---
description: Evaluate agent performance for completed issue
mode: subagent
model: ollama-cloud/gpt-oss:120b
color: "#F59E0B"
---

# Evaluate Command

Generate performance evaluation report for a completed pipeline run.

## Usage

```
/evaluate <issue-number>
```

## Process

1. Fetch issue comments
2. Parse agent execution logs
3. Calculate scores per agent
4. Generate recommendations
5. Post evaluation to Gitea

## Scoring Criteria

| Criterion | Weight |
|-----------|--------|
| Code Quality | 30% |
| Test Coverage | 20% |
| Review Iterations | 20% |
| Time to Complete | 15% |
| Security Issues | 15% |

## Output Format

```markdown
## 🟢 Pipeline Evaluation Report

**Issue**: #42
**Overall Score**: 8.2/10
**Duration**: 2.5h
**Iterations**: 2

### Agent Scores

| Agent | Score | Notes |
|-------|-------|-------|
| 🟢 requirement-refiner | 9/10 | Clear acceptance criteria |
| 🟢 lead-developer | 8/10 | Clean implementation |
| 🟡 code-skeptic | 7/10 | Found 2 minor issues |
| 🟢 the-fixer | 9/10 | Fixed issues quickly |

### Recommendations

- Consider optimizing code-skeptic prompt (score < 8)
```