LLM & Agents

Conduct comprehensive codebase research by spawning parallel agents to document and explain code as it exists. Use this skill when needing to understand how a codebase works, where specific functionality lives, or what patterns exist. This skill orchestrates specialized agents (codebase-locator, codebase-analyzer, codebase-pattern-finder) and synthesizes findings into structured documentation.

This skill teaches the agent how to manage database schemas and migrations in the API project. MANDATORY - You MUST read this skill before modifying any database schema or migration files.

Code generation and file modification agent with delegation capabilities

Smart routing wizard for creating skills, agents, commands with complexity-based skill loading

Generate agent-ready prompts from existing task specification files. Use when regenerating prompts after editing tasks, updating prompt templates, or preparing tasks for cpo execution.

Test suite audit coordinator (L2). Delegates to 5 workers (Business Logic, E2E, Value, Coverage, Isolation). Aggregates results, creates Linear task in Epic 0.

Implement Claude Code hooks for deterministic control over agent behavior. Use when creating custom hooks for notifications, auto-formatting, logging, feedback, permissions, or lifecycle events.

Use when building Retrieval-Augmented Generation systems. Covers document chunking, embedding generation, vector indexing, semantic search, context building, and integration of retrieval with LLM completion for accurate Q&A on Physical AI textbook content.

Helps write conventional commit messages, create atomic commits, and follow git best practices. Use when the agent needs to help with git commits, commit message writing, or git workflow guidance.

Deploy and manage Supabase Edge Functions with E2B sandbox integration for permit research agents. Includes automated deployment, database migrations, RLS policies, and validation workflows.

Specialized agent for comprehensive testing of the BarqNet project across all platforms and layers. Handles unit testing, integration testing, E2E testing, performance testing, security testing, and test automation. Creates test plans, writes test code, executes tests, and generates test reports. Use when implementing tests, debugging test failures, or validating functionality.

生成式引擎优化专家，分析和优化内容在 AI 搜索引擎（ChatGPT、Claude、Perplexity、Google SGE）中的可见性和引用率。

Post-session analysis agent that extracts learnings, decisions, user preferences, and "surprise moments" from conversation transcripts. Stores insights in Memory Lane with vector embeddings for future retrieval.

claude-plugin 프로젝트 개발 가이드라인, 레퍼런스 패턴, 프로젝트 구조 조회. Use when Claude needs to (1) Look up development principles (P1-P4, DRY, KISS, YAGNI, SOLID), (2) Find reference patterns for Hooks/Agents/Commands creation, (3) Understand project structure and file locations, (4) Learn how to create Skills/Hooks/Agents/Commands, or (5) Delegate to claude-code-guide for official Claude Code documentation

Cross-platform audio feedback system for task completion and user prompts. Provides non-intrusive sound notifications to improve workflow awareness.

Search the web using Tavily API for high-quality, AI-optimized results. Use when the agent needs to find current information, verify facts, research topics, or answer questions requiring web data. Keywords: search, web, internet, lookup, find, research, current events, facts.

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.

Build RAG systems with Ollama local + cloud models. Latest cloud models include DeepSeek-V3.2 (GPT-5 level), Qwen3-Coder-480B (1M context), MiniMax-M2. Use for document Q&A, knowledge bases, and agentic RAG. Covers LangChain, LlamaIndex, ChromaDB, and embedding models.

Azure AKS Agentic CLI - AI-powered troubleshooting and insights tool for Azure Kubernetes Service. Use when diagnosing AKS cluster issues, getting cluster health insights, troubleshooting networking/storage/security problems, or analyzing cluster configuration with natural language queries.

Generate tests using AI and run test suites. Use for generating unit tests, running coverage reports, and mutation testing.