Back to Details

capture-eval-issues

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/capture-eval-issues

/capture-eval-issues

Capture noteworthy review violations into the eval inventory.

将值得关注的评审违规情况捕获至评估清单。

Input

输入

This skill receives one or more review JSON file paths as arguments (space-separated). Example:

/capture-eval-issues validator_logs/review_src_claude@1.0.json validator_logs/review_src_gemini@2.0.json

本技能接收一个或多个评审JSON文件路径作为参数（以空格分隔）。示例：

/capture-eval-issues validator_logs/review_src_claude@1.0.json validator_logs/review_src_gemini@2.0.json

Procedure

流程

Read
```
judge-prompt.md
```
from this skill's directory
Spawn a subagent to judge and capture violations:
- Task tool:
```
Task
```
  with
```
subagent_type="general-purpose"
```
  ,
```
model="sonnet"
```
  ,
```
prompt=
```
  judge-prompt content +
```
"\n\nReview JSON files: <file paths>\n\nSkill directory: <this skill's directory path>"
```
- The subagent handles everything: reading files, judging, calling the append script
Report the subagent's capture summary (the
```
CAPTURED:
```
line)

从本技能目录读取
```
judge-prompt.md
```
文件
生成一个子代理（subagent）来判定并捕获违规情况：
- 任务工具：
```
Task
```
  ，参数为
```
subagent_type="general-purpose"
```
  ,
```
model="sonnet"
```
  ，
```
prompt=
```
  judge-prompt内容 +
```
"\n\n评审JSON文件：<文件路径>\n\n技能目录：<本技能的目录路径>"
```
- 子代理负责所有操作：读取文件、判定违规、调用追加脚本
报告子代理的捕获摘要（即
```
CAPTURED:
```
行内容）