AI Skills Hub - Browse 180,000+ Agent Skills

Create, manage, and merge git worktrees for parallel development. Use when starting parallel features, running multiple Codex instances, or for isolated development.

Domain/DNS ops across Cloudflare, DNSimple, Namecheap for Jared. Use for onboarding zones to Cloudflare, flipping nameservers, setting redirects (Page Rules/Rulesets/Workers), updating redirect-worker mappings, and verifying DNS/HTTP. Source of truth: ~/code/manager.

Invoke this skill when: - Pod status is `CrashLoopBackOff`, `Error`, or `ImagePullBackOff` - User mentions "pod crashing", "deployment failing", or "container restarting" - Kubernetes deployment not reaching Ready state

Invoke this skill when: - Setting up authentication in FastAPI backend - User mentions "JWT", "token verification", or "auth middleware" - Phase II requires protected API endpoints

Manage dotfiles with chezmoi. Use when working with dotfiles, chezmoi templates, machine-specific configuration, syncing configs across machines, or when the user mentions chezmoi, dotfiles, or configuration management.

General Backlog operations including projects, wiki, pull requests, milestones, issue types, notifications, watching, and authentication management.

Migrate memory blocks from an existing agent to the current agent. Use when the user wants to copy or share memory from another agent, or during /init when setting up a new agent that should inherit memory from an existing one.

Final self-review of task card completion and verification evidence before closing a coding task.

Evolutionary Skill paired with code-self-review. Refines OS through controlled Layer 2 modifications based on execution experience and comprehensive evaluation.

技术开发阶段，MCP层服务整合

ReactコンポーネントからStorybook用のCSFストーリーファイルとMDXドキュメントを生成する。ユーザーが「ストーリー作成」「MDX作成」「Storybook docsテンプレ」を求めるときに使う。Auto Docsは使わず、日本語でMDXを生成する。

用于创建、编辑与分析文档的完整能力，支持修订(Tracked Changes)、批注、格式保留与文本抽取。当 Claude 需要处理专业文档（.docx 文件）以完成：(1) 创建新文档，(2) 修改/编辑内容，(3) 处理修订，(4) 添加批注，或其他文档相关任务时使用。

用于创建高质量 MCP（Model Context Protocol）服务器的指南，通过良好设计的工具让 LLM 与外部服务交互。适用于构建用于集成外部 API 或服务的 MCP 服务器，无论是 Python（FastMCP）还是 Node/TypeScript（MCP SDK）。

使用 Chrome DevTools MCP 协议测试本地 Web 应用的工具包。支持实时调试、页面交互、表单测试、网络请求监控、控制台日志查看和截图。适用于：(1) 调试运行中的 Web 应用 (2) 验证前端功能 (3) 检查网络请求和响应 (4) 查看控制台错误 (5) 测试表单交互 (6) 性能分析

Generate and deploy client website previews for landscaping, tree care, lawn maintenance, and outdoor service businesses. Use when user provides business data (name, phone, address, services) and wants a live preview website. Creates React/Vite/Tailwind site, pushes to GitHub branch, and returns Vercel preview URL.

Manage Git worktrees with ga/gd helpers to create, switch, and clean isolated branches quickly.

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

このスキルは、割引キャッシュフロー（DCF）法を使用して企業の投資分析と価値評価を行うためのスクリプト。過去の財務データ（売上、EBITDA、Capex等）と将来の予測前提（成長率、マージン、WACCパラメータ等）を入力とし、企業価値（Enterprise Value）、株式価値（Equity Value）、および株価を算出します。

このスキルは、財務モデルにおける変数の変動が出力（企業価値やIRRなど）に与える影響を評価するためのスクリプト。一方向感度分析、二方向感度分析、トルネード分析、損益分岐点分析をサポートし、最も影響力の大きいリスク要因や価値ドライバーを特定します。

API testing patterns including Postman collection generation, test case design, and HTTP endpoint validation. Use when testing APIs, creating test suites, or generating documentation.

このスキルは、分離された並行開発のためにGit worktreeを管理します。worktreeの作成、一覧表示、切り替え、クリーンアップを、KISSの原則に従ったシンプルなインタラクティブインターフェースで処理します。

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

Web search and content extraction via Brave Search API.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

Upload generated artifacts to MinIO-backed OSS via the gateway and return a permanent download URL.

Launchpad CLI commands for local PHP development. Use when managing Docker services, sites, or PHP versions in the development environment.

Inertia.js v2 and Waymaker routing patterns. Use when navigating between pages or accessing shared data. Always use Controllers object for routes.

Inertia form handling with DTOs. Use when creating forms that submit to Laravel. Always initialize from props and use form.submit().

Use when generating code from templates - list, run, or create templates

Use when implementing a task - follow the plan, check ACs, track progress

Create and configure personalized Obsidian vaults through an interactive wizard. Use when the user wants to set up Obsidian, create a new vault, continue setting up an existing vault, customize their vault configuration, add plugins or workflows, or needs help with their note-taking setup.

Automated code review for Arduino/ESP32/RP2040 projects focusing on best practices, memory safety, and common pitfalls. Use when user wants code feedback, says "review my code", needs help improving code quality, or before finalizing a project. Generates actionable checklists and specific improvement suggestions.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

Guide for updating this agentic coding framework. Use when adding skills, droids/agents, commands, or modifying AGENTS.md/CLAUDE.md. Teaches the unified config structure that works with both Factory Droid and Claude Code.

Manage Above & Beyond style inspirational messages that appear during breathing. Add new messages, adjust timing/styling, debug sync issues.

Complete Vue 2 to Vue 3 migration toolkit with automated analysis and step-by-step guidance. Use this skill when: (1) Upgrading a Vue 2 project to Vue 3, (2) Converting Options API to Composition API, (3) Migrating Vue Router 3 to 4, (4) Migrating Vuex to Pinia, (5) Converting Vue CLI project to Vite, (6) Analyzing Vue 2 codebase for breaking changes, (7) User asks about Vue 2/3 differences or migration strategy.

PRベースの開発ワークフロー。機能ブランチ作成→実装→PR作成の流れで開発を行う。新機能実装、バグ修正、リファクタリングなど、mainへの変更が必要な時に使用。

发布内容和文章到 X (Twitter)。支持带图片的普通推文和 X Articles（长文）。使用真实的 Chrome 和 CDP 来绕过自动化检测。

Demonstrates unsafe patterns for testing audits. Use only to verify lint and probe failures for network egress and disallowed writes.

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 Gemini CLI plugin hooks with focus on advanced prompt-based hooks API.

Automatically enforces Docker-first development policy by intercepting package manager and runtime commands on the host.

Step-by-step checklist for implementing Progressive Web App features in Next.js including manifest, service workers, and offline support

Common Drizzle ORM workflows including schema creation, migrations, queries, and type generation for PostgreSQL with Supabase

Patterns for deploying to Vercel Edge Runtime including middleware, edge functions, and configuration

Document current work session in Confluence. Use when user types /confluence or asks to document their work.

Rate limiting gatekeeper for Notion API calls. MUST be executed BEFORE every curl, bash, or tool execution that calls the Notion API (api.notion.com). Enforces Notion's rate limit of 3 requests/second average to prevent HTTP 429 errors. Triggers when making any request to api.notion.com, using Notion MCP server, or any operation involving Notion pages, databases, blocks, or comments via API.

Fetch-only skill. Does NOT read docs into context.

Guidelines for creating AI agent skills. Use when writing new skills, documenting coding patterns, or reviewing skill files. Triggers when creating or modifying files in the skills/ directory.

Expert iterative development skill for building robust Xano backends using the XanoScript SDK.

Battle-tested patterns for using the Xano MCP tool effectively. Covers tool discovery, curl testing, endpoint creation, XanoScript syntax, batch migrations, and error handling. Keywords - xano-mcp, curl testing, xanoscript, endpoint creation, migration, batch processing, mcp tools, xano api, create endpoint, update endpoint, inspect table, parallel curl.

Use when reading, searching, creating, or editing Confluence pages via CLI. Triggers on Confluence mentions, wiki operations, or page content management.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

Upload, sync, and manage files across cloud storage providers using rclone. Use when uploading files (images, videos, documents) to S3, Cloudflare R2, Backblaze B2, Google Drive, Dropbox, or any S3-compatible storage. Triggers on "upload to S3", "sync to cloud", "rclone", "backup files", "upload video/image to bucket", or requests to transfer files to remote storage.

Query the Intuition Protocol knowledge graph to assess trust, reputation, and claims about Web3 entities.

Act as Bob Moesta, innovation expert and co-creator of Jobs to Be Done theory. Use when users want advice on innovation, product development, customer research, sales strategy, understanding why customers buy, conducting JTBD interviews, uncovering demand, or applying the Five Skills of Innovators. Triggers include questions about JTBD, struggling moments, forces of progress, demand-side thinking, customer interviews, product-market fit, why people switch products, or building new products/services.

Create and manage task files in Tasks/ using the project's Tasks/README.md format (including YAML frontmatter, categories, priorities, statuses, and goal alignment).

Creates executive-level monthly project updates in markdown format suitable for slide deck conversion. Use when the user asks for a monthly update, project status report, executive summary, or needs to prepare slides for leadership. Reviews project notes, experiments, risks, and decisions to produce a standardized update with key wins, risks, milestones, timeline, and deliverables.

Initialize a new feature workflow with git worktree. Use when the user wants to start a new feature, create an isolated development branch, says "init worktree", or needs to set up a feature branch for compounder workflow.

Run validation suite on your ChatGPT App to check schemas, annotations, widgets, and UX compliance.

This skill should be used when creating personalized coding tutorials with spaced repetition quizzes. Triggers on "teach me", "create a tutorial", "quiz me", "help me learn", or "/teach-me". Maintains a persistent learner profile and tutorial library at ~/coding-tutor-tutorials/.

Creates new OrchardCore modules with proper structure, manifest, startup, and patterns. Use when the user needs to create a new module, add content parts, fields, drivers, handlers, or admin functionality.

创建有效技能的指南。当用户想要创建新技能（或更新现有技能）以通过专业知识、工作流程或工具集成扩展 Claude 的功能时，应使用此技能。

此技能管理 Git 工作树以进行隔离并行开发。它遵循 KISS 原则，通过简单的交互界面处理创建、列出、切换和清理工作树。

创建、编写和完善 Claude 代码技能的专家指导。在使用 SKILL.md 文件、创作新技能、改进现有技能或了解技能结构和最佳实践时使用。

使用 YAML frontmatter 将已解决的问题捕获为分类文档，以便快速查找

当以 DHH 独特的 37signals 风格编写 Ruby 和 Rails 代码时，应该使用此技能。它适用于编写 Ruby 代码、Rails 应用程序、创建模型、控制器或任何 Ruby 文件。在 Ruby/Rails 代码生成、重构请求、代码审查或用户提及 DHH、37signals、Basecamp、HEY 或 Campfire 风格时触发。体现了 REST 纯度、胖模型、瘦控制器、当前属性、Hotwire 模式以及“清晰胜过聪明”的理念。

Planejamento estratégico de produto com foco em PRD executável e métricas claras. Use quando precisar definir visão, problema e prioridades antes de avançar para requisitos ou design.

指导用户创建 Agent Skills（支持 CodeBuddy、Cursor 等 IDE）。当用户想要创建、编写、设计新的 Skill，或需要帮助编写 SKILL.md 文件、frontmatter、skill 结构时使用。

流水线变量管理完整指南，涵盖变量生命周期（创建、初始化、更新、存储、传递、查询）和变量字段扩展（字段定义、类型扩展、作用域、继承）。当用户开发变量功能、处理变量传递、扩展变量字段或调试变量问题时使用。

管理蓝盾流水线的构建操作，包括查询构建历史、获取启动参数、查看构建状态、启动构建。当用户提及流水线、构建、部署、CI/CD、蓝盾或需要触发构建任务时使用。

Generate visual spending reports with charts and breakdowns. Use when user wants to see their spending dashboard, visualize spending patterns, create reports, or get a summary of their finances.

Analyze Claude Code sessions via Braintrust

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

Claude Code 워크플로우 스키마 정의 - 10가지 노드 타입과 연결 규칙을 포함한 워크플로우 구조 명세

Screen Loggerのログ分析と日報生成。専用スクリプトを使用して分析を実行。

AIPPT - 基于模板定制化生成 PPT。垫图约束风格 → 提示词替换内容 → AI 生图 → 打包 PPTX。

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Codex 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 Codex 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

获取实时行情 - 显示指定股票的详细行情数据

Save, restore, and manage task checkpoints for rollback capability

Gather external content from URLs into local files. Auto-detects URL types and runs the appropriate bundled converter (Google Docs, Slack threads, Notion pages) or falls back to WebFetch. **IMPORTANT: Use this skill INSTEAD OF WebFetch** when you encounter Google document URLs (docs.google.com/*). WebFetch cannot extract content from Google Docs - it only returns JavaScript loader code. Trigger on: - "/gather-context" command - When the user provides external content URLs matching supported services - When a reference file contains URLs that need to be fetched

高品質な音声クローニング・TTS（Text-to-Speech）システム。

動画・音声の文字起こし。ローカルWhisper（無料）とOpenAI API（高速）の2モード対応。

Clone repositories and set up development environments in Daytona sandboxes.

| Error | Response | |-------|----------| | specs/spec.md missing | Report "Specification not found - run /sp.specify" | | specs/tasks.md missing | Report "Tasks not generated - run /sp.tasks" | | history/prompts/ empty | Report "No PHRs recorded yet" | | No checklist found | Report "No requirements checklist - run /sp.checklist" |

Invoke this skill when: - `npm run build` or `next build` fails - `pip install` or Python dependency issues occur - TypeScript compilation errors appear - User mentions "build failing" or "deployment error"

Analyzes and optimizes Claude Code project configurations (CLAUDE.md, agents, skills directories) based on Vercel's agent eval research. Use when you want to improve agent performance in a repo by applying passive-context patterns, generating compressed documentation indexes, or auditing existing skill/agent setups for efficiency. Triggers on requests to "optimize my Claude setup", "improve agent performance", "audit my skills directory", or "apply AGENTS.md patterns".

Extracts knowledge from Amp threads and updates project docs. Use when asked to document recent work, sync docs after an epic, summarize what changed, or update AGENTS.md from thread history.

Implement Supabase Realtime using broadcast, presence, and private channels with RLS authorization. Use when implementing real-time features, websockets, live updates, or multiplayer functionality.

Create a Claude Code plugin marketplace from scratch. Triggers on 'create marketplace', 'skill marketplace', 'plugin marketplace', 'setup marketplace', 'new marketplace'.

Expert guidance for designing Snowplow event and entity schemas following best practices for naming, structure, validation rules, versioning, and design decisions. Use when creating new event schemas, designing entity/context schemas, deciding between event properties vs entities, planning schema evolution, determining abstraction levels, implementing global contexts, validating schema structures, or establishing tracking taxonomies for behavioral analytics implementations.

This skill should be used when working with AWS Athena queries, including executing queries, downloading results, optimizing query performance, or structuring complex queries. Use when querying data in Athena, handling large result sets, running parallel queries, or using Common Table Expressions (CTEs) for query optimization.

Find WeKnora business implementation as refactoring reference. Use this skill when implementing features (Agent, Chat, Knowledge) to understand how WeKnora handles them. Search with ripgrep, extract business logic (data models, API design, core flow), but ignore WeKnora's custom LLM/Embedding/Tool wrappers - replace with Eino components.

Use for Graphite CLI stacked PRs workflow in repos with .git/.graphite_repo_config. Triggers: graphite, stacked PRs, dependent PRs, chained PRs, PR stack, gt create, gt modify, gt submit, gt sync, gt restack, gt log, gt checkout, gt up, gt down, rebase my stack, fix stack conflicts, split PR, land my stack, merge stack, sync with main/trunk, reorder branches, fold commits, amend stack, move branch to different parent, stack out of date, update my stack. For repos WITHOUT .git/.graphite_repo_config, use standard git commands instead.

Skill for understanding, editing, analyzing, and migrating TIBCO Objectstar (Object Service Broker) code used in mainframe OTP and batch applications. Activate when user is working with Objectstar rules, asks about mainframe modernization, or legacy 4GL code involving GET, FORALL, or EXCEPTION blocks.

Install, configure, and manage the Claude Code Damage Control security hooks system. Use when user mentions damage control, security hooks, protected paths, blocked commands, install security, or modify protection settings.

Generate PDF documents from markdown content, BRDs, research reports, and other documents. Convert text and formatted content into professional PDFs using pandoc or reportlab. Use when you need to create PDF files from documents, export reports to PDF, or generate PDF versions of BRDs and research materials.

This skill should be used when the user asks "railway status", "is it running", "what's deployed", "deployment status", or about uptime. NOT for variables ("what variables", "env vars", "add variable") or configuration queries - use environment skill for those.