General skillCode review and quality
critic-overkill
Converge on code or design improvements through three critics and agreement-based fixes.
- Stars
- 0
- Forks
- 0
- Updated
- Updated May 26, 2026
MIT
Converge on code or design improvements through three critics and agreement-based fixes.
critic-overkill runs three calibrated critic agents in parallel, scores the work, and implements only changes independently flagged by at least two critics. It commits each round and stops when the target score is reached or progress plateaus, with critic pools selected for UI, APIs, copy, code, or security-sensitive work. An initial scan detects the project’s stack and verification commands.
Resource types
Use cases
Platforms
Capabilities
Review high-risk code through independent specialist agents and synthesis.
Audit a repository locally and turn cited findings into clear priorities.
Public GitHub facts last synced Jul 10, 2026.
Review code with adjustable roast levels and actionable fixes.
Score and audit Claude SKILL.md files