AI Skills Hub - Browse 180,000+ Agent Skills

Query Google Cloud Monitoring metrics using the cloud_metrics.py tool. Use when users ask about GCP metrics, Cloud Monitoring, Kubernetes metrics (CPU, memory, network), container resource usage, or need to export monitoring data. Triggers on requests like "show me CPU usage", "list available metrics", "describe this metric", "top memory consumers", or any Google Cloud Monitoring queries.

Process invoice emails: download PDF attachments, extract vendor + date, generate normalized filename, and send to Holded inbox via n8n webhook.

Orchestrates a full morning sweep of pending items (email, tasks, Slack, WhatsApp, X). Use when the user asks for a sweep, morning routine, inbox sweep, or all pending items.

Look up Unity API documentation from locally installed Unity docs AND package documentation (Cinemachine, Input System, etc.). Use when user asks to verify documentation or when uncertain about Unity API signatures, parameters, or Unity 6-specific features. Provides efficient access to ScriptReference, Manual, and package markdown docs without inflating context window.

Choose the appropriate protocol based on the task:

Use when building fintech apps. Keywords: fintech, trading, decimal, currency, financial, money, transaction, ledger, payment, exchange rate, precision, rounding, accounting, 金融, 交易系统, 货币, 支付

CRITICAL: Use for error handling. Triggers: Result, Option, Error, ?, unwrap, expect, panic, anyhow, thiserror, when to panic vs return Result, custom error, error propagation, 错误处理, Result 用法, 什么时候用 panic

Use when building CLI tools. Keywords: CLI, command line, terminal, clap, structopt, argument parsing, subcommand, interactive, TUI, ratatui, crossterm, indicatif, progress bar, colored output, shell completion, config file, environment variable, 命令行, 终端应用, 参数解析

Use when designing domain error handling. Keywords: domain error, error categorization, recovery strategy, retry, fallback, domain error hierarchy, user-facing vs internal errors, error code design, circuit breaker, graceful degradation, resilience, error context, backoff, retry with backoff, error recovery, transient vs permanent error, 领域错误, 错误分类, 恢复策略, 重试, 熔断器, 优雅降级

CRITICAL: Use for generics, traits, zero-cost abstraction. Triggers: E0277, E0308, E0599, generic, trait, impl, dyn, where, monomorphization, static dispatch, dynamic dispatch, impl Trait, trait bound not satisfied, 泛型, 特征, 零成本抽象, 单态化

Context-driven development methodology for organized, spec-first coding. Use when: - Project has a `conductor/` directory - User mentions specs, plans, tracks, or context-driven development - Files like `conductor/tracks.md`, `conductor/product.md`, `conductor/workflow.md` exist - User asks about project status, implementation progress, or track management - User wants to organize development work with TDD practices - User invokes `/conductor-*` commands (setup, newtrack, implement, status, revert, validate, block, skip, revise, archive, export, refresh) - User mentions documentation is outdated or wants to sync context with codebase changes Interoperable with Gemini CLI extension and Claude Code commands. Integrates with Beads for persistent task memory across sessions.

Use when (1) writing unit/integration/E2E tests, (2) reviewing generated tests before committing, (3) auditing existing test suites for quality, or (4) test coverage feels high but bugs still escape to production.

Use when validating stack YAML files - checks schema, references, and offers conversational fixes

Web Audio API crossfading and gapless playback techniques. Use when implementing audio transitions, crossfades between tracks, or working on gapless playback. Triggers on mentions of crossfade, gapless, audio transitions, or track switching.

Supabase Row-Level Security for multi-tenancy. Use when implementing database security, tenant isolation, or access control. Triggers on mentions of RLS, row-level security, multi-tenant, tenant isolation, or database policies.

Convert Markdown files to PDF with Japanese font support, MermaidJS diagram rendering, and automatic image embedding. Use when creating PDFs from markdown, documents with Japanese text, technical docs with Mermaid diagrams, or documents with images.

Use when writing CSS for Discourse core, themes, or plugins - handles BEM class naming, modifiers with double dashes, block__element structure, and is-/has- state prefixes

Conduct comprehensive deep research on any topic using Dify-powered workflow - searches documentation, academic papers, tutorials, APIs, best practices, and returns structured analysis with insights.

> **버전**: 2.1.0 > **생성일**: 2025-12-19 > **최종 수정**: 2025-12-24 > **역할**: 로컬 문서 ↔ Notion 동기화 (MCP 연동) > **변경 이력**: 네이밍 리팩토링 - Doc-Agent → Doc-Sync Skill

Expert knowledge for planning and architecting FilamentPHP 4.x applications. Covers resources, forms, tables, schemas, actions, notifications, widgets, authentication, tenancy, and best practices. Use this skill when designing FilamentPHP admin panels, planning feature implementation, or organizing application structure.

Use this skill when implementing automatic dialog confirmation or UI automation in SND macros using the YesAlready plugin. Covers plugin control, feature management, and temporary pausing.

Tracking document for SND plugin skills, repository references, and missing documentation. Use this to find official sources and prioritize skill creation.

Use this skill when implementing Grand Company delivery automation in SND macros using the Deliveroo plugin. Covers GC turn-ins, expert delivery, and supply provisioning.

Initialize a git repository with spec-kit and beads configuration.

Creates new skills from scratch. Generates complete skill packages with SKILL.md, organized directories, and validation. Use when building new capabilities, extending existing skills, or creating reusable skill templates for other projects.

查询并上传到 Google NotebookLM。创建新笔记本，上传本地文件（PDF/MD/TXT），添加 URL，粘贴文本内容。浏览器自动化支持持久身份验证。

Diagnose and fix swarm agent spawn failures when agents don't start processing tasks.

Analisa qualidade de dados e gera perfil estatístico. Usar ao explorar novos datasets ou validar dados.

Use when user EXPLICITLY requests "ESPHome", "ESP32", "ESP8266", or device firmware. NOT for: Home automations (use home-assistant or node-red skill).

Search for fitting svg icons and add them to the html

Diagnoses and fixes OneSignal push notification issues including subscription problems, missing tags, service worker errors, and notification delivery failures. Use when notifications don't work, subscriptions fail, or tags are missing.

Rust expert for rainze_core PyO3 module. Use when working on Rust code, performance-critical components, or Python-Rust FFI.

iNLighT Rental Manager PWA fejlesztési skill. Film equipment rental management alkalmazás (iNLighT Kft.). Használd amikor: projekt struktúra, komponensek, adatbázis műveletek, i18n, vagy bármilyen projekt-specifikus fejlesztés szükséges. Kétnyelvű (EN/HU), Supabase backend, React+TypeScript+shadcn/ui frontend.

ArduPilot communication libraries (GCS_MAVLink, AP_SerialManager, MAVLink routing, telemetry protocols). Use when: (1) Working on GCS_MAVLink or MAVLink message handling (2) Adding new MAVLink messages or MAV_CMD commands (3) Configuring serial ports or streaming rates (4) Implementing parameter, mission, or fence protocols (5) Working with FrSky, CRSF, MSP, or other telemetry (6) Setting up network communication (TCP/UDP MAVLink) (7) Debugging communication or routing issues

Expert guidance for developing with ArduPilot's multicopter/helicopter platform.

ArduPilot control libraries (AC_*, APM_Control, AR_*). Use when working with: attitude/position controllers, waypoint navigation, PID tuning, geofencing, obstacle avoidance, precision landing, auto-tuning, or vehicle-specific controllers (plane L1/TECS, rover steering, helicopter autorotation).

Transform GoHighLevel CRM webhook data into Triple Whale API format for /data-in/orders or /data-in/event endpoints. Use when sending GHL pipeline data to Triple Whale for attribution.

Consolidates deep research outputs from multiple AI models and sources into comprehensive, well-organized final reports. Use for synthesizing research from Claude, GPT, Gemini, Perplexity, web searches, and document analyses. Identifies conflicts, tracks source attribution, scores confidence levels, and highlights research gaps. Produces executive summaries with detailed supporting sections.

Debug specific document parsing failures

Patterns for spec health auditing, cleanup, and tech debt tracking.

Detect code-spec deviations and update specs to match implementation reality.

用于演示文稿（.pptx）的创建、编辑与分析。当 Claude 需要处理演示文稿时使用，包括：(1) 新建演示文稿，(2) 修改/编辑内容，(3) 处理版式布局，(4) 添加批注或演讲者备注，以及其他任何演示文稿任务。

用于创建高质量 MCP（Model Context Protocol）服务器的指南，使 LLM 能通过设计良好的工具与外部服务交互。构建用于集成外部 API/服务的 MCP server 时使用，不论是 Python（FastMCP）还是 Node/TypeScript（MCP SDK）。

用于 .docx 专业文档的创建、编辑与分析（支持修订、批注、格式保留与文本提取）。当 Claude 需要处理专业文档（.docx）时使用，包括：(1) 新建文档，(2) 修改/编辑内容，(3) 处理修订，(4) 添加批注，以及其他任何文档任务。

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Comprehensive observability skill for monitoring, logging, distributed tracing, alerting, and SLI/SLO implementation across distributed systems. Includes dashboard generation, alert rule creation, error budget calculation, and metrics analysis. Use when implementing monitoring stacks, designing alerting strategies, setting up distributed tracing, or defining SLO frameworks.

Comprehensive documentation automation with quality analysis, README generation, CHANGELOG management, API documentation formatting, and Mermaid diagram generation. Integrates with /update.docs command. Use for documentation audits, technical writing, API docs, README creation, diagram generation, and maintaining project documentation.

Comprehensive cross-platform mobile development skill for React Native, Flutter, and Expo. Includes project scaffolding, platform detection, app store validation, and CI/CD setup. Use when building mobile apps, selecting frameworks, validating releases, or setting up mobile development workflows.

Comprehensive legacy codebase analysis skill for technical debt assessment, security vulnerability scanning, performance bottleneck detection, and modernization roadmap generation. Includes 7 Python tools for automated codebase inventory, architecture health analysis, and strategic modernization planning.

Use when building a hook from a design, "implement this hook", "write the hook", "test my hook", or "TDD for hooks". For structure reference, see hook-development.

This skill provides structural reference for building skills in Claude Code plugins. Use for "skill file structure", "SKILL.md format", "progressive disclosure patterns", "organizing skill directories", or "skill anatomy". This is the WHERE and WHAT of skills. For HOW to test, see implementing-skills. For rigorous creation, see skillforge.

| ファイル | 役割 | 注意点 | |---------|------|--------| | `RatioKit/RatioKit.scss` | メインスタイルシート | ルートレベルとSharedStylesにコピー | | `RatioKit/RatioKitSimple.scss` | シンプル版スタイル | 同上 | | `RatioKit/React/src/components/RatioKit/StarterApp.tsx` | Reactスターターキット | `src/App.tsx`として配置 | | `RatioKit/Vue/src/components/RatioKit/StarterApp.vue` | Vueスターターキット | `src/App.vue`として配置 | | `RatioKit/Svelte/src/lib/RatioKit/StarterApp.svelte` | Svelteスターターキット | `src/App.svelte`として配置 | | 各プラットフォームの`main.ts`/`main.tsx` | エントリポイ...

Extract implementation stages from plans and create git worktrees for parallel development.

Lob API integration for physical mail delivery in Capsule Note. Use when implementing or debugging physical letter delivery features, address verification, or mail tracking.

Provides motion design guidance for UI components. Triggers on animation requests ("animate this", "add transition", "motion for"), refinement requests ("clean up this animation", "clean up the motion", "this feels too fast/slow", "make this feel more alive/natural"), and questions about easing, timing, or micro-interactions.

Guides creation of OpenGraph and Twitter share images using next/og ImageResponse. Covers layout patterns, custom fonts, avatars, title case, and Satori rules. Use when building OG images, Twitter cards, or social previews.

Runs the Ralph autonomous loop. Executes stories from prds/*.json using git worktrees.

音声販売AI(VLF)のMVP仕様編集。docs/配下の仕様ファイルを編集し、矛盾チェック、ADR記録、OpenQuestion管理を行う。

Analyzes a company's fundamental performance, growth drivers, and risks using verified financial data and text evidence. Use this when asked to research a stock's business model, revenue segments, or quarterly performance.

書籍の評判を多角的に調査し、構造化されたMarkdownレポートを生成する。ポジティブ・ネガティブ両面のレビューを収集し、国立国会図書館サーチ書影APIで表紙画像を取得する。ユーザーが書籍の評判調査、レビュー確認、購入前の評価確認を依頼した場合に使用する。技術書や一般書籍に対応。

Agent Skillsの活用事例を様々なソース（Zenn、GitHub、技術ブログなど）から調査・収集し、使用パターンを分析してまとめるスキル。ユーザーが「agent skillの事例を調べて」「agent skillの使い方を調査して」などと依頼した際に使用する。

Claude Code 작업이 완료되면 Slack으로 알림을 보내는 스킬입니다.

Convex actions for external API integration - fetch, third-party services, Node.js runtime, and error handling patterns

Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy

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

Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration), ImageMagick (image manipulation, format conversion, batch processing, effects, composition), and RMBG (AI-powered background removal). Use when converting media formats, encoding videos with specific codecs (H.264, H.265, VP9), resizing/cropping images, removing backgrounds from images, extracting audio from video, applying filters and effects, optimizing file sizes, creating streaming manifests (HLS/DASH), generating thumbnails, batch processing images, creating composite images, or implementing media processing pipelines. Supports 100+ formats, hardware acceleration (NVENC, QSV), and complex filtergraphs.

Systematic debugging framework ensuring root cause investigation before fixes. Includes four-phase debugging process, backward call stack tracing, multi-layer validation, and verification protocols. Use when encountering bugs, test failures, unexpected behavior, performance issues, or before claiming work complete. Prevents random fixes, masks over symptoms, and false completion claims.

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

访问公司内部 Confluence Wiki 文档。当用户提到 wiki.p1.cn、内部文档、公司Wiki、知识库，或需要搜索/查看公司内部文档时使用此 Skill。

Fetches Zig language and standard library documentation via CLI. Activates when needing Zig API details, std lib function signatures, or language reference content that isn't covered in zig-best-practices.

Full-context deep analysis for meeting prep, relationship analysis, or strategic planning. Pulls up to 180 memories across multiple dimensions for comprehensive synthesis. Use when "deep dive", "full context", "everything about", "strategic analysis", or when preparing for important meetings.

Creates Agentforce agents using Agent Script syntax with 100-point scoring. Use when building AI agents, defining topics and actions, or deploying AiAuthoringBundle (v65+) or GenAiPlannerBundle (v65+) metadata.

Generates and reviews Salesforce Apex code with 2025 best practices and 150-point scoring. Use when writing Apex classes, triggers, test classes, batch jobs, or reviewing existing Apex code for bulkification, security, and SOLID principles.

Creates and validates Salesforce flows with 110-point scoring and Winter '26 best practices. Use when building record-triggered flows, screen flows, autolaunched flows, scheduled flows, or reviewing existing flow performance.

One-stop save button for git workflows and version tracking. Auto-detects repo state, suggests .gitignore patterns, generates Conventional Commit messages, determines semantic version bumps, and executes commit+tag with final confirmation. Use when saving work, committing changes, or versioning releases.

CI/CDパイプラインの設計・実装・トラブルシューティング。GitHub Actions、GitLab CI、CircleCI、Jenkinsの設定ファイル作成、ビルド最適化、デプロイ戦略（Blue-Green、Canary、Rolling）の実装。「パイプライン」「CI/CD」「デプロイ」「ビルド」「自動化」に関する質問で使用。

LLMアプリケーションの設計・運用・評価・最適化。プロンプト管理、RAG構築、ファインチューニング、評価パイプライン、コスト最適化、本番運用。「LLM」「プロンプト」「RAG」「ファインチューニング」「AI運用」「評価」に関する質問で使用。

クラウドインフラ設計・IaC実装・監視設定・コンテナオーケストレーション。AWS、GCP、Azureのリソース構築、Terraform/Pulumi、Kubernetes、Docker、Prometheus/Grafana監視。「インフラ」「クラウド」「Terraform」「Kubernetes」「監視」「Docker」に関する質問で使用。

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.

Automate creation of complete CRUD entities (backend Laravel + frontend Vue) following Budget Manager project conventions. Use when the user asks to create a new entity, model, resource, or CRUD feature. Triggers on requests like "create a new category entity", "add a product model with CRUD", "generate an entity for transactions", or any request to scaffold a complete feature with database, API, and UI components.

This skill should be used when the user asks to "create a marketing report", "generate marketing analytics", "build a marketing dashboard", "create quarterly marketing insights", or needs help with visualizing marketing performance data.

Build and operate Inngest event-driven workflows (triggers, steps, retries, middleware) using our curated research notes.

Comprehensive DuckDB database backup toolkit supporting both file-based (cp) and native (ATTACH+COPY) backup approaches. Use when you need to backup DuckDB databases locally or to remote storage, create daily scheduled backups, verify backup integrity, or manage backup retention policies.

Use when addressing PR review feedback, after receiving review comments from CodeRabbit or human reviewers - ensures systematic responses to each comment thread with proper attribution and thread resolution.

Use when creating or modifying mocks and fixtures in `tests/conftest.py` - ensures all test infrastructure has proper docstrings and is registered in the mock registry.

Generate executable Python protocols for Opentrons Flex liquid handling robot. Takes experimental designs from hypothesis generation workflow and produces ready-to-run code with plate layouts, reagent calculations, and safety checks. Supports drug treatments, serial dilutions, plate washing, and assay additions. Outputs include Python protocol files, plate map visualizations, and reagent preparation guides.

Search and interact with Bluesky/ATProtocol via credential proxy

Clone GitHub repositories into Claude.ai Projects using git bundles via proxy server. Use when you need to work with git repositories from Claude.ai.

Generates formatted Catholic Penitential Act documents (.docx) from invocation text. Use when creating worship aids or Mass materials that need the Penitential Act (Form C - with tropes) formatted with proper liturgical styling (red rubrics, black text, Sabon Next LT font). Expects three Deacon invocations plus celebration info (Sunday ordinal with season, OR named feast) and Year (A/B/C). Optionally accepts custom priest opening and closing prayer texts.

This skill should be used when the user asks to "add a LiveView page", "create a form", "handle real-time updates", "broadcast changes to users", "add a new route", "create an API endpoint", "fix this LiveView bug", "why is mount called twice?", or mentions handle_event, handle_info, handle_params, mount, channels, controllers, components, assigns, sockets, or PubSub. Essential for avoiding duplicate queries in mount.

This skill should be used when the user asks to "add background processing", "cache this data", "run this async", "handle concurrent requests", "manage state across requests", "process jobs from a queue", "this GenServer is slow", or mentions GenServer, Supervisor, Agent, Task, Registry, DynamicSupervisor, handle_call, handle_cast, supervision trees, fault tolerance, "let it crash", or choosing between Broadway and Oban.

Apply Content Security Policy configuration to **VITE projects only** to prevent CSP errors during **localhost development**.

GitHub Actions 워크플로우 로그를 조회하고 분석합니다. "CI 로그 확인해줘", "워크플로우 실패 원인 분석해줘", "GitHub Actions 상태 알려줘", "빌드 로그 보여줘", "테스트 실패 로그 확인" 등을 요청할 때 활성화됩니다.

Update orbit-web package (includes orbit-core), rebuild the app, and upgrade the CLI. Use when syncing dependencies across the orbit stack.

Bitcoin inscription protocol and API helper for BRC-20, Runes, Ordinals, and UniSat API. Use when user asks to: (1) Generate deploy/mint/transfer inscription JSON, (2) Validate inscription format, (3) Explain inscription protocol differences, (4) Debug inscription encoding issues, (5) Query inscription data via UniSat API, (6) Build inscription transactions. Triggers on keywords: BRC-20, brc20, Runes, Ordinals, inscription, 铭文, deploy, mint, transfer, tick, UTXO, UniSat, indexer, API.

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

Create optimized Docker images for F# applications using multi-stage builds. Use when containerizing apps, optimizing image size, or fixing Docker issues. Ensures small, production-ready images with proper layer caching.

This skill should be used when you need to manipulate the AoT DAG (Work Graph) structure. Use it when decomposing Atoms into sub-tasks, resolving Atoms, managing AND/OR dependencies, performing backtracking on OR branches, or shrinking the DAG by replacing resolved Atoms with summaries in Bindings.