AI Skills Hub - Browse 180,000+ Agent Skills

This skill should be used when managing contact information - updating email, social media links (LinkedIn, GitHub, Instagram), or location. It provides an interactive workflow for editing contact details stored in a TypeScript constants file.

Experiencia de beatmaking con Strudel.cc para Casa 24 Records. Usar cuando el usuario quiera crear beats (trap, reggaeton, house, drill, lo-fi, dembow), programar drums 808/909, diseñar sonidos, o aprender pattern programming. Incluye catálogo completo de synths, drums, efectos, y templates por género.

Manage tasks in the tasker docstore CLI using natural language or explicit commands. Use when a user asks for “tasks today/overdue,” adding tasks, listing tasks, moving tasks between columns, marking done, viewing a board, or onboarding to tasker.

给图片添加文字或图片水印，支持自定义位置、透明度、字体大小等参数；适用于版权保护、品牌标识、内容标记等场景

Comprehensive video processing toolkit using FFmpeg. Supports format conversion, resolution adjustment, cropping/trimming, compression optimization, watermarking, and audio extraction. Use when Claude needs to process video files: (1) Convert between formats (MP4, AVI, MOV, MKV, WebM), (2) Adjust resolution/scale videos, (3) Crop or trim video segments, (4) Compress/optimize file size, (5) Add watermarks (image or text), (6) Extract audio or remove audio streams, or (7) Batch process multiple videos.

A skill that extracts keyframes from video files and analyzes their content. Automatically removes duplicate frames and optimizes image quality to reduce token consumption.

Runs Ralph orchestrator with the code-assist configuration to implement code tasks autonomously. Spawns Ralph as a subprocess that handles the full TDD workflow (Explore, Plan, Code, Commit) for the given code task file.

Use when building or modifying UI components. Use when you need visual feedback during development. Use when implementing designs incrementally.

MANDATORY: Use codemap instead of Grep/Search for finding code. This project has a pre-built index. Use codemap commands to find symbols, trace dependencies, and understand code structure. Only fall back to Grep if codemap doesn't find what you need.

Build data tables with TanStack Table and React Aria Components. Use when creating tables, implementing sorting, filtering, pagination, row selection, or column visibility.

Search, retrieve, and parse papers from arXiv. Extracts structured data including sections, figures, tables, and references from DOCX, PDF, and LaTeX formats. Use for literature search, metadata retrieval, and preparing papers for analysis.

Create a Linear issue. Use when user asks to create an issue, register a task, track work, or needs a ticket before starting development. Do NOT load for: implementation work, code review, deployment.

模拟10年经验项目经理，以犀利、独到的角度对项目需求进行深度追问和挑战。适用于需求评审、项目规划、风险识别等场景，帮助团队发现盲点、完善方案。

根据项目需求文档进行系统架构设计，包括技术选型、中间件选择、架构模式设计和最佳实践应用。适用于新系统架构设计、现有系统重构评估、技术方案评审等场景。

Build and merge M4B audiobooks on Linux from multiple audio files or multi-part M4B sets, with chapter generation, metadata normalization, UTF-8/Russian encoding handling, and validation. Use when combining MP3/M4A/AAC/FLAC/OGG/WAV into one M4B, merging split M4B parts, or fixing audiobook chapters and metadata.

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossible

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Express-inspired Go web framework built on fasthttp.

Build desktop apps with Rust backend and WebView frontend.

Comprehensive n8n workflow automation expertise. Use when building, debugging, or optimizing n8n workflows, including node configuration, expressions, code nodes (JavaScript/Python), validation, and workflow patterns.

将 OpenSpec 分解为可执行的任务列表。 支持十步循环 A.2 (任务规划) + A.3 (Agent 分配)。 实现双层任务架构：tasks.md (粗粒度) + detailed-tasks.yaml (细粒度)。

基于v4.5架构文档管理系统，自动化管理代码架构文档的创建、更新和验证，确保文档与代码100%同步。

Transform text content into professional Mermaid diagrams with CLI tool. Use when users ask to visualize concepts, create flowcharts, make diagrams from text, generate sequences, timelines, mindmaps, or any visualization. Supports validation, layout optimization, and HTML export with built-in syntax error prevention.

Problem decomposition tool that converts complex problems into actionable task lists with HTML reports including Gantt charts, dependency visualization, and estimated effort. Use when user has complex problems that need systematic breakdown into executable tasks.

Manage Dojo development services: Katana (local blockchain) and Torii (indexer). Use when: - Starting/stopping Katana or Torii - Checking service health or ports - Debugging connection issues - Viewing service logs - Keywords: "start", "stop", "katana", "torii", "services", "ports", "logs", "indexer", "bindings", "typescript", "dojo.js", "sdk", "query", "subscribe", "zustand", "optimistic"

Use when writing Lua code for game development (LÖVE2D, Defold, WoW addons), Neovim plugins, or embedded scripting. Use when you think code is "too simple for types" or "just a prototype" - these are symptoms this skill applies.

Sell all SPL tokens in your Solana wallet for SOL

Scaffold repo-local Ralph autonomous harness under scripts/ralph/. Use when user runs /flow-next:ralph-init.

Create structured build plans from feature requests or Flow IDs. Use when planning features or designing implementation. Triggers on /flow-next:plan with text descriptions or Flow IDs (fn-1, fn-1.2).

Manage git worktrees (create/list/switch/cleanup) and copy .env files. Use for parallel feature work, isolated review, clean workspace, or when user mentions worktrees.

Manually trigger plan-sync to update downstream task specs after implementation drift. Use when code changes outpace specs.

Testing patterns for Prowler API: JSON:API, Celery tasks, RLS isolation, RBAC. Trigger: When writing tests for api/ (JSON:API requests/assertions, cross-tenant isolation, RBAC, Celery tasks, viewsets/serializers).

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.

Syncs skill metadata to AGENTS.md Auto-invoke sections. Trigger: When updating skill metadata, regenerating Auto-invoke tables, or after creating/modifying skills.

MSI-a conversational agent patterns using LangGraph. Trigger: When working on agent conversation flow, nodes, state, tools, prompts, or FSM.

Creates UI tests for a GitHub issue and verifies they reproduce the bug. Iterates until tests actually fail (proving they catch the issue). Use when PR lacks tests or tests need to be created for an issue.

Implement with discipline. Apply when executing tasks in /execute workflow.

Generate phased implementation plans from requirements and UI wireframes. Use when the user provides requirements documents and/or UI wireframes and wants to create a detailed, phased implementation plan. Triggers on requests like "create implementation plan", "plan the implementation", or when asked to design an implementation approach for a project with existing requirements. Produces description-only plans (no code) with clear phases, dependencies, and testing checklists.

Transcribes audio and video files to text using OpenAI's Whisper CLI with contextual grounding. Converts audio/video to text, transcribes recordings, and creates transcripts from media files. Use when asked to "whisper transcribe", "transcribe audio", "convert recording to text", or "speech to text". Uses markdown files in the same directory as context to improve transcription accuracy for technical terms, proper nouns, and domain-specific vocabulary.

Use when releasing a new version, updating CHANGELOG.md, or user asks to document changes - enforces Keep a Changelog format with proper categorization derived from conventional commits

Use when maintaining a fork of a Python package without GitHub access, importing upstream releases from PyPI tarballs, or merging upstream updates into a fork using vendor branch strategy

환경변수(.env.*), Spring 프로파일(application-*.yml) 수정 시 사용. app/backend/CLAUDE.md 참조 필수. 서비스별 포트 중복 검증, 민감 정보는 .env.local만, application-*.yml은 플레이스홀더만(기본값 금지). 의미없는 override 지양. SQS 엔드포인트 정확성 확인.

Build type-safe Nuxt 3 applications with Nitro API patterns. Covers validation, fetch patterns, auth, SSR, composables, background tasks, and real-time features.

Test Nuxt 3 / Nitro applications - both API handlers (real PostgreSQL, transaction rollback) and frontend components (@nuxt/test-utils, mountSuspended).

Use when creating REST API clients, SDK wrappers, or HTTP service integrations. Generates type-safe client code with retry logic, error handling, rate limiting, and comprehensive tests. Triggered by requests to integrate external APIs, build SDK clients, or create service wrappers.

Create beautiful terminal output with Rich library including tables, progress bars, panels, and syntax highlighting. Use when building CLI applications or enhancing terminal output in Python.

Search for items and properties on Wikidata and retrieve external identifiers. Use when an agent needs to (1) search for Wikidata items by label or alias, (2) get entity details including labels, descriptions, aliases, (3) retrieve external identifiers (authority control IDs) for an entity, (4) look up properties or claims for items. Triggers on queries mentioning Wikidata, Q-IDs, P-IDs, authority control, external identifiers, or structured knowledge base lookups.

Database seeding toolkit for Supabase projects. Use when: (1) Creating seed data files, (2) Populating lookup/reference tables, (3) Generating test data, (4) Bulk loading data with COPY, (5) Running seed files against database, (6) Managing large seed files with DVC

Database migration toolkit for Supabase projects. Use when: (1) Creating new migration files, (2) Writing schema changes (CREATE TABLE, ALTER, etc.), (3) Adding indexes, triggers, or RLS policies, (4) Fixing RLS performance issues (auth function wrapping, policy consolidation), (5) Validating migration conventions, (6) Running migrations locally, (7) Naming database objects

Generate PROJECT-MAP.auto.scm by extracting structure from codebases. Invoke when user requests project mapping, structure extraction, or needs to create/update .phi maps.

Creates effective Claude Code skills following best practices. Use when the user asks to create a skill, write a SKILL.md, or needs help authoring agent instructions.

Boot configuration for Bazzite OS. BIOS/UEFI access, GRUB menu settings, secure boot key enrollment, and Windows dual-boot setup. Use when users need to configure boot options or access BIOS settings.

GPU monitoring and performance metrics for Ollama inference. Check GPU status, VRAM usage, loaded models, and inference performance metrics like tokens per second.

Security configuration for Bazzite. LUKS disk encryption with TPM auto-unlock, secure boot key management, and sudo password feedback. Use when users need to configure security features.

GPU passthrough and virtualization for Bazzite. KVM/VFIO setup, Looking Glass (kvmfr), USB hotplug for VMs, and libvirt configuration. Use when users need GPU passthrough or advanced virtualization features.

Storage management for Bazzite. Automounting drives (BTRFS/EXT4, Framework, SteamOS), BTRFS deduplication, rmlint disk trimming, and snapper snapshots. Use when users need to configure disk and partition management.

Audio configuration for Bazzite. Virtual audio channels for Game/Voice/Browser/Music, 7.1 surround for headphones, Bluetooth headset profiles, and PipeWire management. Use when users need to configure audio on Bazzite.

Gaming ecosystem for Bazzite. Steam fixes, Proton troubleshooting, EmuDeck emulation, Decky Loader plugins, Sunshine game streaming, frame generation, and media apps. Use when users need help with gaming on Bazzite.

Analyzes continuous glucose monitor CSV data, calculates TIR/TAR/TBR metrics, generates AGP charts, and provides AI-powered diabetes management recommendations. Handles Dexcom, FreeStyle Libre, Guardian formats.

iOS speech recognition implementation using @react-native-voice/voice. Use when debugging transcription issues, modifying session handling, or understanding the accumulated text tracking mechanism.

This skill should be used when developers need to generate pod network smart contract boilerplate. It orchestrates the pod-templating MCP server to scaffold production-ready contracts (tokens, NFTs, voting, auctions, basic) using FastTypes for order-independent execution. Use when starting new contracts, migrating from Ethereum, or needing pod-specific patterns.

Generate ASCII art typography using pyfiglet. Use when user asks for ASCII art text, banners, headers, logo text, terminal art, or decorative typography. Curated whitelist of 24 display fonts available, agent can also use any of 500+ pyfiglet fonts.

iOS SimulatorをAIで操作してデバッグ・検証。ビルド→起動→UI操作→スクショ→分析のループ。 使用タイミング: (1) UIの動作確認が必要な時、(2) 「Simulatorで確認して」「スクショ撮って」、 (3) バグの再現・調査時、(4) UI実装の検証時、(5) アクセシビリティの確認時 前提条件: ios-simulator MCPサーバーが有効化されていること（apple-platform-plugin導入で自動設定）

コードベースから開発者向けドキュメントを生成する。3パス読み取りアプローチで根拠に基づく信頼性の高いドキュメントを作成。「ドキュメント生成」「コードからドキュメント」「codebase map作成」「代表フロー抽出」「変更ガイド作成」と言われた時に使用。生成するのはコードベースマップ、代表フロー（成功+失敗）、変更プレイブック、設定/外部I/F台帳、検証レポート。継続的開発の属人化を防ぎ、変更の安全性を高めるドキュメントを目指す。

コード変更の影響範囲分析スキル。変更が引き起こし得る影響を影響面（code/interface/data/external/config/runtime/security/observability）ごとに整理し、「どこをレビューし、何をテストし、何を観測すべきか」を根拠つきで提示する。

LDE（Law-Driven Engineering）のLink Map（連結表）管理スキル。 Law ↔ Term の相互参照関係を可視化し、孤立の検出と影響分析を行う。 使用タイミング: (1) Law Cardを作成した後、(2) Term Cardを作成した後、 (3) 「Link Mapを更新して」「孤立チェックして」、(4) 変更影響分析時

LLM生成システムの検証設計スキル。assay-kitフレームワークを活用し、LLM特有の失敗モード（幻覚、例への過学習、部分的処理）を考慮した総合的なテストケース設計を支援する。

境界条件・エッジケースの観測。null/空/0/最大値/最小値/オーバーフロー/タイムゾーン等を網羅的にテスト。Use when: テスト設計、バリデーション実装、パーサー実装、日付/金額処理、例は通るが端で壊れる疑い、バグ修正後の再発防止。

pce-memory + shirushiを活用した知識検証・整合性チェックスキル。 以下の場合に使用: (1) 資料・ドキュメント間の矛盾チェック (2) 指示・意思決定の追跡と検証 (3) 作業途中のリアルタイム整合性チェック (4) 成果物と要件の照合検証 (5) shirushi Doc-IDとコードのトレーサビリティ検証 「チェックして」「整合性確認」「矛盾ない？」「検証して」「トレーサビリティ」等で起動。

Chrome DevTools MCPを使用したWebアプリのデバッグ支援スキル。ブラウザ操作、コンソールログ監視、ネットワークリクエスト分析、パフォーマンス計測を行う。 使用タイミング: (1) Webアプリの動作確認・デバッグ (2) UIの自動操作テスト (3) ネットワークエラーの調査 (4) コンソールエラーの確認 (5) パフォーマンス問題の診断 (6) フォーム入力の自動化 (7) スクリーンショット取得

Use when executing approved proposals. Only memory_cleanup and test_gap proposals can be executed. Other types should use create_ticket_from_proposal directly.

This skill should be used when the user asks to "collect Linear activity", "generate Linear report", "show my Linear issues", "what did I work on in Linear", or requests activity summaries from Linear for specific date ranges. Provides workflow for collecting issues, projects, and cycles via Linear MCP.

This skill should be used when the user asks to "lookup Amplitude user", "find user by device ID", "get user activity from Amplitude", or "search Amplitude user events". Queries Amplitude REST API for user data using Device ID or User ID.

Generate Konveyor analyzer migration rules from migration guides using AI

Comprehensive Rust development guidelines based on 6 months of code reviews. Use when writing Rust code, debugging Rust issues, or reviewing Rust PRs. Covers error handling, file I/O safety, type safety patterns, performance optimization, common footguns, and fundamental best practices. Perfect for both new and experienced Rust developers working on CLI tools, hooks, or production code.

Allow droids to interact with Outline Wiki via the outlinectl CLI (auth, collections, docs) with automation-friendly JSON output.

Manage remote Windows servers via WinRM, PowerShell remoting, and SSH. Use when user needs to execute commands on remote hosts or establish remote sessions.

Query and manage Active Directory: users, groups, computers, OUs, GPO status. Use when user asks about AD objects or domain information.

Success

Automatically generate plugin.yaml from Betty Framework registries

Automatically regenerate README.md from Betty Framework registries

Reconcile plugin.yaml with Betty Framework registries

Expert in parsing bank statement PDFs using Docling, handling duplicate transaction detection, and validating against bank summaries. Use when working with bank statement imports, transaction parsing, or financial data validation.

Enforces documentation standards and structure for this project. This skill should be used when creating, updating, or organizing documentation to ensure compliance with project rules, prevent redundancy, and maintain screen-based organization. Activates when user asks to create/update docs or when documentation needs to be generated.

Browser automation, testing, and debugging using Chrome DevTools. Use when users want to take screenshots, test websites, debug UI, inspect network requests, check console errors, or automate browser interactions.

PRIMARY tool for fetching library/framework documentation. PROACTIVELY use instead of WebFetch/WebSearch when user requests docs, API references, setup guides, or code examples for any programming library or framework. Use this skill immediately when detecting queries like "show me X docs", "how do I use Y", "get Z documentation", etc. Token-efficient alternative to MCP servers.

Fetch Google Calendar events. Use when checking schedule, finding meetings, or verifying calendar entries. Invoked by morning-metrics, win-the-day, and other scheduling skills.

Mermaid 플로우/시퀀스 다이어그램이 필요할 때

テストコードを書く・修正する前に必ず参照する。テスト作成・修正・レビュー・リファクタリング時に使用。

Baseline justfile commands - exact comment strings, all projects implement these

Batch upload local Markdown files to Notion via Python script. Optimized for single or multiple files with zero token cost. Direct script execution bypasses LLM parsing, saving significant tokens on large files while preserving formatting (tables, code blocks, rich text).

Manage blog categories including CRUD operations, slug generation, and category assignment. Use when working with categories, category forms, slugs, or organizing blog content by category.

Level 3 patterns - test-smart, deploy, migrate, logs, status (production systems)

Project documentation with MkDocs Material - consistent structure, API auto-generation, GitHub Pages deployment

Use when creating or editing agent definitions - ensures proper frontmatter, clear structure, validation of references, and no duplication with existing agents

Working in isolated worktree directories for parallel work - work normally, tests isolated, orchestrator handles cleanup

Track user journeys with intent context and friction signals. Use when instrumenting funnels or multi-step flows.

Configure source maps for readable stack traces. Use when setting up error tracking, debugging production issues, or configuring build tools.

Convert USD amounts to foreign currencies (EUR, PLN, AUD) using historical exchange rates. Use this skill when users ask to convert dollar amounts to other currencies for a specific date, or when they need historical currency exchange rates.