Skillget

genpark-self-refine-iterative-critique-optimization-skill

mcp
Security Audit
Warn
Health Warn
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 7 GitHub stars
Code Pass
  • Code scan — Scanned 6 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Self-Refine iterative critique-and-refinement loop evaluating constraint adherence and applying structured revisions

README.md

Self-Refine Iterative Critique Optimization Skill

High-efficiency, zero-dependency Python implementation of Self-Refine: Iterative Refinement with Self-Feedback.

Features

  • Iterative Feedback Loop: Interleaves generation, automated rubric critique, and targeted revision.
  • Convergence Guarantees: Terminates early upon attaining quality score thresholds or hitting max iteration budgets.
  • Zero External Dependencies: Pure Python standard library.
  • Native MCP Protocol: JSON-RPC 2.0 stdio server compatible with Claude Desktop, Cursor, and Windsurf.

Architecture

graph LR
    Draft["Initial Output Draft"] --> Critique["Automated Critique / Scorer"]
    Critique --> Eval{"Score >= Threshold?"}
    Eval -- Yes --> Final["Accepted Optimized Output"]
    Eval -- No --> Refine["Targeted Revision Engine"]
    Refine --> Critique

Reviews (0)

No results found