腳本程式

MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.

Create and refine Codex skills (folders containing `SKILL.md`). Use when you need help naming a skill, writing effective `name`/`description`, structuring the on-disk instructions, or adding scripts/references/assets for repeatable workflows.

Manage Google Calendar and Gmail through Python code execution. Trigger keywords include calendar, gmail, meeting, email, schedule, event.

Add headless Chrome automation with Puppeteer/Playwright on Cloudflare Workers. Use when: taking screenshots, generating PDFs, web scraping, crawling sites, browser automation, or troubleshooting XPath errors, browser timeouts, binding not passed errors, or session limits.

Format TypeScript sources using Deno formatter

Build Model Context Protocol (MCP) servers on Cloudflare Workers - the only platform with official remote MCP support. TypeScript-based with OAuth, Durable Objects, and WebSocket hibernation.Use when: deploying remote MCP servers, implementing OAuth (GitHub/Google), using dual transports (SSE/HTTP), or troubleshooting URL path mismatches, McpAgent exports, OAuth redirects, CORS issues.

mypy - Static type checker for Python with gradual typing, strict mode, Protocol support, and framework integration

Generate optimized Apple App Store metadata recommendations with ASO best practices. Use this skill when analyzing app listings, optimizing metadata (title, subtitle, description, keywords), performing competitive analysis, or validating App Store listing requirements. Triggers on queries about App Store optimization, metadata review, or screenshot strategy.

Master Python syntax, data types, control flow, functions, OOP, and standard library

Universal skill generator using 7-step ReAct pattern with 95+/100 quality guarantee. This skill should be used when creating new skills, editing existing SKILL.md files, or updating skill descriptions and quality.

Use this skill when creating or refining Claude Code skill definitions. Skills are model-invoked capabilities that Claude activates autonomously based on context. Helps design focused skills with discovery-optimized descriptions, proper directory structures, and supporting resources. Automatically invoked when user requests "create a skill", "make a capability", "add autonomous behavior", or mentions skill development. Ensures skills follow Anthropic specifications with clear activation triggers.

This skill should be used when the user asks about "GitHub Actions", "CI/CD", "continuous integration", "automated testing", "deployment automation", or setting up workflows for Rails projects. Load this skill when configuring GitHub Actions.

Coordinate agents via the AMQ CLI for file-based inter-agent messaging. Use when you need to send messages to another agent (Claude/Codex), receive messages from partner agents, set up co-op mode between Claude Code and Codex CLI, or manage agent-to-agent communication in any multi-agent workflow.

Automated validation results analysis for post-commit workflow. Triggers when user requests validation analysis, code review summary, or checking background validation results. Analyzes Biome, TypeScript, and AI review reports.

[Code Quality] Removes code duplication and cleans up dead code. Use to eliminate copy-paste code, consolidate similar logic, and remove unused code paths.

Version control management system for git operations with intelligent commit messages and workflow automation. Handles commits, pushes, branches, merges, and integrates with test-manager and docs-manager for automated workflows. Use when committing changes, pushing code, creating branches, or managing git workflows. Always asks for confirmation before any destructive operations.

Interactive debugger for Deno/TypeScript applications using the V8 Inspector Protocol. This skill should be used when investigating issues in Deno applications, including memory leaks, performance bottlenecks, race conditions, crashes, or any runtime behavior that requires step-by-step debugging, heap analysis, or CPU profiling. Provides CDP client tools, heap/CPU analyzers, and investigation tracking.

Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.

Python code quality standards (PEP 8, type hints, docstrings). Use when writing Python code.

Scaffolds a new Python agent file in 'src/agents/' from a template. Use when asked to create a new agent.