evaluation

DSH 插件评测工具：YAML 用例驱动真实 agent 回归评测 + baseline 对比 PASS/WARN/FAIL 门禁｜Regression eval harness for DeepSeek Harness plugins

Local-first experiment and evaluation workbench plugin for DeepSeek Harness (DSH).

Reproducible DSH profile and patch experiment matrices with reports and policy gates

该仓库暂未提供项目说明。

Public, reusable DeepSeek Harness plugins and skills: workflow canvas toolkit, blind eval harness, LLM cost lab, incident ledger.