examples, API references, and best practices for JavaScript, Python, Go, Rust, and other libraries. Use when users ask about library documentation, need code examples, want API usage patterns, are learning a new framework, need syntax reference, or troubleshooting with library-specific information. Triggers include questions like "Show me React hooks", "How do I use Prisma", "What's the Next.js routing syntax", or any request for library/framework documentation.

REST-based access to Knack Objects and Views for data extraction and transformation. Primary skill for reading HTI operational data from Knack data...

iOS Simulator automation - screenshot capture, UI testing, visual QA for SwiftUI apps

Android Emulator automation - screenshot capture, UI testing, visual QA for Android apps

Generates professional PDF reports for VC due diligence. Compiles metrics, cap table, risk assessment, and market context into executive-ready documents with Mermaid visualizations. Use when finalizing diligence, creating IC materials, or generating LP reports. Triggers on "generate report", "create PDF", "IC materials", "diligence report".

Models cap tables, dilution scenarios, and exit waterfalls for VC due diligence. Use when analyzing ownership structures, modeling investment rounds, calculating dilution, building waterfall analyses, or reviewing liquidation preferences. Triggers on "cap table", "dilution", "ownership", "waterfall", "liquidation preference", "option pool".

코드 리뷰 전문 skill. TypeScript, JavaScript, Python, Swift, Kotlin, Go 지원. 정적 분석, 베스트 프랙티스 검사, 보안 스캔, 리뷰 체크리스트 생성. 사용 시기: (1) PR 리뷰 시 (2) 코드 품질 피드백 시 (3) 보안 취약점 식별 시 (4) 코드 표준 검사 시 (project)

Optimize BK search with intent, detail level, and store filtering

This skill should be used when the user asks about "MakerKit patterns", "CLAUDE.md files", "what MCP tools are available", "how does MakerKit structure", "personal vs team accounts", "RLS patterns in MakerKit", or needs quick reference for MakerKit conventions.

数式、フォーマット、データ分析、視覚化をサポートする包括的なスプレッドシート作成、編集、分析。Claudeがスプレッドシート（.xlsx、.xlsm、.csv、.tsvなど）を操作する必要がある場合：(1) 数式とフォーマットを含む新しいスプレッドシートを作成、(2) データを読み取りまたは分析、(3) 数式を保持しながら既存のスプレッドシートを変更、(4) スプレッドシートでのデータ分析と視覚化、または(5) 数式を再計算

追跡変更、コメント、フォーマット保持、テキスト抽出をサポートする包括的なドキュメント作成、編集、分析。Claudeがプロフェッショナルドキュメント（.docxファイル）で作業する必要がある場合：(1) 新しいドキュメントを作成、(2) コンテンツを変更または編集、(3) 追跡変更で作業、(4) コメントを追加、またはその他のドキュメントタスク

モダンなフロントエンドWebテクノロジー（React、Tailwind CSS、shadcn/ui）を使用して、精巧なマルチコンポーネントclaude.ai HTML成果物を作成するためのツールスイート。状態管理、ルーティング、またはshadcn/uiコンポーネントを必要とする複雑な成果物に使用 - シンプルな単一ファイルHTML/JSX成果物には使用しないでください。

This skill provides instructions for using the Code Repos MCP server to discover and navigate code repositories.

WebRTC loopback pipeline ve debug rehberi. Anahtar kelimeler: loopback, RTCPeerConnection, SDP, opus bitrate, remote stream, activator audio, delay

Maintain ChatGPT persistent context in LyreAutoPlayer/ops/ai/context/agents.md and generate a Claude execution prompt in .claude/private/plan.md from a chat transcript.

Export Typst page as PNG and view it. Use when debugging layout issues, checking visual output, verifying formatting, or when the user wants to see what the document looks like.

This skill should be used when the user asks to "use Gemini Batch API", "process documents at scale", "submit a batch job", "upload files to Gemini", or needs large-scale LLM processing. Includes production gotchas and best practices.

This skill should be used when the user asks to “access LSEG data”, “query Refinitiv”, “get market data from Refinitiv”, “download fundamentals from LSEG”, “access ESG scores”, “convert RIC to ISIN”, “get shareholder activism data”, “query poison pills”, “access corporate governance data”, “find activist campaigns”, “get syndicated loans data”, “query loan deals”, “get infrastructure projects”, “query project finance data”, “get private equity data”, “query VC investments”, “find PE-backed companies”, “get M&A data”, “query mergers and acquisitions”, “find acquisition deals”, “get IPO data”, “query equity offerings”, “find new issues”, “get joint venture data”, “query strategic alliances”, “get news headlines”, “query news data”, “fetch news articles”, or needs the LSEG Data Library Python API.

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.

Spawns parallel pi agents to work on multiple GitHub issues or PRs using git worktrees. Use when asked to process multiple items in parallel, perform bulk reviews/fixes, or orchestrate entire projects.

Create gradient skybox with horizon control

Generate heightmap-based terrain with noise functions and vertex displacement

Contract for writing Mixboard skills—structure, scope, declarations, and prohibitions

Execute Maven or Gradle builds to validate migrations including clean builds, test execution, and error analysis. Use when verifying that migration changes compile and tests pass.

Get Image [from] Internet Link - Zero-setup CLI for downloading full-resolution images from iCloud, Dropbox, Google Photos, and Google Drive share links. Four-tier capture strategy, browser automation, HEIC conversion, album support. Node.js/Playwright.

静默管理项目状态,返回 CURRENT_PROJECT 路径供工作流使用。用户开始描述选题时自动调用。

Research agent for external documentation, best practices, and library APIs via MCP tools

SoloDevFlow R-D-C-T 工作流入口：需求分析阶段。 将自然语言需求转化为结构化文档，深挖依赖链。 当用户提出新功能、修改需求、报告 Bug，或说"添加"、 "实现"、"我想要"、"能不能"、"帮我做"等意图时自动触发。 输出 docs/requirements/<domain>/<feature>.md 文档。

Develop Reachy Mini robot behaviors. Use when writing Python scripts to control the robot, understanding SDK patterns, or debugging motor/sensor issues. Triggers on keywords like "reachy", "robot", "antenna", "head pose", "stewart platform", "goto_target", "daemon".

// 24pt - List row icons Image(asset: .X24.camera)

Is this text for spaces/objects/collaboration? YES → Workspace.xcstrings (493 keys) NO → Continue

This creates: `Modules/AnytypeCore/AnytypeCore/Generated/FeatureFlags.swift`

Track and manage work with bd issue tracker for persistent context across sessions and compaction events. Use for work needing dependencies, recovery after compaction, or multi-session tracking.

Write CMake and Make files like a principal engineer with decades of experience. Use when creating, refactoring, reviewing, or debugging CMakeLists.txt, Makefiles, or build system configurations for C/C++ projects. Produces elegant, minimal, modern build files that reflect deep understanding of build systems.

Manages cross-session learning and memory persistence. Use when user mentions 前回何をした, 履歴, 過去の作業, セッション記録, continue from before, session history. Do NOT load for: 実装作業, レビュー, 一時的な情報.

Cursorでclaude-memのMCPサーバーにアクセスし、過去のセッション記録を検索・新しい観測を記録。トリガー: 'メモリ検索', 'claude-mem', '過去の判断', '記録して', 'memory search', 'past decisions'. Do NOT load for: 通常のコーディング、一時的なメモ、実装作業。

配合 backend-feature 使用的 Java 21 + Spring Boot 3 后端自动化测试技能。包含单元测试(Service)、切片测试(Controller)及 AssertJ 断言规范。Use this skill to generate JUnit 5 tests. Enforces Mockito for isolation, WebMvcTest for APIs, and strictly validates CommonResult/PageResult structures.

Add Neovim plugins not available in NixVim's official plugin set using extraPlugins and extraConfigLua. Use this skill when the user requests adding a plugin by GitHub URL or mentions a plugin that doesn't exist as a native NixVim module.

Create new shell functions for Kit's Toolkit following established patterns. Use when adding functions, extending toolkit capabilities, creating utilities, or when user mentions "add function", "create function", "new kit function", or references kit_pattern.md. Handles pattern validation, category management, and testing.

This skill should be used when the user asks to "create a mock", "generate a mock", "use @Mocked macro", "mock a protocol", "write test mocks", mentions "Swift Mocking library", asks about "@MockedMembers", "@MockableProperty", or "@MockableMethod" macros, or needs guidance on protocol mocking for unit tests in Swift.

ROSBAGファイルからGMappingでマップを生成する。rosbagからmap作成、SLAMマッピング、センサーデータからマップ生成時に使用。

Manage GitHub issues with full CRUD operations. Use for creating, listing, updating, commenting on, and closing issues.

Write Go unit tests following project patterns. Use when creating tests, improving coverage, or fixing test failures.

Process video files with audio extraction, format conversion (mp4, webm), and Whisper transcription. Use when user mentions video conversion, audio extraction, transcription, mp4, webm, ffmpeg, or whisper transcription.

Search YouTube channels for videos and extract transcripts. Use when user asks to find YouTube videos, get video transcripts, search specific channels, analyze YouTube content by topic or date range, or needs video URLs and content for research.

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

Generate procedural images in vanilla JavaScript for UI elements, icons, and test patterns without external URLs. Use when creating icons, glyphs, symbols (electronics, UI, arrows), placeholder images, or test patterns programmatically. Triggers on requests for generated images, procedural graphics, inline icons, or when external image URLs are unavailable.

Implement Supabase webhook signature validation and event handling. Use when setting up webhook endpoints, implementing signature verification, or handling Supabase event notifications securely. Trigger with phrases like "supabase webhook", "supabase events", "supabase webhook signature", "handle supabase events", "supabase notifications".

Deploy Supabase integrations to Vercel, Fly.io, and Cloud Run platforms. Use when deploying Supabase-powered applications to production, configuring platform-specific secrets, or setting up deployment pipelines. Trigger with phrases like "deploy supabase", "supabase Vercel", "supabase production deploy", "supabase Cloud Run", "supabase Fly.io".

Deploy Vercel integrations to Vercel, Fly.io, and Cloud Run platforms. Use when deploying Vercel-powered applications to production, configuring platform-specific secrets, or setting up deployment pipelines. Trigger with phrases like "deploy vercel", "vercel Vercel", "vercel production deploy", "vercel Cloud Run", "vercel Fly.io".

Collect Vercel debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Vercel problems. Trigger with phrases like "vercel debug", "vercel support bundle", "collect vercel logs", "vercel diagnostic".

Implement Vercel webhook signature validation and event handling. Use when setting up webhook endpoints, implementing signature verification, or handling Vercel event notifications securely. Trigger with phrases like "vercel webhook", "vercel events", "vercel webhook signature", "handle vercel events", "vercel notifications".

Figmaデザインをピクセルパーフェクトなコードに変換する。Figmaファイルからの実装時、「デザインを実装して」「コードを生成して」「コンポーネントを作って」「Figmaデザインを構築して」といったリクエスト時、FigmaのURLが提供された時、またはFigmaの仕様に合わせたコンポーネント作成を依頼された時に使用。Figma MCPサーバーへの接続が必要。

Firebase platform expert with Vertex AI Gemini integration for Authentication, Firestore, Storage, Functions, Hosting, and AI-powered features. Use when asked to "setup firebase", "deploy to firebase", or "integrate vertex ai with firebase". Trigger with relevant phrases based on skill purpose.

Automatic activation for all google cloud agent development kit (adk) Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

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 Clawdis to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

Manage Apple Reminders via the `remindctl` CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.

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

需求分析助手，将模糊需求转换为结构化文档。支持两种输出格式：用户故事（User Story）适合敏捷开发，PRD（产品需求文档）适合完整功能规划。通过针对性提问澄清歧义。

Export X/Twitter bookmarks to markdown. Use when asked to fetch, export, or save bookmarks from X/Twitter.

Publish newsletter articles to Substack as drafts. Use when "publish to substack", "create substack draft", "post newsletter to substack", "substack draft".

Orchestrate multi-agent workflows with kiro-cli and Gemini workers. **Trigger Conditions:** - WHEN starting execution from a Kiro spec directory - WHEN dispatching tasks to worker agents - WHEN handling task completion and review - WHEN synchronizing state to PULSE document **Use Cases:** - Multi-agent code implementation with kiro-cli and Gemini - Tmux-based task visualization and monitoring - Structured review workflows with Codex reviewers - Dual-document state management (AGENT_STATE.json + PROJECT_PULSE.md)

Rust 项目工程化开发 Skill：统一 workspace + 多 crate 分层架构；强制门禁（fmt/check/test/build/clippy -D warnings）；遵循 perf-book 的“先测量再优化”原则；鼓励不兼容重构减债；提供单文件/函数体行数门禁脚本（支持 glob）；测试参考 rust-testing（mockall/proptest/wiremock/mockito，集中管理 tests）。

Build and debug Reflex (rx) UIs in this repo. Use for editing ui/*.py, choosing rx components, fixing Var/conditional/foreach issues, and applying responsive/layout patterns from the Reflex docs.

Stand up and verify the “real skeleton” observability stack (Prometheus, Grafana, Loki, Tempo, OTel Collector) plus Python service instrumentation. Use when wiring or debugging metrics/logs/traces in the Compose environment.

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".

A comprehensive YouTube KOL discovery and analysis system for product marketing. Use this skill when users need to (1) Search and discover YouTube channels (KOLs) by keywords, (2) Analyze channel metrics (subscribers, views, engagement rates), (3) Detect channel language and video content language, (4) Use AI (Deepseek/Zhipu) to evaluate channel-product fit for marketing campaigns, (5) Export analysis results to Excel with multiple sheets, (6) Deploy a Docker-based web system with real-time progress tracking on Synology NAS or other servers, (7) Manage YouTube API keys with automatic rotation and quota tracking, (8) Support incremental updates to track new channels over time.

Creates a new subproblem when the current problem is too complex. Use when agent-solve determines decomposition is needed. Creates child problem and links it to parent's preliminaries.

Applies a direct fix to proof text. Use when agent-fix determines a gap can be fixed with minor additions (3 or fewer steps). Updates proof and records the response in validation.responses.

Submits a completed proof for verification. Use when agent-prove has written a full proof and is ready for agent-check to verify it. Updates the statement with proof text and sets status to validating.

Marks a statement as false when a counterexample is found. Use when agent-prove or agent-fix discovers the statement is unprovable due to being actually false. Records the counterexample and updates status.

Creates a sub-statement to fill a gap identified by agent-check. Use when agent-fix determines the gap requires a non-trivial intermediate result. Records the response in validation.responses and links to parent's preliminaries.

Creates a statement that resolves a problem. Use when agent-solve determines a single statement can bridge the gap between hypothesis and objective. Invokes src/state.py to create the statement and src/prob.py to link it.

Proposes a modified statement when the original is unprovable but fixable. Use when agent-prove or agent-fix determines the statement needs stronger premises or weaker conclusion. Records the proposal for orchestrator decision.

This skill should be used when the user asks to "deploy", "upload", "publish" a frontend project, static website, or build output. Also activates when user mentions "pinme", "IPFS deployment", or wants to host static files online.

Supabase database, auth, and Edge Functions procedures

Railway deployment and troubleshooting procedures

Use this skill when working with Circle's Cross-Chain Transfer Protocol v2 on Solana, including `receiveMessage` (mint) and `depositForBurn` operations.

Use this skill when building raw Solana instructions that interact with Anchor programs, especially when bypassing Anchor's method builders.

Parse large documents into structured sections with abstracts and metadata

Perform comprehensive code review of recent changes (diff/commit/PR). Analyze security, code quality, performance, reliability, and Susumon project conventions. Use when the user requests a review (e.g. "/review", "review this code"), before opening a PR, or after significant changes.

This skill should be used when generating integrated reports from lab notebooks, improving existing reports, or exporting reports to PDF/typst. Triggered by requests like "generate report", "create summary", "refine report", "improve report", "export to PDF", "typst出力", "PDFに変換", "レポートを作成", or "export report to PDF". For PDF export, use scripts/export_pdf.sh (pandoc + typst).

This skill should be used when initializing a new bioinformatics research project, checking project status, updating project phase, or getting research best practices guidance. Triggered by requests like "initialize project", "check status", "update phase", or "research best practices".

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Validates type consistency across Rust, TypeScript, and PostgreSQL boundaries.

Transcribe audio recordings from meetings (MP3, WAV, M4A) into text using AWS Transcribe service

Evaluates whether a programming language dependency should be used by analyzing maintenance activity, security posture, community health, documentation quality, dependency footprint, production adoption, license compatibility, API stability, and funding sustainability. Use when users ask "should I use X or Y?", "are there better options for [feature]?", "what's a good library for [task]?", "how do we feel about [dependency]?", or when considering adding a new dependency, evaluating an existing dependency, or comparing/evaluating package alternatives.

HTML/reveal.js content generation guide. Use this skill when you need to create HTML presentations that can be previewed via `task-mind view`. Covers reveal.js advanced design, CSS techniques, and multi-page collaboration workflow.

HTML/reveal.js content generation guide. Use this skill when you need to create HTML presentations that can be previewed via `frago view`. Covers reveal.js advanced design, CSS techniques, and multi-page collaboration workflow.

Build automated pipelines to extract structured content (frameworks, tactics, examples) from video courses using Google Gemini API. Creates reusable extraction systems with configurable prompts, batch processing, and markdown output. Use this skill when the user needs to convert video content into searchable, structured knowledge bases.

Bundle a local git repository into a zip excluding .gitignored files (optionally include sanitized .git metadata), submit it to an OpenAI API model for a long-running review, extract a unified diff patch from the response, apply the patch locally, and capture follow-up instructions.

scaling skill

Develop R packages following best practices with devtools, roxygen2, and testthat. Supports both tidyverse and base R coding styles. Use when creating new R packages, adding functions to packages, writing documentation, creating tests, managing dependencies, building vignettes, creating package websites with pkgdown, or preparing for CRAN submission. Triggers on R package development tasks, DESCRIPTION file editing, roxygen2 documentation, testthat testing, pkgdown website setup, or R CMD check issues.

Write comprehensive tests following AAA pattern. Use when creating unit tests, integration tests, or adding test coverage.