sanshan1978/codeguard-rag-mcp
Skill Claude CodeCodex
Autonomous spec-driven development agent. Syncs DEVSPEC.md into chapter-based reference files, identifies the next pending task from the schedule, implements code following spec architecture and patterns, runs tests with up to 3 auto-fix rounds, and persists progress with atomic commits. Use when user says "auto…
sanshan1978/codeguard-rag-mcp
Skill Claude CodeCodex
Fully autonomous QA testing agent for Modular RAG MCP Server. Reads test cases from QATESTPLAN.md, executes ALL test types automatically without human intervention — CLI commands, Dashboard UI via Streamlit AppTest headless rendering, MCP protocol via subprocess JSON-RPC, provider switches, and data lifecycle checks.…
sanshan1978/codeguard-rag-mcp
Skill Claude CodeCodex
A resume-writing helper for describing project experience from the Modular RAG MCP Server project. It produces tailored descriptions in Chinese or English based on technical details and the user's business context.
sanshan1978/codeguard-rag-mcp
Skill Claude CodeCodex
Guide for creating effective agent skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends the agent's capabilities with specialized knowledge, workflows, or tool integrations. Use when user says "create skill", "new skill", "build a skill", "update skill", or…
sanshan1978/codeguard-rag-mcp
Skill Claude CodeCodex
A mock technical-interview agent for a Modular RAG MCP Server project. It can optionally use a résumé, ask detailed questions for up to three rounds, and produce a saved interview report with answers, feedback, and scores.
sanshan1978/codeguard-rag-mcp
Skill Claude CodeCodex
A project-cleaning and packaging workflow that removes development leftovers and sensitive keys from configuration. It produces a smaller codebase intended for sharing or distribution.
sanshan1978/codeguard-rag-mcp
Skill Claude CodeCodex
Interactive project learning coach via interview-style Q&A. Reads codebase and docs, dynamically generates interview questions per knowledge domain and sub-topic, conducts up to 4 follow-up rounds, scores answers, provides learning guidance with code/doc references, and persists progress. 10 domains × 3-5 sub-topics =…
sanshan1978/codeguard-rag-mcp
Skill Claude CodeCodex
An interactive study guide for the Modular RAG MCP Server project. RAG means retrieving relevant information before generating an answer, and MCP is a standard way for AI tools to connect to software.
sanshan1978/codeguard-rag-mcp
Skill Claude CodeCodex
Interactive project setup wizard. From a clean codebase, guides user through provider selection (OpenAI/Azure/DeepSeek/Ollama/Qwen/Gemini/etc.), API key configuration, dependency installation, config generation, and launches the dashboard. If user selects an unimplemented provider, auto-scaffolds the provider code…