A Claude Skill that rewrites your prompt, runs it, and grades the result against its own success criteria — in one turn. Bounded loop: max 2 refine passes, a separate stop condition, and a no-progress halt.
Cross-referenced across 55 tracked directories
#9039
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
7/30/2026
Created
1
GitHub Stars
1
Open Issues
8/26/2026
Last Commit
Recently added to the ecosystem
Score: 100/100
0 dependency vulnerabilities found
dprctd
Detect duplicated code, dead code, and anti-patterns in AI-generated codebases
tomquirk
A multi-model council plugin for OpenCode that runs prompts across multiple LLMs and synthesizes their responses to identify consensus and discrepancies.
...more