eval-report

# Evaluation Report Generate a quality report from accumulated evaluation results. ## Research Foundation - **REF-001**: BP-9 - Continuous evaluation of agent performance - **REF-002**: KAMI benchmark methodology for real agentic task evaluation ## Usage ```bash /eval-report /eval-report --output .aiwg/reports/quality-report.md /eval-report --compare previous-report.json /eval-report --mode sdlc --format json ``` ## Options | Option | Default | Description | |--------|---------|-------------| | --output | stdout | Output file path | | --compare | none | Previous report to diff against | | --mode | all | Agent category: sdlc, marketing, forensics, all | | --format | markdown | Output format: markdown, json | | --since | none | Only include results after this date (ISO 8601) | | --threshold | 0.85 | Score below this triggers a warning | ## Process 1. **Collect Results**: Read all `eval-*.json` files from `.aiwg/reports/` 2. **Aggregate Scores**: Compute per-agent and per-archetype scores 3. **Detect Regressions**: Compare against --compare baseline if provided 4. **Rank Agents**: Sort by overall score, flag below-threshold agents 5. **Build Recommendations**: Surface specific agents and archetypes needing attention 6. **Output Report**: Write markdown or JSON to --output or stdout ## Report Sections ### Summary Dashboard Overall health at a glance — total agents tested, aggregate score, regression count. ### By Archetype Pass rates per Roig (2025) failure archetyp...