review-loop

Run a six-step quality-check loop over session deliverables.

2|1|Updated Feb 4, 2026
One-click install
npx skills add https://github.com/davidbeglenboyle/davids-claude-code-setup --skill review-loop
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review-loop
Source: https://github.com/davidbeglenboyle/davids-claude-code-setup/tree/main/skills/ready-to-use/review-loop
Command: npx skills add https://github.com/davidbeglenboyle/davids-claude-code-setup --skill review-loop

SYSTEM DOCUMENTATION & REQUIREMENTS

## What problem does it solve? Run a structured quality-check loop over session deliverables to verify content quality, consistency, and alignment with project standards.

## Core Features & Use Cases

  • Identify Deliverables: detect files created or modified in the session with common deliverable extensions (md, docx, pdf, pptx, xlsx, txt).
  • Verify Quality: apply a quality-score to each deliverable using the Bash tool when available and re-run after fixes.
  • Review & Fix: route findings to a critic or devils-advocate depending on context, apply fixes, and re-score.
  • Report: generate a final summary of scores, fixes, and remaining issues for user decision.
  • Context Routing: adapt reviews for branded client work vs internal projects using internal agents.

### Quick Start Use the review-loop to initiate a manual quality check on the most recently modified deliverables.

Frequently Asked Questions about review-loop

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

FAQPage Schema
How do I automate a quality check for markdown and document deliverables?

You can automate a structured quality check for markdown, docx, pdf, pptx, and xlsx files by running a deterministic six-step workflow that identifies, verifies, reviews, fixes, re-scores, and reports on session deliverables.

What is a structured review loop for session deliverables?

A structured review loop is an automated process that applies a quality-score to modified deliverables, routes findings to a critic or devils-advocate, applies fixes, and generates a final summary report of remaining issues.

Can I route feedback differently for branded client work versus internal projects?

Yes, context routing adapts the automated review standards and uses subagents to differentiate between branded client work and internal projects during the quality verification process.

How do I verify content consistency and apply a quality score to modified files?

The review workflow verifies content consistency by applying a quality-score to each deliverable using the Bash tool, re-running the score after fixes are applied to ensure measurable improvement.

What is the best way to fix and re-score deliverables during a review?

The best way to fix and re-score deliverables is to route findings to a critic, apply necessary fixes, and automatically re-score the updated files to confirm quality improvements before reporting.

Does the automated review workflow require the Bash tool to score deliverables?

The automated review workflow applies a quality-score to each deliverable using the Bash tool when available, ensuring deterministic verification and re-scoring of fixes across the session.