chapzin

Guidelines for using the local LLM wiki as durable project memory. Use when researching prior decisions, synchronizing session transcripts, preserving provenance, or turning repo/session knowledge into reusable context.

Design RESTful APIs following best practices

Systematic bug investigation and root cause analysis

Review code quality, patterns, and best practices

Generate commit messages following conventional commits with scope detection

Generate and update technical documentation

Break down features into implementable tasks

Review pull requests against team standards and best practices

Use this skill when a user wants Codex CLI or another MCP-compatible coding client to work through a harness-engineering loop with explicit execution contracts, persistent local knowledge/RAG, durable traces, structured verification evidence, project-local governance policy, PASS/FLAG/BLOCK governance audits, trace-level observability reports, harness profiles, eval cases/runs, Meta-Harness-lite proposals and promotion decisions, natural-language harness spec export, MCP resources/prompts, compact handoff context, multi-client setup, and completion gates before claiming work is done. Triggers on codex-harness, harness engineering, AgentOps observability, agent harness, governance audit, Claude Code MCP, OpenCode MCP, Kilo MCP, Gemini CLI MCP, Cursor MCP, VS Code MCP, Cline MCP, Windsurf MCP, Roo Code MCP, natural-language agent harnesses, persistent project memory, local RAG for Codex, deep research memory, implementation learning, benchmark/eval records, harness profile comparison, harness optimization, Meta