LLM 與 Agent

Git commit assistant. Triggers when user says "提交代码", "commit", "提交一下", "帮我提交", "push code", or any commit-related requests. Automatically lists changed files, generates commit message, asks for confirmation, executes git add/commit/push after approval.

This skill should be used when the user asks about "MCP tools", "Unity MCP", "enable tool groups", "which MCP tools", "create GameObject", "add component", "run Unity tests", "check scene hierarchy", "spawn agent for Unity", "MCP not working", or needs to coordinate Unity Editor operations via MCP.

Generate tests following project conventions. Use when writing unit tests, integration tests, creating test fixtures, or implementing test builders. Triggers on requests like "write tests for", "add test coverage", "create test builder", "test this handler", or "implement tests".

deepagents framework integration patterns for agent creation, planning, filesystem operations, and subagent orchestration. Current version 0.2.5 with LangGraph 1.0.2+

Use OpenAI Codex CLI as a discussion partner to verify ideas, evaluate plans, and improve quality. Automatically triggered during implementation planning, troubleshooting, debugging, or when seeking a second opinion on technical decisions.

Builds real-time multiplayer applications with PartyKit on Cloudflare's edge. Use when creating collaborative apps, games, AI agents, or stateful WebSocket servers with global low-latency deployment.

Parallel internal codebase search. Launches 2-4 search agents, consolidates findings to tmp/scout-results.md, returns summary. Use for 3+ files or unknown areas.

Validates PopKit compliance with Claude Code patterns using concrete standards and automated checks

Process and transform FAQ documents (xlsx, word, pdf, txt) into RAG-optimized format. Use when working with FAQ files, knowledge base documents, or when the user needs to analyze and restructure FAQ content for RAG systems.

Answers questions about the cgl-consulting plugin including commands, agents, and methodology. Auto-activates on plugin help requests like "what commands", "how do I use", "where do I start", or "explain the methodology". Provides quick reference or spawns guide agent for complex questions.

Use this skill after code changes are made, when reviewing implementations, checking code quality, or ensuring constitutional compliance. Apply when user mentions reviewing, analyzing, or checking code quality. Also use proactively after significant code implementations to verify they follow mini_agent framework principles.

Publishing assistant for Thomas's Astro-based GitHub Pages site (readme-pages). Creates publish-ready Markdown files for notes, recipes, and pages. Use when asked to write blog posts, articles, notes, recipes, or content for the readme-pages site at thomasrohde.github.io/readme-pages. Also use for content requests mentioning "publish", "blog", or "my site".

Generate professional prompts for Nano Banana Pro image generation. Use when the user wants to create images, thumbnails, infographics, edit photos, generate character-consistent content, create storyboards, or any visual asset using Nano Banana Pro. Transforms vague requests into detailed, effective prompts following Nano Banana Pro's "thinking model" best practices.

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 Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Semantic compression of verbose documentation into OCTAVE format achieving 60-80% reduction with 100% decision-logic fidelity. Use when converting natural language to OCTAVE, streamlining documentation, creating semantic density, optimizing agent prompts, or compressing knowledge artifacts. Triggers on: octave compression, compress to octave, semantic compression, documentation streamlining, OCTAVE optimization, compress documentation, semantic density.

Crypto wallet assistant for generating payment links for supported tokens (USDC, USDT, vUSD, ICP, CKUSDC) across multiple networks (Solana, Ethereum, Base, BSC, Vly, ICP), X402 redirect links for accessing payment-protected content, and providing access to the vly.money wallet interface. Use when users request to send/transfer crypto, mention 402 errors or payment-required content, or explicitly ask to access vly.money wallet.

Creates a battle-tested ChatGPT-style chatbot widget that solves real-world production issues. Features infinite re-render protection, text selection "Ask AI", RAG backend integration, streaming SSE, and comprehensive performance monitoring.

Navigate and understand this project's structure, including agents directory with XML/MD prompt files, templates for task creation, XML-based task management with naming conventions, and development workflows. Use when exploring the codebase structure, understanding project organization, or explaining how agents, tasks, and templates work together.

Create, validate, and package Claude skills automatically. Use PROACTIVELY when users want to create a new skill, validate existing skill files, or package skills for distribution. Works across Claude.ai, API, and Claude Code platforms.

Modern Python development with uv, FastAPI, Pydantic, and clean architecture. Use for Python project setup, LLM app development, API design, testing strategy, and architecture decisions. Ideal for TypeScript developers transitioning to Python.