agent-self-evaluation
Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.
| Field | Value |
|---|---|
| Owner | affaan-m |
| Curator | Thomas Cherickal |
| Source | affaan-m/ECC |
| Repo stars | 302,998 |
| License | MIT |
| Repo last push | 2026-11-09 |
Links
- Roles: ai-engineer
- Source repo: affaan-m/ECC
- Same repo: agent-eval, eval-harness, healthcare-eval-harness, scientific-thinking-scholar-evaluation, rust-patterns, rust-testing, django-celery, django-patterns
- Registry seed skills for this role: ai-engineer seed skills