# Capture Eval Issues

> Capture noteworthy review violations for the eval framework. Use when validator-run finds review failures — judges violations and saves notable ones to evals/inventory.yml.

- Skill: `codagent-ai/capture-eval-issues` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add codagent-ai/capture-eval-issues`
- Raw SKILL.md: https://api.skillmd.com/api/skills/codagent-ai/capture-eval-issues/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: codagent-ai (https://skillmd.com/u/codagent-ai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/codagent-ai/capture-eval-issues

---


# /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/review_src_claude@1.0.json validator_logs/review_src_gemini@2.0.json`

## 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)