Self-Eval: Honest Work Evaluation
ultrathink
Tier: STANDARD Category: Engineering / Quality Dependencies: None (prompt-only, no external tools required)
Description
Self-eval is a Claude Code skill that produces honest, calibrated work evaluations. It replaces the default AI tendency to rate everything 4/5 with a structured two-axis scoring system, mandatory devil's advocate reasoning, and cross-session anti-inflation detection.
The core insight: AI self-assessment converge
[Description truncada. Veja o README completo no GitHub.]