Skip to content
Get packs

Review Team Pod Reviewer

Lets an agent act as an independent code reviewer within a multi-agent review pod

Source Download skill
Repository
mvschwarz/openrig
Stars
8,553
Licence
Apache-2.0
Files
1 file

What it does

This skill teaches an AI agent to act as a fresh-eyes reviewer on a software change inside an OpenRig multi-agent team. It tells the agent when a review is actually assigned, how much rigor to apply, what context to read first, and how to check for duplicated or inconsistent code. It also describes how to write findings to disk and report them to an orchestrator using rig commands, with severity ratings from MUST-FIX down to INFO.

Great for

  • Developers running OpenRig multi-agent pods who want a dedicated review seat
  • Teams that want consistent, severity-rated code review reports from AI agents
  • People building their own review workflows who want a reference for independent review and hindsight review

Skip it if

  • Solo users who only want a quick code review with no team or orchestrator, since the skill assumes rig commands and a pod structure
  • Repositories where the review must not run shell commands, because the skill expects validation runs and rig CLI calls
  • Anyone expecting it to review code on its own initiative, since the skill tells agents not to start reviews without an explicit assignment

Try asking

  • “Review the changes on this branch for the assigned slice and report findings to the orchestrator”
  • “Do a hindsight review of these ad hoc dogfood patches against their commit messages”
  • “Write my review findings to docs/review and send a summary with severities”
Step-by-step guide: how to use Review Team Pod ReviewerInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.

    review-team.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip review-team.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip review-team.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Set up the pod and assignment first so the agent has an explicit review target; otherwise it will wait rather than review
  • Point the agent at the exact branch or commit to review, since it reviews the named target only
  • Check the written review file in docs/review, since the findings depend on the agent's reading of the source

What's inside

  • SKILL.md

Redistributed unmodified from mvschwarz/openrig under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.