review-loop Skill
Iterative review loop using any lens agent against any target (plan, code, design). Use when you want to run a focused review cycle: spawn a fresh reviewer subagent with a specific lens, present findings and remediation to the user, apply fixes with user guidance, and repeat until clean. Published by microsoft in Trieste.
What is review-loop Skill?
Iterative review loop using any lens agent against any target (plan, code, design). Use when you want to run a focused review cycle: spawn a fresh reviewer subagent with a specific lens, present findings and remediation to the user, apply fixes with user guidance, and repeat until clean. Published by microsoft in Trieste. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Security review
- Design and media
- Security review use cases
- Design and media use cases
Technical details
- Install or run with Copy skill directory
When to use review-loop Skill
- Use it for security review.
- Use it for design and media.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/Trieste
- Skill file: .github/skills/review-loop/SKILL.md
What it does
Iterative review loop using any lens agent against any target (plan, code, design). Use when you want to run a focused review cycle: spawn a fresh reviewer subagent with a specific lens, present findings and remediation to the user, apply fixes with user guidance, and repeat until clean.
Skill instructions
Review Loop Use this skill to run an iterative review cycle against any target using any lens agent. Inputs The user specifies: 1. Lens — which lens/reviewer to use (e.g., adversarial-lens, security-lens, conservative-lens, speed-lens, usability-lens). 2. Target — what to review (a plan, file(s), module, design document, diff, etc.). If either is ambiguous, ask the user before proceeding. Procedure Step 1 — Gather Context Read the target material and any surrounding context needed for a meaningful review. This includes: - The target itself (plan text, file contents, etc.) - Relevant WF specs, token definitions, and pass pipeline context - Relevant tests or prior review findings Step 2 — Spawn Reviewer Subagent Spawn a fresh subagent with the specified lens. Provide it: - The full target material (verbatim — do not summarize) - Sufficient surrounding context for the reviewer to assess the target meaningfully - Instructions to produce structured findings per the lens's Expected Output fo
Explore related resources
Frequently asked questions
What is review-loop?
review-loop is a open-source AI agent skill with Copy skill directory. Iterative review loop using any lens agent against any target (plan, code, design). Use when you want to run a focused review cycle: spawn a fresh reviewer subagent with a specific lens, present findings and.
Who is review-loop best for?
review-loop is best for reusing agent instructions, scripts, and references, security review workflows, design and media workflows.
How do I install review-loop?
Install or run review-loop using Copy skill directory. Check review-loop for the latest setup command.
Is review-loop actively maintained?
review-loop may need a closer maintenance check before production use.
Auto-fetched from GitHub.
