review-loop
#65 in Coding Agents & AI DevelopmentIterative worker-reviewer cycle that spawns a critic subagent to score work 1-10 and provide actionable feedback, then revises until a quality gate is met.
Overview
Iterative worker-reviewer cycle that spawns a critic subagent to score work 1-10 and provide actionable feedback, then revises until a quality gate is met. Use when implementing features, writing specs, reviewing existing code, or completing any task where quality matters more than speed. Trigger phrases: "use review-loop", "polish this", "iterate on this", "/review-loop", "review with feedback loop".From the project's GitHub description
Our editorial assessment of review-loop is still in review. Facts below come from the repository and our catalogue.
Good for
Technical specifications
Each attribute is labelled with where it came from.
- Software type
- Agent / Skillevidence
- Agent ecosystem
- Skillevidence
- Interface
- No direct user interfaceevidence
- Runtime
- Agent runtimeevidence
- Interaction model
- Agent-operatedevidence
- Deployment model
- Local installationevidence
- License
- Not verified. GitHub could not identify this licence; check the repository before adopting.
Install
A skill is a set of instructions your agent loads. Install it into the agent you use; there is nothing to host.
$ npx skills add https://github.com/2dmurali/review-loop-skill --skill review-loop- Listing
- skills.shInstall counts come from skills.sh.
Alternatives
Also in Coding Agents & AI Development
Same category, not necessarily equivalent.
Gemini CLI
An open-source AI agent that brings Gemini into your terminal.
Context7
Up-to-date library documentation for coding agents, served over MCP.
Reviews
Community ratings are kept separate from Beav Scout rankings.
No reviews yet. Community reviews and comments are opening soon; you'll be able to rate review-loop once signed in.