Eval 命令¶
管理基于评估的开发工作流。
用法¶
/eval [define|check|report|list|clean] [feature-name]
评估定义¶
/eval define feature-name
创建新的评估定义:
- 在
.claude/evals/feature-name.md中创建模板:
## EVAL: feature-name
Created: $(date)
### Capability Evals
- [ ] [기능 1에 대한 설명]
- [ ] [기능 2에 대한 설명]
### Regression Evals
- [ ] [기존 동작 1이 여전히 작동함]
- [ ] [기존 동작 2이 여전히 작동함]
### Success Criteria
- capability eval에 대해 pass@3 > 90%
- regression eval에 대해 pass^3 = 100%
- 提示用户输入具体标准
评估检查¶
/eval check feature-name
对功能运行评估:
- 从
.claude/evals/feature-name.md中读取评估定义 - 对于每个能力评估(capability eval):
- 尝试验证标准
- 记录 PASS/FAIL
- 将尝试记录到
.claude/evals/feature-name.log - 对于每个回归评估(regression eval):
- 运行相关测试
- 与基线比较
- 记录 PASS/FAIL
- 报告当前状态:
EVAL CHECK: feature-name
========================
Capability: X/Y passing
Regression: X/Y passing
Status: IN PROGRESS / READY
评估报告¶
/eval report feature-name
生成综合评估报告:
EVAL REPORT: feature-name
=========================
Generated: $(date)
CAPABILITY EVALS
----------------
[eval-1]: PASS (pass@1)
[eval-2]: PASS (pass@2) - 재시도 필요했음
[eval-3]: FAIL - 비고 참조
REGRESSION EVALS
----------------
[test-1]: PASS
[test-2]: PASS
[test-3]: PASS
METRICS
-------
Capability pass@1: 67%
Capability pass@3: 100%
Regression pass^3: 100%
NOTES
-----
[이슈, 엣지 케이스 또는 관찰 사항]
RECOMMENDATION
--------------
[SHIP / NEEDS WORK / BLOCKED]
评估列表¶
/eval list
显示所有评估定义:
EVAL DEFINITIONS
================
feature-auth [3/5 passing] IN PROGRESS
feature-search [5/5 passing] READY
feature-export [0/4 passing] NOT STARTED
参数¶
$ARGUMENTS:
- define <name> - 创建新的评估定义
- check <name> - 运行并检查评估
- report <name> - 生成完整报告
- list - 显示所有评估
- clean - 清理旧评估日志(保留最近 10 次执行)
本页原文 Markdown:在 AtomGit 查看·内容源自开源项目 ev/ECC