发现 部署与运维 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Creates technical documentation including READMEs, API references, user guides, architecture docs, ADRs, and runbooks. Use for requests to create, write, generate, or draft documentation. Trigger phrases includ...
Defines the standard 8-category taxonomy for classifying project files: Config, Tests, Docs, Scripts, Source Code, Data, AI Tooling, and Other. REFERENCE THIS SKILL whenever categorizing files, auditing project...
Ensure Python classes include appropriate, developer-friendly dunder methods—especially __repr__ and __str__. Use when: (1) Writing or modifying Python class definitions in .py files, (2) Refactoring existing P...
Updates existing README.md files after code changes. Use for requests to update, check, fix, or add to an existing README. Trigger phrases include "update readme", "check readme", "is the readme current", "add...
Set up and configure DuckDB databases. Use when user needs to create databases, configure settings, or initialize DuckDB projects.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends an agent's capabilities with specialized knowledge, workflows, or...
Convert markdown PRDs to executable JSON format. Use after creating a PRD with the prd skill to generate the prd.json for autonomous task completion.
Read cards from and write new cards to a local Anki installation
Unified execution engine for all development workflows. Progressive disclosure for phase execution, quick features, story completion, and scaffolding. Integrates with artifact-tracking and meatycapture-capture....
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically...
Capture bugs/enhancements/ideas to request-logs. For quick operations use /mc command instead.
Recover from crashed, failed, or interrupted Claude Code sessions. Use this skill when: session crashed during multi-agent parallel execution, need to determine what work was completed vs incomplete, want to ge...
Generate and optimize PRDs, Implementation Plans, and Progress Tracking documents optimized as AI artifacts for development agents. Use when creating new feature plans, breaking down long planning docs (>800 li...
Reorganize project documentation with bilingual (English/Japanese) structure. Use when asked to "reorganize docs", "update documentation", or "sync documentation".
DuckDB, MotherDuck cloud analytics, and Parquet file handling for Node.js/TypeScript applications
Use when deploying applications, choosing deployment platforms, or troubleshooting deployment issues - routes to platform-specific skills (Vercel, Fly.io, Cloudflare)
Use when building Chrome extensions (Manifest V3). Covers floating panel architecture, sidepanel API, storage patterns, message passing, content scripts, SPA navigation detection, context menus, Vitest testing,...
Use when generating PDFs from markdown with Pandoc - covers differences from Python-Markdown, blank line rules, fix scripts for labels/anchors/metadata, and visual testing workflow
Use when deploying to Fly.io - covers single volume limitation, monorepo deployment, Dockerfile patterns for Next.js/Python, and common troubleshooting
Use when working with Cloudflare R2 object storage, D1 SQLite database, KV, or Workers integration - covers bindings, limits, gotchas, and best practices
Use when implementing dependency installation systems - covers bundled portable executables in MSI installers, unified detection/execution code paths, and Windows installer best practices
Server-Sent Events (SSE) for real-time progress updates in Next.js/Vercel. TransformStream patterns, client consumption, progress tracking.
Use when deploying MkDocs documentation to GitHub Pages with GitHub Actions - covers Python-Markdown gotchas (indentation, footnotes, grid tables), workflow configuration, and systematic markdown fixing
Use when automating browsers with Playwright/Puppeteer, testing Chrome extensions, using Chrome DevTools Protocol (CDP), handling dynamic content/SPAs, or debugging automation issues
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。