DifyのWorkflow/Chatflow YAMLから、ハンズオン用にLLMノードのプロンプトとコードノードのコードを抽出し、Markdown/TXTに整形して保存します。YAMLファイルからLLMノードのプロンプトとコードノードのコードを抽出し、Markdown/TXT形式で整形して保存します。抽出スクリプト(extract_prompts_and_code.py)を使用してYAMLからLLM/コードノードを抽出し、指定された出力形式(MD/TXT)で指定ディレクトリに保存します。ハンズオンやドキュメント作成時に必要なプロンプトとコードを効率的に取得し、再利用可能な形式で提供します。
Dify上のフローをAPI経由で直接編集します。YAMLファイルを変更せずに、環境変数の更新、ノード/エッジのパッチ適用、部分的なグラフ更新が可能です。運用中のフローの軽微な修正に使用します。「API編集」「直接編集」「パッチ」「環境変数更新」などの依頼時に使用します。
Difyインポート時・実行テスト時に発生したシステムエラーを分析し、scripts/dify_validation.pyに新しい検出ルールを追加します。「インポートエラー」「実行時エラー」「バリデーション強化」「検証ルール追加」などの依頼時に使用します。
作成したDifyフロー(Workflow/Chatflow/Trigger)を分解・汎用化し、再利用可能なテンプレートとしてdify/templates/に保存します。機密情報除去・変数汎用化・メタデータ付与を行い、チーム内での再利用性を高めます。「テンプレート化」「パターン化」「汎用化」「再利用」などの依頼時に使用します。
Post content to WeChat Official Account (微信公众号). Supports both article posting (文章) and image-text posting (图文).
Send WhatsApp messages via Kapso Meta proxy or the whatsapp-cloud-api-js library, and manage WhatsApp templates (create/update/submit/status/send) with media uploads.
Manage WhatsApp Flows via Kapso Platform API: list/create/update/publish flows, manage flow versions, attach data endpoints, and check encryption. Use Meta proxy only for send-test and delete operations.
审查 Bitbucket Pull Request,分析代码变更并发布审查评论。
Terraform CLI でインフラストラクチャを管理する。IaC タスク時に使用。
连接并操作PITA数据库。当用户需要搜索、导入、更新或删除数据时使用此skill。支持自然语言查询、智能数据导入、实体管理、文件上传等操作。用户需在.env文件中配置KB_ACCESS_TOKEN。
Run CRISPResso2 analysis for CRISPR genome editing experiments using Docker. Use this skill when analyzing CRISPR editing outcomes, quantifying indels, evaluating HDR efficiency, or processing base/prime editing data from amplicon sequencing.
此技能用于从图片或PDF中提取文字。当用户需要OCR识别图像内容(截图、照片、扫描件、 发票、表单等)或从图片URL中读取文本时触发。不适用于纯文本文件或代码文件。
"/dev.state", "dev.state", "PR 상태", "상태 변경", "queue", "pause", "continue", "status", "list" PR 상태 관리 통합 스킬 - 대기열 추가, 중단, 재개, 상태 조회, 목록 확인
Checks if code is ready for a pull request by running type checks, linting, tests, and code quality review for Node.js/TypeScript and Python projects. Use when preparing code for a PR, running pre-commit validation, or when the user asks to check code quality, run linters, run tests, or verify PR readiness.
Use when modifying Emacs config files - ensures you edit .org source files not generated .el files, and properly tangle changes
Generate diagrams (state machines, class diagrams) from natural language requirements using Umple. Use when user requests: (1) State machine diagrams (2) UML class diagrams (3) Diagram generation from text descriptions, (4) Any mention of Umple diagram generation, (5) Visual representation of states, transitions, events, classes, or relationships. Outputs SVG diagrams with organized folder structure.
Git operations with conventional commits. Use for staging, committing, pushing, PRs, merges. Auto-splits commits by type/scope. Security scans for secrets.
協助建立或修改 GitHub Pull Request。根據當前分支的 commits 自動產生繁體中文 PR 標題與描述。適用於「建立 PR」、「create pull request」、「幫我開 PR」、「修改 PR 內容」等請求。使用 GitHub CLI (gh) 執行 PR 操作。
Design new agent skills using the 10-step Skill Design Loop (SDL). Use when creating reusable, portable agent capabilities with progressive disclosure, VOI-driven uncertainty management, and security hardening.
Create and validate Mermaid diagrams in markdown files
Create and validate Mermaid diagrams in markdown files
LLM이 잘 설계된 도구를 통해 외부 서비스와 상호작용할 수 있게 하는 고품질 MCP (Model Context Protocol) 서버 생성 가이드입니다. Python (FastMCP) 또는 Node/TypeScript (MCP SDK)로 외부 API나 서비스를 통합하기 위해 MCP 서버를 구축할 때 사용하세요.
Customize the Shadcn design system (Tailwind v4 supported). Update design tokens, safe refactoring, and color management.
Monitor network health across all layers (ISP, modem, router, DNS, latency). Use for network diagnostics, status dashboards, outage detection, and troubleshooting connectivity issues. Provides JSON output suitable for dashboards and alerting.
PageRangers SEO API integration for AI assistants. TRIGGER when user mentions PageRangers, SEO keywords, search rankings, SERP analysis, or keyword research. Provides keyword analysis, ranking data, KPIs, and keyword opportunities via the PageRangers Monitoring API. Requires python3. Works with Claude Code and Codex CLI.
Runbook SchedulerService (start/stop/reschedule) avec APScheduler, détection Gunicorn vs flask run et healthchecks.
Guide pour maintenir PostgresStore (migrations, bascule JsonStore, validation pool psycopg) et scripts Neon.
Monday.com project management integration. Create, read, update, and delete boards, items, and task data. Use when working with Monday.com tasks, dashboards, automations, or syncing project data.
前后端字段统一管理与追踪系统。用于记录和追踪前后端字段的增删改操作,确保字段定义的一致性。触发场景:涉及字段操作、API开发、数据模型设计、前后端对接、类型定义、数据库schema变更时使用。
Discover and inventory API endpoints across Java, .NET, Node.js, and Python frameworks for QA automation. Use when you need to identify REST endpoints in a codebase, extract HTTP methods and paths, detect authentication requirements, build an endpoint inventory for test planning, analyze API surface for test coverage, or support QA MVP Step 1. Supports Spring Boot, JAX-RS, ASP.NET Core, Express, NestJS, FastAPI, Flask, and Django REST Framework.
Diagnose and triage API test failures from Newman/Postman runs. Use when you need to analyze test failures, classify failure types, identify root causes, suggest remediation steps, create failure reports, prioritize fixes, debug flaky tests, or support QA MVP Step 8. Covers HTTP error classification, assertion failure analysis, timeout diagnosis, and actionable remediation patterns.
创建和管理技能(元技能),支持新建技能、扫描校验、同步索引。 **触发词**:新建skill、技能模板、SKILL.md结构、添加技能、创建技能、更新skills、同步skills、扫描skills、刷新索引、sync skills **使用场景**:新建技能文档、从社区复制技能后同步索引
Enables agents to communicate with Agent Zero instances via A2A protocol. Use when connecting to remote Agent Zero agents, sending messages with file attachments, managing multi-turn conversations, or coordinating multi-agent workflows. Supports FastA2A v0.2+ protocol with automatic context management, file attachments, and comprehensive error handling.
Swing detection and strike filtration specialist for NIFTY options
Tag-based upstream sync for a fork/secondary-development repo: fetch tags, let the user choose a tag, create a fresh branch from that tag, then read the old customization branch’s git changes + intent Markdown to re-implement the requirements on the new branch (no merge/rebase of the old branch).
Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction. NOT when only fetching static content (use curl/wget instead).
Implement SEO meta tags: title, description, Open Graph, Twitter Cards, canonical URLs, viewport. Auto-validates via PostToolUse hook. Use when adding or fixing meta tags, implementing social sharing, or setting up head management. Supports Astro, Vite, TanStack Start, Next.js.
Comprehensive OpenCode SDK integration toolkit for client creation, session management, file operations, authentication, and real-time events. Use when Claude needs to build integrations with OpenCode server, generate SDK code, create automation scripts, or implement any functionality using the @opencode-ai/sdk package. Includes code generators, API reference, templates, and examples for all SDK workflows.
Production-grade implementation of Better-Auth with Neon Postgres and Drizzle ORM. This skill should be used when implementing secure signup, login, session management, and role-based access control for the Physical AI & Robotics platform.
Automate macOS operations including keyboard/mouse simulation, screenshot and OCR, system notifications, iMessage, Reminders, desktop organization, and media control. Use when performing any macOS automation task such as sending keystrokes to applications, capturing and reading screen content, controlling music playback, organizing desktop files and icons, sending iMessages, or creating reminders.
Configure DigitalOcean Managed Postgres with bindable variables or schema isolation. Use when setting up databases, creating users, managing permissions, configuring multi-tenant schemas, or troubleshooting database connectivity on App Platform.
Analyze IFC building models for CO2 emissions. Parses IFC files, classifies materials, calculates embodied carbon using Dutch NIBE database, and generates PDF reports.
Manage OmniFocus tasks via JavaScript for Automation (JXA) scripts. Use when the user asks Clawdbot to interact with OmniFocus, including - (1) Adding tasks to inbox, (2) Listing or searching tasks (inbox, available, flagged, overdue, due soon), (3) Completing tasks, (4) Updating task properties (notes, due dates, flags), (5) Getting OmniFocus statistics, (6) Reporting on task status, or (7) Acting on tasks in OmniFocus based on user queries.
Endpoints document management API toolkit. Scan documents with AI extraction and organize structured data into categorized endpoints. Use when the user asks to: scan a document, upload a file, list endpoints, inspect endpoint data, check usage stats, create or delete endpoints, get file URLs, or manage document metadata. Requires ENDPOINTS_API_KEY from endpoints.work dashboard.
Control Home Assistant smart home devices, run automations, and receive webhook events. Use when controlling lights, switches, climate, scenes, scripts, or any HA entity. Supports bidirectional communication via REST API (outbound) and webhooks (inbound triggers from HA automations).
交易/持仓的策略分析与可执行动作输出(保命优先)。优先复用本仓库产物(outputs/run_*/report.md、holdings_user.json、rebalance_user.json、signals*.json、cash_signal.json、opportunity_score.json 等),把“看起来不错”落成“怎么做/什么时候错/错了怎么办”。
This skill provides comprehensive administration, optimization, and troubleshooting workflows for Orange Pi Zero 2W running Ubuntu 24.04. Focuses on SD card longevity through write-reduction strategies, system performance optimization, thermal management, and common administrative tasks specific to ARM-based SBCs. Use when administering, optimizing, troubleshooting, or maintaining an Orange Pi Zero 2W system.
Control Home Assistant smart home devices, run automations, and receive webhook events. Use when controlling lights, switches, climate, scenes, scripts, or any HA entity. Supports bidirectional communication via REST API (outbound) and webhooks (inbound triggers from HA automations).
A universal PDF conversion toolkit. Converts PDF documents to Word (.docx), Excel (.xlsx), or PowerPoint (.pptx). Handles single files or batch processing.
Reviews translation quality, consistency, terminology, and style. Use when checking translations, reviewing UI text, verifying translation guidelines, or ensuring consistent terminology across languages.
智能布线连接:支持smart_route自动寻路、c_route/l_route手动布线、straight_route直连等多种布线方式,用于连接器件端口。
为通用 AI 助手安装技能。当用户请求列出可用技能、从 Git 仓库(GitHub/GitLab/Gitea)或本地目录安装技能到特定 AI 助手(Codex、Roo、Claude、Copilot、Cursor 等)的指定作用域时使用此技能。
管理 ROADMAP.md 中的任务生命周期的技能。支持开始任务、完成任务和更新子任务进度三种操作。当用户需要更新项目路线图中的任务状态时使用此技能。支持自然语言指令解析、命令行和交互模式,保持格式一致性。
Generate diagrams from Mermaid syntax. Uses a markdown-based flow, defaults to PNG, and requires double-quoted labels.
Delegate browser automation tasks to a subagent to keep main context clean. Use this skill when you need to perform browser interactions (navigate, click, type, screenshot, etc.) without bloating the main agent's context window.
Fix Dependabot security vulnerabilities in Java/Gradle projects using severity-based processing, dependency substitution strategies, and dependency graph verification. Use when Dependabot alerts need resolution with proper CI validation.
Write and review XML API documentation for SkiaSharp following .NET guidelines. Use when user asks to document a class, add XML docs, write XML documentation, add triple-slash comments, review documentation quality, check docs for errors, fix doc issues, fill in missing docs, remove "To be added" placeholders, or mentions API documentation.
Build Apache Cordova applications into Android APK packages. Use when working with Cordova projects and need to (1) Build debug APK for testing, (2) Build release APK for distribution, (3) Package the app for Android devices, (4) Sign APKs for Google Play Store, or (5) Troubleshoot build issues. Triggers on requests like "build Android APK", "package Cordova app", "create APK", or "build for Android".
Applies TDD approach to skill documentation with pressure testing. Use when creating new skills, editing existing skills, or verifying skills work.
Manage OmniFocus tasks via JavaScript for Automation (JXA) scripts. Use when the user asks Clawdbot to interact with OmniFocus, including - (1) Adding tasks to inbox, (2) Listing or searching tasks (inbox, available, flagged, overdue, due soon), (3) Completing tasks, (4) Updating task properties (notes, due dates, flags), (5) Getting OmniFocus statistics, (6) Reporting on task status, or (7) Acting on tasks in OmniFocus based on user queries.
Control Home Assistant smart home devices, run automations, and receive webhook events. Use when controlling lights, switches, climate, scenes, scripts, or any HA entity. Supports bidirectional communication via REST API (outbound) and webhooks (inbound triggers from HA automations).
Use the Fly.io flyctl CLI for deploying and operating apps on Fly.io: deploys (local or remote builder), viewing status/logs, SSH/console, secrets/config, scaling, machines, volumes, and Fly Postgres (create/attach/manage databases). Use when asked to deploy to Fly.io, debug fly deploy/build/runtime failures, set up GitHub Actions deploys/previews, or safely manage Fly apps and Postgres.
You are an expert on Clawdbot documentation. Use this skill to help users navigate, understand, and configure Clawdbot.
Playwright MCPを使用したE2Eテスト・動作確認を実行する。「E2Eテスト」「動作確認」「ブラウザテスト」「画面テスト」と依頼された場合、または /develop-feature の Phase 3.2 から呼び出される場合に使用。
Control Home Assistant smart home devices, run automations, and receive webhook events. Use when controlling lights, switches, climate, scenes, scripts, or any HA entity. Supports bidirectional communication via REST API (outbound) and webhooks (inbound triggers from HA automations).
Monitor AirGradient air quality devices via the local API.
Interact with the Endpoints API to manage document endpoints, scan files, retrieve extracted data, and access persistent memory (cc-ram/cc-drive). Use for listing endpoints, scanning documents, managing memory, and checking usage stats.
Systematic debugging workflow for Next.js/React applications. Use when investigating bugs, troubleshooting issues, or diagnosing unexpected behavior. Covers isolation techniques, debugging tools, and regression prevention with tests.
Control IKEA Dirigera smart home devices (lights, outlets, scenes, controllers). Use when the user asks to control smart home devices, check device status, turn lights on/off, adjust brightness/color, control outlets, trigger scenes, check battery levels, or work with IKEA smart home automation. Accessible via Cloudflare tunnel on VPS.
Track flights in real-time with detailed status, gate info, delays, and live position. Use when user asks to track a flight, check flight status, look up flight information by flight number (e.g., "track AA100", "what's the status of United 2402", "check my flight BA123"), or wants to display flight data in a formatted view similar to Flighty app.
Control AdGuard Home DNS filtering via HTTP API. Use when managing blocklists/allowlists, checking domain filtering status, toggling protection, or clearing DNS cache. Supports blocking/allowing domains, viewing statistics, and protecting/disabling DNS filtering.
Endpoints document management API toolkit. Scan documents with AI extraction and organize structured data into categorized endpoints. Use when the user asks to: scan a document, upload a file, list endpoints, inspect endpoint data, check usage stats, create or delete endpoints, get file URLs, or manage document metadata. Requires ENDPOINTS_API_KEY from endpoints.work dashboard.
Search the web using SearXNG. Use when you need current information, research topics, find documentation, verify facts, or look up anything beyond your knowledge. Returns ranked results with titles, URLs, and content snippets.
Host static files on subdomains with optional authentication. Use when you need to serve HTML, images, CSS, JS, or any static content on a dedicated subdomain. Supports file upload, basic auth, quota management, and automatic SSL via Caddy. Commands include sf sites (create/list/delete), sf upload (files/directories), sf files (list/delete).
Security scanner for Moltbot skills. Audits skills for security vulnerabilities, prompt injection, data exfiltration, obfuscation, and other threats before installation. Use when installing a new skill, asked to scan/audit a skill, or asked to check a skill's safety. Triggers automatically on skill install requests.
将文章内容拆解为小红书风格的系列配图。支持从 URL、文件或文本生成封面图、内容图和结尾图,自动创建提示词并调用图片生成工具。
Research-driven quality heuristics for plugin validation. Use when: validation, quality gates, heuristics, remediation, quality metrics, validation loops, "quality check", "validate plugin". Supports: structure validation, schema validation, progressive disclosure.
Expert guidance for creating Claude Code hooks and lifecycle automation. Use when: hooks, event hooks, PreToolUse, PostToolUse, exit codes, hook scripts, lifecycle events, validation hooks, "create hook", "add hook", hook configuration, hooks.json, Stop hook, SessionStart. Supports: all 12 event types, command hooks, prompt hooks, exit codes.
Send and receive SMS/RCS via Google Messages web interface (messages.google.com). Use when asked to "send a text", "check texts", "SMS", "text message", "Google Messages", or forward incoming texts to other channels.
Audits and implements Didit.me API v3 verifications, decisions, and webhooks. Handles orchestration and standalone flows.
Diagnoses RAG pipeline failures in WaTaxDesk. This skill should be used when debugging why queries fail, analyzing test results, tracing retrieval issues, or identifying missing knowledge base documents.
Audit an iOS app repo (Swift/Xcode or React Native/Expo) for App Store compliance and release readiness; output a pass/warn/fail report and publish checklist.
This skill should be used when the user asks to "test on iOS simulator", "run app on iPhone", "take iOS screenshot", "tap button in simulator", "automate iOS UI", "install app on simulator", "boot simulator", or when working with iOS apps, Xcode, Simulator, simctl, idb, UI automation, or iOS testing. It automates iOS Simulator workflows including device lifecycle (create/boot/erase), app management (install/launch), push notifications, privacy grants, screenshots, and accessibility-based UI navigation.
Monitor SEC EDGAR for new filings and get Telegram/Slack summaries via Clawdbot. Use when setting up SEC filing alerts, adding/removing tickers to monitor, configuring form types, starting/stopping the watcher, or troubleshooting filing notifications.
1) Start the API server:
Epic completion review - verifies all epic tasks implement spec requirements. Triggers on /flow-next:epic-review.
Use when the user wants to customize Gemini CLI behavior using hooks (events, blockers, loggers).
Cache and reuse code from prior AI agent executions via Raysurfer. Search before coding, upload after success.
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.
This skill provides patterns and templates for NestJS 11.x with Fastify, Prisma ORM, and TypeScript 5.x development. It should be activated when creating NestJS modules, controllers, services, DTOs, guards, interceptors, or tests.
This skill provides patterns and templates for Java 21 Spring Boot 3.5.x WebFlux REST API development. It should be activated when creating controllers, services, repositories, DTOs, or reactive tests.
This skill should be used for browser automation tasks including website testing, UX validation, responsive design checks, or any Playwright-based automation.
This skill provides patterns and templates for building production AI agents with Python 3.13, LangChain v1.2.8, LangGraph v1.0.7, and FastAPI 0.128.x. Use when creating AI agents, RAG systems, graph workflows, tools, memory systems, or agent tests.
This skill should be used when starting a new project or brand and needing to find a registrable domain. It brainstorms creative domain names and checks real availability via DNS/WHOIS.
Build production-ready web scrapers using Crawlee and Playwright. This skill guides you through analyzing websites, identifying selectors, and generating crawler code that follows best practices. Use when: - User wants to "scrape a website", "extract data from a page", or "build a crawler" - User provides a URL and asks to extract product/deal/content information - User needs help finding CSS selectors for web elements - User wants to create an Apify actor for data extraction - User asks about "web scraping", "DOM analysis", or "Playwright selectors" Triggers: "scrape", "crawler", "extract from website", "web scraping", "find selectors", "Apify actor", "Playwright", "Crawlee"
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.
> Backend skill wrapping `npx convex` CLI. Routes to workflows for specific operations.
Cache and reuse code from prior AI agent executions. Search before coding, upload after success.
macOS-only AppleScript control for the ChatGPT Atlas desktop app. Use only when the user explicitly asks to control Atlas tabs/bookmarks/history on macOS and the "ChatGPT Atlas" app is installed; do not trigger for general browser tasks or non-macOS environments.
Use for cryptocurrency price analysis, technical indicators, support/resistance levels, and price trend assessment. Provides structured price data interpretation.