zsp/everything-claude-code
1
0
Fork 0
mirror of https://github.com/affaan-m/everything-claude-code.git synced 2026-04-13 05:03:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs(zh-CN): sync Chinese docs with latest upstream changes (#304)

Browse Source 
* docs(zh-CN): sync Chinese docs with latest upstream changes

* update

---------

Co-authored-by: neo <neo.dowithless@gmail.com>
This commit is contained in:
zdoc.app
2026-03-03 14:28:27 +08:00
committed by GitHub
parent adc0f67008
commit ada4cd75a3
114 changed files with 11161 additions and 4790 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
docs/zh-CN/skills/eval-harness/SKILL.md
View File

@@ -1,6 +1,7 @@
---
name: eval-harness
description: 克劳德代码会话的正式评估框架，实施评估驱动开发（EDD）原则
origin: ECC
tools: Read, Write, Edit, Bash, Grep, Glob
---
@@ -8,6 +9,14 @@ tools: Read, Write, Edit, Bash, Grep, Glob
一个用于 Claude Code 会话的正式评估框架，实现了评估驱动开发 (EDD) 原则。
## 何时激活
* 为 AI 辅助工作流程设置评估驱动开发 (EDD)
* 定义 Claude Code 任务完成的标准（通过/失败）
* 使用 pass@k 指标衡量代理可靠性
* 为提示或代理变更创建回归测试套件
* 跨模型版本对代理性能进行基准测试
## 理念
评估驱动开发将评估视为 "AI 开发的单元测试"：