china-qijizhifeng

Agent Harness Evolution — 基于 HARNESS.md v1.0 规范的评估、审计与改进工作流。加载后自动检查当前 workspace 结构合规性，引导 evidence-driven 的 Harness 改进。当用户要求做 Harness 审计、初始化 Agent workspace、生成或验证 Change Manifest、对 harness 组件做 evidence-driven 改进，或反复出现同一类失败模式时触发。

Install and use the bundled agent debugger CLI source to configure adb LLM settings, download Langfuse traces, ask QA questions about traces, and run adb check quality analysis. Use when the task is about agent-debugger CLI workflows, trace debugging, or explaining how adb is configured.

NexAU agent evolution reference for a simple starting agent. Use when adding tools, middleware, sub-agents, or skills during evolution. Covers all available components, YAML config schema, and creation guides. Reference docs in reference/ for deep dives.

Researches any capability and crystallizes it into a reusable skill with the right structural pattern (tool wrapper, generator, reviewer, pipeline, or inversion). Trigger when the user asks to "create a skill", "make a skill for", "turn this into a skill", or "learn how to use X". Also trigger proactively when: (1) the task involves unfamiliar CLI tools, APIs, libraries, or workflows that need research; (2) the task would benefit from a structured, repeatable workflow — such as code review with checklists, consistent document generation, multi-step deployment with approval gates, or project scaffolding with configuration interviews; (3) a previously generated skill fails, produces poor results, or a referenced skill is missing. Do NOT trigger for tasks you can already handle reliably without a structured workflow.