loop-review-skill-until-fixed-point

Automate repeated /review-skill passes on a target document until no issues remain.

1|1|Updated Jan 23, 2026

Ready to run

npx skills add https://github.com/corygabrielsen/skills --skill loop-review-skill-until-fixed-point

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: loop-review-skill-until-fixed-point
Source: https://github.com/corygabrielsen/skills/tree/main/loop-review-skill-until-fixed-point
Command: npx skills add https://github.com/corygabrielsen/skills --skill loop-review-skill-until-fixed-point

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates iterative peer-review passes on a target document, ensuring that all reviewers declare no issues before finalizing.

Core Features & Use Cases

Iterative review loop: automatically runs /review-skill against a target until all reviewers report NO ISSUES.
Isolate iterations: each pass is context-isolated to prevent leakage of prior findings.
Use Case: teams aiming for consensus on a document can enforce convergence by repeatedly reviewing until fixed point is reached.

Quick Start

Run the skill against a target SKILL.md path to initiate repeated reviews until convergence.

Frequently Asked Questions about loop-review-skill-until-fixed-point

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate iterative peer reviews until a document converges on no issues?▼

Automating iterative peer reviews requires running isolated review passes against a target document until all reviewers report NO ISSUES. This skill loops through context-isolated iterations, recording per-iteration outcomes to enforce convergence on policy papers, technical specifications, or code reviews.

What is a fixed point in automated document review workflows?▼

A fixed point in automated document review is reached when all reviewers declare NO ISSUES after repeated passes. This skill enforces this convergence by applying context-isolated iterations to a target document, ensuring collaborative consensus before finalizing.

How do I run repeated reviews on a SKILL.md file until convergence?▼

Running repeated reviews on a SKILL.md file requires providing the target path and a max_iterations cap. The skill executes isolated iterations of the review command, automatically stopping when all reviewers return no issues or the iteration limit is met.

Can I use automated review loops for technical specifications and code reviews?▼

Yes, automated review loops support collaborative review workflows across technical specifications, code reviews, and policy papers. The skill applies isolated review passes to these documents, repeating until all reviewers converge on no issues.

Why do my iterative document reviews keep failing to converge on no issues?▼

Reviews fail to converge when findings leak between iterations or the max_iterations cap is too low. This skill prevents context leakage by isolating each review pass, ensuring prior findings do not influence subsequent iterations, and records per-iteration outcomes for tracking.

Do I need a max_iterations cap to run automated review passes on a document?▼

Yes, a max_iterations cap is required to bound the automated review loop. The skill uses this cap alongside a target SKILL.md path to execute isolated review iterations, preventing infinite loops while converging on a no-issues fixed point.