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.
Meta-skill for creating and managing Claude Code skills
--- name: aspire-integration-testing description: > Use this skill whenever implementing or reviewing cross-component integration tests or smoke tests for .NET Aspire applications to ensure distributed system integrity. ---
使用 Banana API 生成知识笔记可视化图。支持思维导图、卡片、时间线、层级图、信息图等多种样式。当用户需要将知识点可视化、生成学习笔记图、知识总结图时使用此skill。
Comprehensive Ansible role auditor based on Red Hat Automation Good Practices. Performs in-depth analysis across 59 rules covering security, structure, modules, tasks, genericity, reusability, and Molecule tests. Use when the user asks to: audit an Ansible role, check Ansible best practices, analyze role quality, detect security vulnerabilities, validate a role, "audit ansible", "lint ansible", "review ansible role", "check role quality". Combines automated linting (yamllint, ansible-lint, checkov) with manual analysis against Red Hat Community of Practice guidelines.
Convert standard Markdown folder to EPUB ebook. Creates professional ebooks with cover, table of contents, chapters, and embedded images. Final step in the audioread pipeline.
Slack 봇이 매일 10시/19시에 DM으로 오늘 집중할 한 가지 일을 정하고, Lark 캘린더에 Focus Block을 자동 생성. 저녁에는 Coach GPT와 함께 회고. 트리거: "/daily-focus", "/daily-review", 또는 "오늘 집중할 일", "회고", "Focus Block", "캘린더 시간 확보" 같은 요청. 외부 연동: Slack (Bot API), Lark (Calendar OAuth), OpenAI (Coach GPT)
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
This skill should be used when the user asks to "design data model", "create entity definitions", "define TypeScript types", "design database schema", "create data structure", or "model entities". Defines data structures and entity models with TypeScript type definitions for Wave A parallel execution.
This skill should be used when the user asks to "create coding standards", "setup development environment", "design test strategy", "write operations runbook", "define deployment process", or "document implementation guidelines". Creates implementation preparation documents.
Physical robot emotion expression through Bluetooth-connected Freenove Pico Robot using R2-D2 beeps and sounds. Use when agents need to express emotions, status updates, or personality during task execution. Trigger on (1) successful task completion (happy), (2) errors/blocked states (angry), (3) processing/calculating (think), (4) ambiguous requests (confused), or (5) streaming audio playback (stream_audio).
Source and evaluate candidates from LinkedIn using the linkedin_scraper Python library. Use when the user wants to (1) scrape LinkedIn profiles for candidate data, (2) evaluate candidates against a job description, (3) generate boolean search strings for sourcing, (4) produce candidate scorecards, summaries, or comparison tables, or (5) any recruiting/talent-sourcing task involving LinkedIn data.
Core Elixir language patterns, idioms, and decision guidance for writing idiomatic functional code
Oban background job patterns including workers, queues, scheduling, unique jobs, retries, and testing
Reviews Go code for idiomatic patterns, error handling, concurrency safety, and common mistakes. Use when reviewing .go files, checking error handling, goroutine usage, or interface design.
This skill should be used when the user asks to "update dependencies", "update npm packages", "bump dependencies", "upgrade node packages", "check for outdated packages", "update package.json", or mentions dependency updates, npm/pnpm/yarn/bun package upgrades, or taze CLI usage.
Token-efficient library documentation fetcher using Context7 MCP with 86.8% token savings through intelligent shell pipeline filtering. Fetches code examples, API references, and best practices for JavaScript, Python, Go, Rust, and other libraries. Use when users ask about library documentation, need code examples, want API usage patterns, are learning a new framework, need syntax reference, or troubleshooting with library-specific information. Triggers include questions like "Show me React hooks", "How do I use Prisma", "What's the Next.js routing syntax", or any request for library/framework documentation.
This skill should be used when the user asks to "搜索应用", "查找应用", "安装应用", "卸载应用", "检查更新", "升级应用", "查看应用详情", "反馈问题", "应用商店" or mentions "ll-cli" with app install/update tasks.
Create a new brainstorming domain - scaffolds directory structure and writes DESCRIPTION.md under ideate/.
Read, parse, and summarize iCalendar (.ics) files from Google Calendar, Apple Calendar, and similar providers. Use when extracting upcoming events, filtering by date range, converting ICS events to JSON/text, or debugging calendar fields like DTSTART/DTEND/TZID/RRULE.
Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.
Audit web pages for accessibility violations using Playwright and axe-core. Produce a prioritized report with specific fix suggestions tied to source files.
Control Home Assistant (lights, switches, climate, scenes, scripts) via the Home Assistant REST API. Use when Nicolai asks to control devices at home, query entity states, or run Home Assistant services.
블로그의 SEO 인프라(메타 태그, canonical, sitemap, robots.txt 등)를 감사합니다.
Create and send interactive cards to Feishu (Lark) with buttons, forms, polls, and rich UI elements. Use when replying to Feishu messages and there is ANY uncertainty - send an interactive card instead of plain text to let users choose via buttons. Automatically handles callbacks via long-polling connection. Use for confirmations, choices, forms, todos, polls, or any scenario requiring user interaction in Feishu.
将PDF文件的每一页转换为图片文件;支持自定义图片格式(PNG/JPG)和分辨率;适用于文档处理、图片化存档等场景
图片生成技能,当用户需要生成图片、创建图像、编辑/修改/调整已有图片时使用此技能。支持10种图片比例(1:1、16:9、9:16等)和3种分辨率(1K、2K、4K),支持文生图和图生图编辑。
Quick validation that the Narra plugin is properly configured and working
本技能针对你这套 OpenClaw + 企业微信自建应用(wecom-app)环境,提供可复用的“怎么做”步骤。
Python CLI + skill files for posting to Moltbook, focused on Ergo Platform messaging.
Emova MCP 서버 코드에 대한 셀프 코드 리뷰를 수행합니다.
PDF generation, visual regression testing, and optimization
Translates PDF documents with academic-quality standards (rewrite-based workflow). Extracts text, applies three-step translation (rewrite→diagnose→refine), generates PDF with Chinese fonts (STHeiti) and English font mixing. Use when translating PDFs to Chinese with TOC/preservation needs.
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
画面遷移図(画面フロー図 / Screen flow / UI flow / Wireflow)を、要件・ユーザーストーリー・既存ルート・Figma構成・文章仕様から再現可能に作成/更新する。出力はMermaidのflowchartを基本とし、画面カタログ(画面ID/名称/状態/権限)と遷移カタログ(トリガー/条件/結果/例外)も併記する。例外系(失敗・戻り・未ログイン・権限不足・空状態)を必ず含め、スパゲッティ化する場合はユースケース単位で図を分割(L0/L1/L2)する。トリガー語: 画面遷移図, 画面フロー, UIフロー, screen flow, wireflow, 遷移図, フロー図, 画面一覧, 画面設計, 導線
Backup strategy design, data integrity verification, and disaster recovery planning. Invoke with /backup.
Retrieve market data from MetaTrader 5 using pdmt5 library. Use when you need to: (1) Get available trading symbols and their specifications (2) Fetch current bid/ask prices and tick data (3) Retrieve OHLCV (candlestick) historical price data (4) Get tick-by-tick data for high-frequency analysis Requires active MT5 connection (use mt5-connection skill first).
Creates, edits, and validates Mermaid diagrams including flowcharts, sequence diagrams, class diagrams, state diagrams, ERDs, Gantt charts, and more. Use when working with Mermaid syntax, creating diagrams from descriptions, visualizing architecture, documenting workflows, or when user mentions mermaid, flowchart, sequence diagram, UML, or visualization.
GitHub PR review operations via gh CLI. Create pending reviews with line comments, submit reviews (approve/reject/comment). Use when adding PR comments, submitting reviews, or managing GitHub code reviews.
Stacked (dependent) pull request workflow. Use when creating, managing, or troubleshooting stacked PRs, or when user mentions stacked diffs, dependent PRs, PR stacks, or breaking large features into smaller PRs.
Address review/issue comments on the open GitHub PR for the current branch. Fetches all comments and review threads, summarizes what needs attention, and helps apply fixes. Use when responding to PR feedback, resolving review comments, or when user mentions "address comments" or "fix review feedback".
Creates FHIR R4 Questionnaires with official LOINC codes. NEVER suggest codes from memory - ALWAYS use provided scripts to search LOINC database.
Lists all code tasks in the repository with their status, dates, and metadata. Useful for getting an overview of pending work or finding specific tasks.
Serverless deployment with zero-downtime, multi-environment strategies, and infrastructure validation. Use when deploying Lambda functions, managing environments, or troubleshooting deployment failures.
Convert slides into LinkedIn-ready carousel PDFs. Triggers: 'create LinkedIn carousel', 'convert slides to carousel', 'carousel PDF from images', 'PPTX to carousel', 'slides to PDF for LinkedIn'. Supports square (1080x1080) and vertical (1080x1350) formats from HTML slides, image folders, or PowerPoint files.
NocoDB setup, integration, and operations for database UI and administration. Use when setting up NocoDB locally with Docker, connecting NocoDB to external databases (Supabase, PostgreSQL), creating views and relationships, configuring security (RLS bypass, image scanning), managing backups, or troubleshooting NocoDB connectivity issues. Includes two-database architecture patterns (metadata DB vs external data source), NC_DB connection string configuration, view creation via UI, relationship auto-detection via FK constraints, and operational procedures (backup, monitoring, error handling). Reference NocoDB documentation at https://nocodb.com/docs for official guidance.
Deploy Fireproof Connect to a dedicated Studio VM on exe.dev. Sets up cloud sync backend for all your Vibes apps.
Search, fetch, and convert Slack Developer Docs pages from https://docs.slack.dev into clean markdown files for local grep and analysis. Use when you need to browse Slack developer documentation, locate relevant pages by keyword, or extract a page's content into a temporary file.
Plan resource budgets (time, tokens, workers, tools) for orchestrator execution. Use when estimating cost, limiting concurrency, or enforcing budget constraints.
Terraform Cloud operations and registry documentation lookup. Watch runs, view plan/apply logs, check workspace status, look up provider docs. Invokes Terraform MCP server on-demand without loading tool definitions into context.
Produces standardized completion reports under docs/reports with masking and docs-only commit rules.
Kills running OASIS instances and rebuilds the executable.
Show learning system health - insight counts, tag distribution, effectiveness, feedback loop status.
freee 会計・人事労務 API を MCP 経由で操作するスキル。詳細なAPIリファレンスと使い方ガイドを提供。
Generate 50-question interactive quizzes using the Quiz component with randomized batching. Use when creating end-of-chapter assessments. Displays 15-20 questions per session with immediate feedback. NOT for static markdown quizzes.
Upload PDF slides to CDN and configure chapter README with slides metadata. This skill should be used when adding teaching presentation slides to a chapter. Handles: PDF upload, part/chapter resolution, README frontmatter update, Teaching Aid heading.
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.
基于 PptxGenJS 生成精美 PPTX:当用户给出一段文本/大纲/结构化要点,希望自动排版成现代风格的 .pptx,并需要插入 charts/images/media/shapes/tables/text 时使用;本技能提供 deck-spec(JSON) 到 pptx 的生成脚本与工作流
Gemini APIで日報要約を構造化JSON出力。LLM要約、構造化出力、プロンプト設計、日報生成エンジン実装時に使用。OpenAI APIからGemini APIへの移行も対応。
Runs the totem validation script which checks: - CONSCIOUSNESS directory structure (4 subdirectories) - All required tracking files (18 files) - File format validation (TSV pipes, bracket notation) - Hook installation (3 core hooks) - CLAUDE.md compliance (preamble, required sections) - GPS and time log commands functionality - Legacy file cleanup - Cross-reference validation (consciousness repo only)
Claude Code plugin creation guide. Use when creating new plugins, adding commands/skills/hooks/MCP servers to plugins, or setting up marketplace distribution. Triggers on "create plugin", "add command", "add skill", "add hook", "plugin structure".
Transcribe audio and video files using the Deepgram API. This skill should be used when the user requests transcription of audio files (mp3, wav, m4a, aac) or video files (mp4, mov, avi, etc.). Handles large video files by extracting audio first to reduce upload size and processing time.
Token-efficient C++ build output processing for CMake/vcpkg/MSVC/GCC/Clang projects. Use when detecting CMakeLists.txt in project, running cmake configure/build commands, or when user requests C++ compilation. Reduces build log tokens by 80-95% through intelligent filtering while preserving actionable error information.
Add Wikipedia reference links to concepts that don't have one. Searches for relevant Wikipedia articles and adds them to the references array.
自动构建高质量Dify Workflow并进行效果测试与迭代的专业技能。当用户需要:(1)根据需求自动生成Dify Workflow JSON,(2)构建复杂的多步骤AI工作流,(3)设计RAG、Agent、条件分支、迭代等高级流程。
Convert HTML to PDF with pixel-perfect rendering and excellent Hebrew/RTL support. Use when the user asks to 'convert HTML to PDF', 'generate PDF from HTML', 'create PDF from webpage', 'export to PDF', or needs PDF generation with Hebrew text support.
Exact-time task reminder scheduling using Dapr Jobs API for Phase V event-driven architecture.
This skill validates and enforces stateless agent architecture compliance with the constitutional requirement: **NO in-memory conversation state**.
Execute the fashion photoshoot generation pipeline scripts. Use after getting prompts from the editorial-photography skill. This skill runs the actual image/video generation and stitching.
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.
Expert knowledge for deploying Node.js/TypeScript serverless functions on Vercel with better-auth, Express, and Prisma. Includes lazy initialization patterns, ES module configuration, error handling, and troubleshooting. Use when deploying to Vercel, fixing FUNCTION_INVOCATION_FAILED errors, configuring ES modules, or setting up better-auth on serverless platforms.
Automate the Daily News Roundup (DNR) newsletter pipeline for the Center for Cooperative Media. Run the DNR script with different modes (--preview generates HTML preview only, --dry-run shows story counts without generating files, full pipeline creates Mailchimp draft). Use this skill when working on DNR newsletter automation, running the pipeline, previewing newsletters, testing story collection and classification, or troubleshooting the NJ News Commons newsletter workflow.
Comprehensive data analysis toolkit for Python using pandas, numpy, and visualization libraries. When Claude needs to: (1) Load and explore datasets from CSV, JSON, Excel, or databases, (2) Perform statistical analysis and identify trends, (3) Clean and transform messy data, (4) Generate formatted reports with visualizations, or (5) Detect outliers, missing data, and data quality issues. Use for data exploration and insight generation, not for machine learning model building.
Guidelines for creating and modifying Git-Mastery exercises. Use when developing new exercises, understanding exercise types, or following exercise patterns.
自动扫描 docs/notes 目录,生成 VuePress 配置文件 navbar.ts 和 notes.ts。当需要发布新笔记、更新导航栏、重新生成笔记配置或初始化 VuePress 笔记结构时使用。适用于 vuepress-theme-plume 主题。
Manual testing workflow for Claude HUD to verify core functionality. Use when asked to "test the app", "verify the app works", "run manual tests", "test after changes", or after implementing significant features. Performs full reset, launches app, and guides through verification checklist.
Expert Unix and macOS systems engineer for shell scripting, system administration, command-line tools, launchd, Homebrew, networking, and low-level system tasks. Use when the user asks about Unix commands, shell scripts, macOS system configuration, process management, or troubleshooting system issues.
This skill should be used when the user asks to "create a bootstrap prompt", "handoff", "save session state", "continue in new session", "create handoff", "session summary for continuation", "bootstrap for fresh session", or wants to capture the current session state for resumption in a new Claude Code session.
This skill should be used when tracing resource requests through the Maestro system to debug resource lifecycle issues, track request flow from client to agent and back, or troubleshoot failures in resource creation, update, or deletion operations across the server-agent-server pipeline. Supports both Kubernetes log files and ARO HCP Kusto CSV exports.
Connect to PostgreSQL using psql with a multi-datasource YAML config (profiles) and safe-by-default scripts for connectivity checks, querying, and schema introspection.
Send an email notification (SMTP) when a task completes. Use when you want a repeatable script/CLI to email users on success or failure, including subject/body templating via arguments or stdin.
Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.
Send WeCom (企业微信) application messages by fetching an access_token then calling message/send. Use when you need a repeatable CLI/script to send text or markdown to specific users/parties/tags (or @all) via 企业微信自建应用.
No description available
No description available
No description available
Use PROACTIVELY when you need to create, update, configure, or validate Claude hooks for various events and integrations
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.
Extends [websocket-updater-core](../websocket-updater-core/SKILL.md) with googleai_dart-specific configuration.
Phomemo M02 Pro向けのレイアウトJSONの生成・修正・検証・プレビュー/印刷を扱う。576px固定幅、長尺はY方向で確保、回転/分割送信などの制約を踏まえて設計する依頼、天気/ToDo/定規などの印刷テンプレを作る依頼、dry_runでプレビューしてから印刷する依頼で使う。
Audit a repository's structure and propose a safe, approval-gated reorganization plan. Use when asked to review repo anatomy, propose folder changes, or apply an approved reorg with rollback.
Use when creating, validating, or packaging Claude Code skills - provides six-step workflow, progressive disclosure, and reference-first philosophy.
Use when starting a new development project - creates memory folder structure with project_state.md, architecture scaffolding, and registers project
通用 Web 项目构建工具,自动检测项目类型(Vue、React、Ant Design Pro 等),执行依赖安装和生产构建,生成可部署的静态文件并返回预览链接。
This skill provides guidance on using the PowerPlatform Dataverse Client SDK for Python. Use when users ask about "Dataverse SDK", "Dataverse Python", "DataverseClient", "Dataverse authentication", "Dataverse CRUD operations", "create Dataverse records", "query Dataverse", "Dataverse connection", or need help with the Microsoft Dataverse Python SDK.
kubectl-localmesh固有の運用操作(起動、/etc/hosts管理、サービスアクセス、依存関係チェック)を提供します
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 when researching topics in Notion, synthesizing findings, or creating research documentation. Load for searching Notion and creating structured reports.
Use when setting up project-specific hooks for Claude Code enforcement. Load during INIT state when .claude/hooks/ is missing, or when creating new project. Installs 5 hooks that read from .claude/config/project.json (tests, health, dependencies).