Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Multi-Reviewer Patterns

A playbook for running parallel code reviews across quality dimensions, then deduplicating findings, calibrating severity and producing one consolidated report.

Security & ReviewIntermediate★ 40,179⑂ 4,286AI score 7/10Last updated: Oct 1, 2026

What it does

  • Picks which review dimensions to assign (Security, Performance, Architecture, Testing, Accessibility) based on the change type: API endpoints, frontend components, DB migrations, auth changes.
  • Gives explicit merge rules when reviewers hit the same file:line — merge identical issues, keep co-located ones separate, take the higher severity on conflict, keep both recommendations with attribution.
  • Standardizes Critical/High/Medium/Low criteria plus calibration rules (externally exploitable vulns are always Critical/High, hot-path perf issues at least Medium, etc.).
  • Emits a consolidated report template with per-dimension counts and prioritized actions.

Who it's for

  • Tech leads fanning out PR reviews to multiple agents or teammates.
  • Teams whose severity labels drift between reviewers, breaking prioritization.
  • Anyone needing a pre-release sweep across security, performance and tests.

Examples

  1. "Review this auth PR" → only Security + Testing dimensions assigned, vulnerabilities floored at High.
  2. Paste three reviewers' findings and ask for a deduplicated, single consolidated report.
  3. Frontend component change → Architecture + Testing + Accessibility, with core WCAG violations rated at least Medium.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/wshobson/agents/HEAD/plugins/agent-teams/skills/multi-reviewer-patterns/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the plugins/agent-teams/skills/multi-reviewer-patterns folder from the GitHub repo wshobson/agents into my ~/.claude/skills/multi-reviewer-patterns/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/wshobson/agents.git /tmp/agents && mkdir -p ~/.claude/skills && cp -r /tmp/agents/plugins/agent-teams/skills/multi-reviewer-patterns ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/wshobson/agents.git
  2. Create the skills folder if needed: mkdir -p ~/.claude/skills
  3. Copy just this skill: cp -r agents/plugins/agent-teams/skills/multi-reviewer-patterns ~/.claude/skills/
  4. Restart Claude Code and confirm multi-reviewer-patterns shows up in your skill list.
  5. Trigger it with something like: "Split the review of this PR across security and performance, then give me one consolidated report."
View source on GitHub ↗License: MIT