AI Skills Hub - Browse 180,000+ Agent Skills

Export query results to various formats (CSV, JSON, Excel, Markdown tables) with proper formatting and headers. Use when saving analysis results to files.

Use when sending Slack alerts or notifications. Automatically uses the configured SLACK_WEBHOOK_URL from environment.

論文PDFをページ単位で画像化・テキスト抽出・和訳し、メモに出力するスキル。さらに章ごとの要約と新規性分析も自動生成。ユーザーが「論文を翻訳して」「PDFをページごとに翻訳」「この論文を日本語にして」などと指示した時に使用。ClaudeCLIを使って各ページのテキストを和訳する。

Design, configure, launch, and analyze ablation sweeps for GRPO training. Use for hypothesis testing, hyperparameter experiments, and systematic comparisons.

プルリクエストのレビューコメントに体系的に対応するスキル。未解決コメントを取得し、問題を分析し、修正案を提案し、コメント単位でコミットを作成し、手動での返信とresolveをガイドします。GitHubのPRレビューに構造化された整理された対応が必要な場合に使用してください。

Analyze the WaveCap-SDR audio stream to assess tuning quality, detect silence, noise, proper audio, or distortion. Use when checking if SDR channels are properly configured or debugging audio issues.

Get real-time signal quality metrics (RSSI, SNR, S-meter) from WaveCap-SDR channels. Use when checking signal strength, monitoring reception quality, or debugging weak signals.

View and analyze WaveCap-SDR server logs, debug output, and error messages. Use when troubleshooting server issues, debugging API errors, monitoring SDR device status, or investigating capture/channel problems.

Automatisiert Pull-Request-Erstellung mit Branch-Management, Code-Formatierung und Integration mit professional-commit-workflow. Unterstützt GitHub CLI, automatische PR-Beschreibungen und projektspezifische Formatter (Biome, Black, Prettier).

Integrate RubyCritic to analyze Ruby code quality and maintain high standards throughout development. Use when working on Ruby projects to check code smells, complexity, and duplication. Triggers include creating/editing Ruby files, refactoring code, reviewing code quality, or when user requests code analysis or quality checks.

Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.

Expert in Freshdesk helpdesk API for building integrations, extracting support data, managing tickets/contacts/companies, and automating support workflows. Use when working with Freshdesk, building helpdesk integrations, analyzing support ticket data, or creating customer support applications.

Send messages and notifications to Poke (poke.com) via webhook API. Use when alerting the user, sending task completion notifications, status updates, reminders, or any message to their Poke assistant.

Optimize 3D Gaussian Splat scenes for real-time rendering on iOS, macOS, and visionOS. Use when working with .ply or .splat files, targeting mobile/Apple GPU performance, or needing LOD, pruning, or compression strategies for 3DGS scenes.

Go error handling patterns including wrapping, custom error types, errors.Is/As, and error conventions. Use when handling, creating, or checking errors in Go.

Go testing best practices including table-driven tests, race detection, test coverage, and mocking strategies. Use when writing or reviewing Go tests.

GraphQL resolver patterns including dataloader for N+1 prevention, context propagation, authorization, error handling, and validation. Use when implementing GraphQL resolvers.

Analyze Firefox bookmarks and tags directly from the places.sqlite database. Extract recent bookmarks, analyze tag popularity, find bookmark statistics, and explore bookmark metadata. Use when working with Firefox bookmarks, analyzing bookmark usage, organizing tags, or extracting bookmark data from Firefox profiles.

Analyze git repository changes, branch differences, and commit history. Use when analyzing branches, comparing changes, examining commit history, or preparing for PR/commit operations.

Dokploy 셀프호스팅 PaaS 플랫폼의 전체 관리 스킬. SSH 및 API를 통한 서버 관리, 애플리케이션 배포, Docker Compose/Swarm 관리, 데이터베이스(PostgreSQL, MySQL, MongoDB, Redis) 관리, Traefik 리버스 프록시 설정, SSL 인증서(Let's Encrypt, Cloudflare Origin CA), 도메인 설정, 볼륨 백업/복원, 컨테이너 모니터링, 서버 문제 해결 및 디버깅을 지원합니다.

개발자 업무 진행도 추적 및 자동화 (Supabase DB 기반). Use when (1) 할당된 이슈 진행 상황, (2) 현재 진행 상태 확인, (3) 워크플로우 단계 자동화.

Slack 채널에 메시지 전송 (공통 Skill). Use when (1) 이슈/태스크 알림, (2) 릴리스 알림, (3) /SEMO:slack 커맨드, (4) 팀원 멘션 요청.

이슈 업무 할당 및 작업량 자동 산정 (Supabase DB 기반). Use when (1) Issue assignee 지정, (2) 작업량(Point) 자동 계산, (3) 이슈 본문 체크리스트 추가, (4) 상태 업데이트, (5) Slack 담당자 알림.

중단된 워크플로우 재개. Use when (1) 일시정지된 워크플로우 계속, (2) 세션 복구 후 워크플로우 재시작, (3) 이전 진행 상황에서 계속.

SEMO 패키지를 외부 프로젝트에 배포. Use when (1) 새 프로젝트에 SEMO 설치, (2) 기존 프로젝트 SEMO 업데이트, (3) 브라운필드 프로젝트 SEMO 도입.

SEMO 패키지 소스와 .claude/ 동기화 자동화. Use when (1) Agent/Skill/Command 변경 후 동기화, (2) 서브모듈 업데이트 후 심볼릭 링크 동기화, (3) 버저닝 완료 후 배포 준비.

SEMO Skill 생성 가이드 및 자동화. Use when: (1) 새 Skill 생성 요청, (2) Skill 구조 초기화, (3) Skill 검증 필요, (4) Skill 패키징. Anthropic Skills 표준 기반.

SEMO 패키지 구조 및 Sub-Agent 최적화 규칙 검증. Use when (1) Agent/Skill 추가/수정/삭제 후 검증, (2) CLAUDE.md 업데이트 후 일관성 확인, (3) 버저닝 전 품질 게이트, (4) Sub-Agent 최적화 규칙 준수 감사.

Start tmux sessions, send prompts to the CLI, capture output, and verify behavior using helper scripts. Use when testing the CLI, interactive mode, TUI components, or when the user mentions tmux sessions.

Queries indexed repositories via Greptile API for codebase-aware answers. Use when asking natural language questions about code architecture, searching for implementations, understanding how features work, or locating specific code patterns across the repository.

Creates and configures Claude Code hooks for lifecycle automation. Use when implementing PreToolUse validation, PostToolUse formatting, PermissionRequest auto-approve, custom notifications, session management, or deterministic agent control.

Alchemy IaC patterns for deploying TanStack Start apps to Cloudflare Workers with D1 databases. Use when setting up new TanStack Start projects, configuring Alchemy deployments, working with D1/Drizzle migrations, local development with Cloudflare bindings, or deploying to custom domains.

Investigates HEC-HMS internals through decompiled Java classes. Provides JythonHms API reference, CLI options, version-specific differences (3.x vs 4.x), and guides on-demand decompilation for new discoveries. Use when debugging HMS behavior, discovering undocumented features, understanding version differences, validating automation approaches, or investigating HMS API capabilities. Includes complete JythonHms method reference, Python 2 vs 3 syntax differences, and decompilation tooling. Complements hms_doc_query (official docs) with internal implementation details. Trigger keywords: decompile, HMS internals, JythonHms API, HMS version differences, CLI options, undocumented, HMS jar, HMS classes, debugging HMS, HMS source code, HMS 3.x support, Python 2 vs 3, HMS methods, HMS parameters.

Build and deploy iOS app to connected iPhone via USB. Fast deployment (~8-10 seconds) for development iteration. Use when deploying, installing, or building apps to physical iPhone.

Start Android screen mirroring using scrcpy. Displays device screen in real-time on Mac with optional console logs. Use when viewing Android screen, mirroring device, or monitoring app with logs.

Testing strategy, test pyramid (70% unit/25% integration/5% E2E), PGlite patterns, Playwright best practices. Use when writing tests, debugging test failures, or when user mentions testing/test/spec/E2E.

Use when diagnosing openai_harmony.HarmonyError or gpt-oss tool calling issues with vLLM. Identifies error sources (vLLM server vs client), maps specific error messages to known GitHub issues, and provides configuration fixes for tool calling problems with gpt-oss models.

This skill generates comprehensive chapter content for intelligent textbooks after the book-chapter-generator skill has created the chapter structure. Use this skill when a chapter index.md file exists with title, summary, and concept list, and detailed educational content needs to be generated at the appropriate reading level with rich non-text elements including diagrams, infographics, and MicroSims. (project, gitignored)

Manage MCP servers on Windows. Add, remove, list MCPs with proper cmd /c wrapper. Handles both global (~/.claude.json) and project (.mcp.json) configs.

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.

Check which Claude skills are loaded globally and project-level. Displays loaded skills by category (Hostinger, Anthropic, custom), counts, and helps troubleshoot missing skills.

This skill should be used when the user reports OneDrive sync errors caused by Windows reserved filenames (NUL, CON, PRN, AUX, COM1-9, LPT1-9). It efficiently locates and removes these undeletable files using Git Bash.

Identifies and removes dead, unavailable, or error torrents from Real-Debrid account using the API. Shows torrent status, filters by health, and safely deletes torrents with missing files. Use this when Jellyfin scans are slow, when troubleshooting 404 errors, to clean account storage, or before major library refreshes.

Generate, edit, or transform images with Gemini Nano Banana using bundled Python scripts (Flash or Pro) including aspect ratio, resolution, image-to-image edits, logo overlays, and reference images. Use when users request image generation, image edits, image-to-image transformations, logo placement, or specific aspect ratios or resolutions.

Manage starmap data assets for Stapledons Voyage. Use when downloading star catalogs, galactic backgrounds, or processing astronomical data. (project)

Evolve and maintain game vision through Q&A interviews and decision tracking. Use when exploring game concepts, validating feature alignment, or making design decisions.

World of Darkness 20th Anniversary toolkit for Vampire (V20), Werewolf (W20), Mage (M20), Wraith (Wr20), Changeling (C20), Demon (D20). Creates characters, locations, items, organizations, weapons. Triggers: WoD, Vampire, Kindred, clan, ghoul, Garou, tribe, Gift, caern, Tradition, Technocracy, Sphere, rote, Arcanoi, Kithain, Art, spirit, Umbra, crossover, weapon stats, firearm, melee, ranged, Demon, Fallen, House, Lore, evocation, Earthbound, thrall, pact, apocalyptic form, Faith, Torment.

Automated versioning, changelog generation, and git tagging using release.sh script with semantic versioning and conventional commits

总结 YouTube 视频内容，提取关键信息、时间线和核心观点。当用户提供 YouTube 链接、视频 URL 或要求总结视频内容、提取视频要点时使用。支持结构化摘要、时间戳笔记等多种输出格式。

校准和修正 AI 自动转录生成的字幕文本，包括专业术语校正、断句优化、格式统一和口语化内容润色。当用户提供 SRT/VTT 字幕文件、转录文本，或要求修正字幕错误、优化字幕可读性、统一术语表达时使用。

YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video

使用 Pake 将任意网页打包成轻量级桌面应用程序（macOS/Windows/Linux）。当用户需要将网站变成桌面 App、创建 Web App 桌面版、打包网页应用、或提及 Pake 时使用。

Process D&D session videos through the complete chunking pipeline. Use when the user requests to process, chunk, transcribe, or analyze a D&D session video file.

Convert colors between formats (HEX, RGB, HSL, CMYK, LAB, LCH, oklch, ANSI), generate color harmonies (complementary, triadic, analogous), check accessibility (WCAG contrast), and simulate color blindness. Use when working with colors, design systems, CSS themes.

Store ClickHouse Cloud credentials in Doppler + 1Password for gapless-crypto-clickhouse. Use when setting up new services, rotating credentials, or backing up authentication material. Covers API keys, connection details, and database password storage.

Test and validate ClickHouse Cloud connection using clickhouse-connect for gapless-crypto-clickhouse. Use when validating connectivity, troubleshooting connection issues, or verifying environment configuration. Includes version check and query validation.

Write and create Typst documents (.typ files). Use when the user asks to create, write, edit, or convert documents to Typst format, write Typst markup, create academic papers, reports, or documents in Typst, convert LaTeX to Typst, or work with .typ files. Typst is a modern markup-based typesetting system alternative to LaTeX.

Fetch ClickHouse Cloud service details from API (organization ID, service endpoints, configuration). Use when setting up new ClickHouse Cloud services, discovering endpoints, or validating service metadata for gapless-crypto-clickhouse project.

This skill should be used when analyzing chess positions. Automatically triggers when users provide FEN positions for analysis or ask about specific chess positions. Provides engine-powered analysis with natural language explanations of best moves, key variations, and strategic/tactical themes.

Show project status and deployment information

Steal existing skills, commands, and agents from GitHub repositories. Use when the user wants to copy/import valid OpenCode resources from external GitHub repos. Only works with existing resources (does not convert arbitrary repos).

Automates end-to-end testing and debugging of terminal UIs using Termwright. Use when testing TUI apps (ratatui, crossterm, ncurses), automating terminal interactions, capturing screenshots, or debugging terminal-based interfaces. Handles step files, daemon control, and artifact analysis.

WHAT: Command line tool for Atlassian Jira. WHEN: managing issues, adding comments, viewing tickets, sprint workflows. KEYWORDS: jira, ticket, issue, sprint, comment, cli, atlassian, backlog, story, epic.

Claude Code hooks configuration reference. Use when creating hooks, understanding hook events (PreToolUse, PostToolUse, Stop, SessionStart, etc.), debugging hook behavior, or implementing automation.

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.

Use for code quality and engineering standards. Covers code style conventions, conventional commit messages, documentation standards (ADRs, API docs, changelogs), and security patterns (input validation, secrets management, OWASP). Activate for code review, commit preparation, documentation writing, or security considerations.

Search past reasoning for relevant decisions and approaches

Deterministic router for math cognitive stack - maps user intent to exact CLI commands

Research-to-implement pipeline chaining 5 MCP tools with graceful degradation

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

Unit-aware computation with Pint - convert units, dimensional analysis, unit arithmetic

Parallel Agent Type Contracts

Graceful Degradation with Helpful Messages

Onboard company employees (Claude Code CLI users) to use gapless-crypto-clickhouse package with ClickHouse Cloud credentials. Use when company employee needs to set up ClickHouse Cloud access, mentions first-time setup, credential configuration, connection testing, or troubleshooting ClickHouse Cloud connections.

Create, edit, and manipulate Obsidian Canvas (.canvas) files. Use this skill when the user wants to visualize concepts, build flowcharts, or organize information spatially using the JSON Canvas format.

Comprehensive validation skill for Claude Code plugins, marketplaces, hooks, skills, and MCP servers. Use this skill when examining, debugging, or validating any Claude Code plugin component.

Duration and timing tokens from industry standards. Use when selecting animation duration, converting between milliseconds and frames, or comparing timing across design systems. References W3C DTCG, M3, Fluent, and Carbon specifications.

Implements core RDAP client functionality following RFC 7480 standards with TypeScript strict mode

在任意仓库中按 CSV TODO 清单闭环逐条处理：每条 todo 仅允许一次 `codebase-retrieval`（MCP/LSP）索引后再改代码；每条 todo 必须按项目文档指定的构建命令构建成功再 `git commit`；提交后回写 CSV 的 `status/notes/evidence/commit` 并继续下一条。启动时自动读取 `{repo_root}/AGENTS.md`（优先）或 `{repo_root}/CLAUDE.md` 作为项目规则输入上下文。

Claude Code用のスキルを作成・設計するためのガイド。Anthropic公式skill-creatorをベースに最適化。スキル作成、skill作成、新しいスキル、SKILL.md、スキル設計、スキルの書き方の時に使用。

GAS Webアプリ開発スキル（HIG準拠版）。 Use when: GASでWebアプリを作成、doGet、スプレッドシート連携Webアプリ、HIG準拠、GASウェブアプリ、gas-webapp、Apps Script Webアプリ、Googleサービス連携、Gemini API連携の時。

YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video

モバイルアプリUI/UXデザインの包括的原則と品質基準を提供します。タイポグラフィ、レイアウト、色彩設計、ダークモード、アクセシビリティについてアドバイスが必要な場合に使用してください。デザインレビュー、UIの改善提案、「ダサい」デザインの修正時に活用します。

Hasura DDN v3 supergraph 開發完整工作流程指南。使用此 skill 當： - 需要配置 AuthConfig（webhook/JWT/noAuth 認證） - 新增或管理 Models、Commands、Relationships - Introspect OpenAPI 或 MySQL connectors - 建置和部署 supergraph - 解決 HML metadata 錯誤

Guide for creating specialized AI agents (subagents). Use when users want to create a new agent, define agent configurations, or need guidance on agent architecture. Triggers: "create an agent", "new agent", "make a subagent", "agent template"

Analyzes legacy PL/I (Programming Language One) programs to assist with migration to modern Java applications. Extracts business logic, data structures, procedure definitions, and file operations from PL/I code. Generates migration reports and creates Java implementation strategies. Use when working with mainframe migration, PL/I analysis, legacy system modernization, or when users mention PL/I to Java conversion, analyzing .pli/.PLI/.pl1 files, working with PL/I procedures, or planning Java service implementations from PL/I programs.

Database + Alembic workflow for Slack-MM2 Sync (migrations, collapsed history, NEVER CANCEL guidance, and troubleshooting queries). Use when changing schema, debugging DB state, or dealing with migration failures.

Transform YouTube videos into magazine-style ebook articles

Debug running Python processes using Python 3.14+ sys.remote_exec(). Inject debugging scripts to get stack traces from stuck processes, including gevent-based Celery workers with greenlet introspection.

Generate a paper digest (Markdown) and extract reference entries (structured JSON array) from a MinerU-produced paper Markdown file. Use when invoked as $literature-digest with a prompt-embedded JSON payload containing md_path.

Manage data population and synchronization for ASIC short data and stock prices. Use when populating the database, syncing data, or troubleshooting data issues.

Web scraping and Markdown conversion toolkit for extracting web content with images. Use when Claude needs to: (1) Save web articles/blogs as Markdown files, (2) Export WeChat articles (mp.weixin.qq.com), (3) Batch crawl Wiki sites and merge into single document, (4) Download webpage images locally, (5) Convert HTML tables/code blocks to Markdown format.

Accurate, low-token guidance for the Jujutsu (jj) version control system: CLI commands/flags, revsets, bookmarks, conflicts, config, and Git interop. Use when a request mentions Jujutsu, `jj`, revsets, bookmarks, `jj git`, `jj rebase`, `jj undo`, or interpreting `jj` output.

Vitest を使用したテストコード作成・リファクタリング・デバッグ。ユニットテスト(.unit.test.ts)、Reactコンポーネント・Hooksテスト(.browser.test.tsx)、APIハンドラテストに対応。「テストを書いて」「テストケースを追加して」「テストをリファクタリングして」「テストコードを整理して」「このテストをガイドラインに沿って修正して」などのリクエストで使用。.test.ts/.test.tsx ファイルの作成・編集・改善が必要な場合に活用。

Set up IEEE Std 830-1998 and US ISO/IEC 25051 compliant project context files so downstream SRS skills can operate with stakeholder data, quality criteria, and definitions.

搜索 Twitter (X) 上的推文。

Fetch web documentation and convert to clean Markdown using readability + turndown. Use when: need to download documentation from web URLs as markdown files. Perfect for API docs, tutorials, technical articles.

Diagnose and fix common MobileAgent issues including ADB connection problems, Unicode input failures, MCP tool errors, and device communication issues. Use when user reports errors or automation is not working.

Social media and dating app operations including like, comment, share, send message, follow, and swipe matching. Supports LINE, Facebook, Instagram, Threads, WeChat, X, Telegram, YouTube, Gmail, and dating apps (Tantan, Tinder, Bumble, etc). Adapts to different UI languages and version differences.

Reset all PULSE features, progress, and lessons to clean state. Requires CONFIRM to proceed.