mcpField
C
capture-eval-issues

capture-eval-issues

github.com/codagent-aiTesting & quality3063 installsUpdated 1d ago
Repository

About capture-eval-issues

A skill for reviewing JSON reports and recording noteworthy violations in an evaluation inventory. It delegates judgment and capture to a subagent, then reports the capture summary.

Key features

  1. 01Reads review JSON paths
  2. 02Uses a judge prompt
  3. 03Delegates to a subagent
  4. 04Reports the capture summary

Use cases

  1. 01Capture violations from review reports
  2. 02Add judged issues to an evaluation inventory

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/codagent-ai/agent-validator --skill capture-eval-issues

After installing, type/capture-eval-issuesin Claude Code to confirm it loaded.

Bundled filesjudge-prompt.mdscripts/append-inventory.ts

Details

From the project README

/capture-eval-issues

Capture noteworthy review violations into the eval inventory.

Input

This skill receives one or more review JSON file paths as arguments (space-separated). Example: /capture-eval-issues validator_logs/[email protected] validator_logs/[email protected]

Procedure

  1. Read judge-prompt.md from this skill's directory
  2. 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
  3. Report the subagent's capture summary (the CAPTURED: line)

Comments

Markdown supported