AI Skills Hub - Browse 180,000+ Agent Skills

Analyze git diff and generate a manual testing checklist for QA before merging PRs

CodeRabbit - AI Code Review

Idiomatic Go coding standards, Clean Architecture structure, and best practices for Fiber and Ent. Use when writing or refactoring Go code.

Fetches GitHub pull request review comments for the current repository and formats them as markdown for LLM consumption. Use when the user asks to fetch or address PR review comments or feedback.

Test the pgsql-parser repository (SQL parser/deparser). Use when working in the pgsql-parser repo, fixing deparser issues, running parser tests, or validating SQL round-trips. Scoped specifically to the constructive-io/pgsql-parser repository.

GitHub リポジトリのドキュメント（README.md, docs/）とコードの実態を深層比較し、 古い記述・不一致・誤情報を検出するスキル。 **検出原則**: 疑わしきは報告（False Positiveは許容、False Negativeは回避） Use this skill when: 「ドキュメントが最新化されてるかチェック」「READMEの内容が正しいか確認」 「ドキュメントとコードの整合性チェック」「古い記述がないか検証」と依頼された時。 NOTE: リポジトリ単位で実行。全体チェックには時間がかかるため、対象リポジトリを指定して実行する。

Set up tRPC with TanStack Query in Next.js App Router projects. Use when: (1) Setting up tRPC from scratch in a Next.js project, (2) Adding new routers or procedures, (3) Integrating authentication with tRPC context, (4) Using tRPC with React Server Components, (5) Configuring prefetching and hydration patterns.

Prisma ORM 資料庫操作技能。包含查詢模式、事務處理、 空值處理標準（重要）、軟刪除。操作資料庫時使用此技能。

調試技能。包含 Chrome DevTools MCP 操作、前後端調試技巧。 遇到 Bug 或需要調試時使用此技能。

Compliance verification and quality gate agent

Guide for assistant-stream package and streaming protocols. Use when implementing streaming backends, custom protocols, or debugging stream issues.

Control Govee smart lights via the Govee API. Supports turning lights on/off, adjusting brightness, setting colors, and scenes. Use for: (1) Controlling individual lights or groups by name, (2) Setting colors and brightness, (3) Managing device states

Sync and query CalDAV calendars (iCloud, Google, Fastmail, Nextcloud, etc.) using vdirsyncer + khal. Works on Linux.

Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features

Fix for Tauri app not loading .env file with dotenvy. Use when: (1) Environment variables return "not set" errors in Tauri commands, (2) dotenvy::from_filename() fails with relative paths like "../../.env", (3) API keys or config work locally but not in Tauri app, (4) GhostClient::from_env() or similar fails with missing env vars. The fix is that `cargo tauri dev` runs with CWD at project root, not at ui/src-tauri, so use ".env" not "../../.env".

Tauri IPC commands fail silently when testing via browser at localhost. Use when: (1) Tauri invoke() calls return no data or fail silently in Playwright/browser tests, (2) window.__TAURI__ is undefined when accessing localhost:port directly, (3) App works in Tauri window but not when tested via browser automation, (4) React Query or other data fetching shows empty results for Tauri commands. The fix is to test in the actual Tauri webview or mock the Tauri API for browser tests.

Fix for NextResponse.redirect going to wrong host (localhost:8080) on Railway, Vercel, or containerized deployments. Use when: (1) redirects work locally but go to localhost in production, (2) console shows ERR_CONNECTION_REFUSED to localhost:8080 or similar internal URL, (3) using `new URL(path, request.url)` for redirects in Next.js API routes or middleware. The fix is to use NEXT_PUBLIC_APP_URL environment variable instead of request.url as the base URL.

Fix for webhook authorization failures caused by Base64 padding character (=) being dropped when copying secrets between systems. Use when: (1) Webhook returns "Unauthorized" or "Server Error" but the secret looks correct, (2) INTERNAL_API_SECRET, WEBHOOK_SECRET, or similar auth tokens fail validation between Railway/Vercel and Convex/database, (3) Secret comparison fails despite values appearing identical, (4) CLI tools display truncated environment variables. Common with Railway CLI, Vercel CLI, and other deployment platforms that may not display trailing = characters.

Manage Better Auth user data in Convex component tables. Use when: (1) need to manually verify user email in development, (2) "Email not verified" error blocking login, (3) need to modify Better Auth user/session/account data directly, (4) can't write mutations to access component tables, (5) debugging auth issues in Convex + Better Auth setup. Covers CLI data access, export/import workflow, and common gotchas.

Fix for "let chains are only allowed in Rust 2024 or later" errors when downgrading Cargo.toml edition from 2024 to 2021. Use when: (1) changing edition = "2024" to edition = "2021", (2) compilation fails with let chain errors across multiple files, (3) need to systematically refactor `if let ... && let ...` patterns to nested if-let. Covers the refactoring patterns for converting let chains to 2021-compatible code.

Fix for Ghost Admin API posts created with empty content when using HTML. Use when: (1) Ghost posts are created successfully but have no body content, (2) HTML field is sent in POST request but post appears empty, (3) title appears but html/body is blank, (4) implementing Ghost Admin API integration with HTML content. The fix is to use source=html as a QUERY PARAMETER, not in the JSON request body.

Fix infinite loops in demo/showcase modes for scene stack architectures. Use when: (1) Demo mode gets stuck repeating the same scene, (2) scene cycling doesn't progress through all scenes, (3) orchestrator scene's on_resume isn't being called, (4) pushed scenes bypass the demo controller. Applies to game engines, UI frameworks, and any stack-based state machine with automated testing or demo modes.

Fix for Tauri v2 app crashing on startup in WSL2 with gdk-pixbuf panic: "data.len() must fit the width, height, and row_stride". Use when: (1) Tauri app panics immediately on launch in WSL2/Linux, (2) error occurs in gdk-pixbuf crate at pixbuf.rs, (3) crash happens before window renders, (4) app works on Windows/macOS but fails on Linux/WSL2. The fix is to use an empty icon array in tauri.conf.json to bypass icon loading issues with GTK.

Fix for Next.js OG image build errors with invalid CSS display values. Use when: (1) Build fails with "Invalid value for CSS property display", (2) error mentions allowed values "flex" | "block" | "none" | "-webkit-box", (3) using display: inline-block or other CSS display values in next/og ImageResponse components. The fix is to use display: flex with alignSelf: flex-start instead of inline-block.

Fix for "Unauthorized" errors in Convex mutations called from Next.js API routes when using internal API secrets for authentication. Use when: (1) Convex mutation throws "Unauthorized" even though secret is set in .env.local, (2) webhook handlers fail with 500 status and "Unauthorized" in Convex function, (3) internal API calls work locally in Next.js but fail when calling Convex mutations. The fix is to set the secret in BOTH Next.js .env.local AND Convex environment variables.

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

Transform technical or factual knowledge points into respectful, adult, consensual sexual or intimate analogies that aid understanding and memory. Use when a user explicitly requests a sexual or intimate metaphor for an abstract or technical topic for educational or creative explanation; avoid formal or sensitive contexts and refuse sexual advice or content involving minors, coercion, or explicit pornographic detail.

タスク開始時の受付票。Type 宣言 + Permit 取得を強制。 Implementation 以外は範囲制限付き。

設計ドラフトの成果物を文書のみに制限。 コード変更禁止。「設計相談 = 実装」誤認を構造的に防ぐ。

UIテスト方法（Scenario, スクショ, meta.json, C-UX契約）の環境固有手順を独立Skill化。 人間にもわかる言語で説明する。

新スレッド/新エージェントが最短で開発状況に追いつくための読み順・手順を固定。 **重要: STATUS.md だけでなく、実際のコードを検証して進捗を確認する。**

ONLY when user explicitly types /gcommit. Never auto-trigger on mentions of git, commit, push, or save.

保留图像，仅重新生成大纲

Evaluate Agent Skill design quality against specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files. Provides multi-dimensional scoring and actionable improvements.

Serena MCPの使用ガイド。シンボルベースのコード編集、検索、リファクタリングのためのコマンドリファレンス。

.claude/rules/ディレクトリにベストプラクティスに沿ったルールファイル（.md）を作成します。コーディングルール、テスト規約、セキュリティ要件などのプロジェクト固有の指示を作成する場合に使用します。paths frontmatterによる条件付きルール、適切なファイル名、サブディレクトリ構造をサポートします。

Comprehensive Storybook story creation guidelines. Covers story structure, naming conventions, and visual testing patterns. Reference this skill when creating Storybook stories for components with conditional rendering or complex UI states during Phase 2 (Testing & Stories).

Configure and use MCP (Model Context Protocol) servers in VS Code. Use when setting up MCP servers, configuring mcp.json, using MCP tools in chat, managing server trust, or troubleshooting MCP connections.

Manage Synology NAS via dsget CLI: Download Station (add/pause/resume/delete torrents, magnets, URLs), File Station (browse folders, create folders, file info), and RSS Feeds (list, view items, download). Use when managing downloads on a Synology NAS or browsing NAS files.

Use when working with Daytona SDK - uploadFile(Buffer, path), Bun install, CodeLanguage options

Set up sprint from spec file. Use when user has a spec and wants to create beads and SAM features for implementation.

Use when starting feature work that needs isolation from current workspace or before building from implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - merge, PR, or cleanup

Prisma ORM for type-safe database operations with PostgreSQL. Use when: Defining schemas, writing type-safe queries, creating migrations, modeling relations, or replacing raw SQL with ORM patterns.

TailwindCSS utility-first styling and dynamic theme system for Luxia e-commerce frontend. Use when: styling React components, creating responsive layouts, implementing the dynamic theme system, working with design tokens, or building admin/storefront UI.

Builds RESTful API routes, middleware, and request handling with service layer patterns. Use when: Creating API endpoints, adding middleware, implementing authentication guards, or structuring backend services.

Implements Redis for session storage, caching, rate limiting, and Bull job queues. Use when: implementing caching layers, session management, background jobs, rate limiting, pub/sub messaging, or idempotency keys for payment flows.

Elasticsearch audit log search and analytics for INVOOPAY platform. Use when: implementing audit logging, searching audit events, building analytics dashboards, configuring data streams, or debugging outbox publishing.

Node.js LTS runtime and server-side JavaScript patterns for INVOOPAY backend. Use when: working with backend services, async operations, crypto, Buffer handling, or Node.js APIs.

Playwright E2E testing for Luxia e-commerce platform. Builds tests for checkout flows, cart operations, authentication, CMS pages, and multilingual routing. Use when: Writing E2E tests, debugging test failures, testing payment flows, checkout sessions, cart operations, user authentication, or admin panel functionality.

Jest unit testing and test configuration for Express + TypeScript backend services. Use when: Writing unit tests, mocking services, testing business logic, setting up test infrastructure, or validating service layer functions.

Landlock-based sandbox for CLI agents. Use when running untrusted code or protecting sensitive files.

Post to X (Twitter) - tweets, media, threads with history tracking. Use when the user wants to post, tweet, or share something on X/Twitter.

Use this skill when the user needs to interact with the production environment. This includes: SSH access to the server, viewing production logs, running health checks, deploying code, viewing server status, or troubleshooting the live website. Activate when user mentions: production, deploy, SSH, server, health check, logs, live site, droplet, DigitalOcean, or asks about the deployed application.

Documentation reference catalog commands for building, checking, and fixing doc-to-code links.

Debug Rails API backend on Heroku using CLI. Use when investigating errors, checking logs, querying database via rails runner, inspecting Redis, or viewing dyno status. Supports -r staging and -r production remotes.

Build React Native UI with HeroUI Native component library. Use when user explicitly mentions HeroUI, heroui-native, or asks about HeroUI Native components like Button, Card, TextField, Dialog, BottomSheet, Toast, Switch, Checkbox, Tabs, or Accordion. Provides component APIs, compound component patterns, styling with Tailwind/Uniwind, and theming guidance.

Testing standards for C# 14 / .NET 10 with xUnit and Shouldly. Covers naming conventions (Should_X_When_Y), AAA pattern, test data builders, and mocking rules. Use for writing tests, "/test", or "help with tests".

X/Twitter CLI for reading, searching, posting, and engagement via cookies.

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

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

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

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 CoWorker4YES to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

Code quality guide for Rust. USE WHEN: writing Rust code, reviewing code, or ensuring code quality.

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.

Query Open Targets Platform for target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs, for therapeutic target identification.

Scala 3.4+ development specialist covering Akka, Cats Effect, ZIO, and Spark patterns. Use when building distributed systems, big data pipelines, or functional programming applications.

HVDC JSON 데이터를 RDF(Turtle)로 변환하고 정합성을 검증하는 스킬.

Get current test coverage and code quality status with plain-English summary

Does something useful

Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.

Plan implementations, design architectures, create technical roadmaps with detailed phases. Use for feature planning, system design, solution architecture, implementation strategy, phase documentation.

Activate for brand voice, visual identity, messaging frameworks, asset management, and brand consistency. Use when creating branded content, establishing tone of voice, managing marketing assets, validating brand compliance, or maintaining brand standards across marketing materials.

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.

Conversion copywriting formulas, headline templates, email copy patterns, landing page structures, CTA optimization, and writing style extraction. Activate for writing high-converting copy, crafting headlines, email campaigns, landing pages, or applying custom writing styles from assets/writing-styles/ directory.

Design schemas, write queries for MongoDB and PostgreSQL. Use for database design, SQL/NoSQL queries, aggregation pipelines, indexes, migrations, replication, performance optimization, psql CLI.

Design gamified marketing campaigns using points, badges, leaderboards, streaks, challenges. Use for loyalty programs, referral campaigns, onboarding flows, engagement boosts, email gamification. Provides mechanics selection, psychology alignment, strategy docs, templates, KPIs.

Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.

Manage isolated dev environments with git worktrees, auto ports, and preview URLs

How this integration talks to Marstek devices via the local Open API over UDP (JSON messages) and how to handle errors safely

Runs flake8 linting and pytest to verify no regressions. Use before completing tasks or when asked to verify/test.

Compose tailored resume with no fabricated content. Uses LLM to rewrite bullet points to align with job description keywords while strictly adhering to facts.

Professional-grade Python development with Ruff (v0.14.10) - an extremely fast Python linter and formatter. Use when working with Python codebases for (1) linting and fixing code quality issues, (2) formatting Python code, (3) configuring Ruff settings, (4) understanding and resolving specific rule violations, (5) integrating Ruff into projects or editors, (6) migrating from other tools (Black, Flake8, isort, etc.), or (7) any Ruff-related development tasks. Includes complete documentation for 937+ lint rules, formatter settings, configuration options, and editor integrations.

Validate Loopr order YAML files and referenced feature/task/test artifacts. Use as a preflight before generating tasks/tests or before implementation, and anytime order files change.

Build and publish the Weave Python SDK to PyPI. Use when releasing a new version.

Bump the Weave Python SDK version for release. Use when preparing a new release.

View recent CloudWatch logs for Lambda functions and API Gateway.

Organize, validate, and manage photo/video galleries. Create gallery structures, validate image files, and prepare content for upload.

Create effective Claude Code skills, plugins, and marketplaces with proper structure, frontmatter, and best practices. Use when creating new skills, plugins, marketplaces, converting workflows to skills, or improving existing skills.

Capture learnings from feature development to make future work easier. Called after review cycles during execute phase. Each call captures one focused learning.

将 Markdown 格式的产品功能结构思维导图转换为详细的产品功能描述文档（PRD）。适用于产品设计、需求分析、产品规划等场景，能够将层级结构的功能列表扩展为完整的功能描述。

日本市場向け高CVランディングページ制作スキル。LP、ランディングページ、セールスページ、商品ページ、サービス紹介ページの制作時に使用。PASONAの法則に基づく縦長構成、信頼要素（実績バッジ、お客様の声）、日本語フォント、CTAボタンの色心理学を適用し、シリコンバレー的ミニマルデザインを回避して日本市場で「受ける」LPを生成する。

Bootstrap and maintain a Clawdbot gateway VPS (Ubuntu 24.04) with standard dev tooling (nvm/Node 22.22.0, pnpm 10.23.0, git, python, uv, bun, homebrew optional) and verify gateway readiness. Use for new VPS setup, toolchain standardization, or auditing dev environment + permissions on Clawdbot hosts.

The Universal Package Manager for AI Skills & MCP. MUST use this skill for ANY operation related to skills: install, uninstall, update, restore, search, list, refresh, or fix configuration.

Idris2 development guidelines including OOM avoidance, project conventions, and idris2-evm EVM compilation

Vitestのテスト結果からエラー情報を効率的に抽出・分析するスキル。テストが失敗した際、テストエラーの調査時、または「テストエラーを分析」「テスト失敗の原因」「test failed」などと言及された際に使用。

Pack codebases into AI-friendly XML/Markdown bundles for context loading. Supports auto-discovery, segmented bundles, compression. Use for code review, debugging, architecture understanding. Keywords: repomix, bundle, codebase, context.

Injects WebStatic PHP/TypeScript Framework context for CMS development. Provides project structure, build commands, and code patterns for the Teslasoft content management system. Keywords: webstatic, cms, php, typescript, durandal.

Track collaboration state between Claude sessions using git branches. Enables seamless context switching by persisting progress in feature branches. Use for multi-session work, handoffs, and publishing completed work. Keywords: collab, git, branch, session, checkpoint, resume, publish.