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.
- Kind
- Skill
- Works with
- Claude Code, Codex
- Source
- affaan-m/ECC @ d3b8a3e90890
- Path
- skills/agent-self-evaluation/SKILL.md
- License
- MIT
- Jobs
- Review
InstallCopy it from the source repository, or sign in and let the assistant adapt it for your project.
# Agent Self-Evaluation After completing a complex task, the agent pauses to rate its own output against a structured 5-axis rubric. This is NOT a pass/fail gate — it's a deliberate reflection step that catches omissions, flags overconfidence, and surface areas for improvement before the user has to. ## When to Activate - After writing code that spans 3+ files or 50+ lines - After completing a multi-step workflow (implement → test → review) - After a debugging session that involved 3+ attempts - After producing a design document, architecture decision, or written analysis - When the user asks "how good was that?" or "rate yourself" - At the end of any session Stop hook (if configured — see `references/hook-integration.md`) ## Core Concepts ### The 5 Evaluation Axes | Axis | Question | What it catches | |---|---|---| | **Accuracy** | Are the facts, claims, and outputs correct? | Hallucinations, wrong API names, incorrect syntax, false statements | | **Completeness** | Did it cover everything the user asked for? | Missed edge cases, unhandled error paths, forgotten requirements, skipped subtasks | …