设计和优化AI代理的动作空间、工具定义和观察格式,以提高完成率。
当你在改进智能体的规划、调用工具、从错误中恢复以及收敛到完成状态的方式时,使用此技能。
智能体输出质量受限于:
每个工具响应都应包括:
status: success|warning|errorsummary: 一行结果next_actions: 可执行的后续步骤artifacts: 文件路径 / ID对于每个错误路径,应包括:
跟踪:
Copy a source-pinned command for your client. You run it yourself.
Destination: .claude/skills/agent-harness-construction · pinned to the source commit
git clone https://github.com/affaan-m/ECC.git
cd ECC
git checkout d8409a4b0813771235555e32e3d8046a73988bfa
mkdir -p ".claude/skills/agent-harness-construction"
cp -r "docs/zh-CN/skills/agent-harness-construction" ".claude/skills/agent-harness-construction"Review the source before running. This copies files into your project; it is not a one-click install and does not verify runtime safety.
Scanner static-checks@0.1.0 · commit d8409a4b0813. Static checks cannot prove runtime safety – review the source and the exact diff before installing. How checks work.
No static rules matched. This is not a safety guarantee.