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

Review Work (5-Agent Parallel Review Orchestrator)

A post-implementation review gate that spawns five parallel sub-agents — goal verification, hands-on QA, code quality, security, and context mining — and passes only if all five pass.

Dev & CodingAdvanced★ 67,531⑂ 5,507AI score 9/10Last updated: Aug 9, 2026

What it does

  • Fires before a PR handoff or on phrases like "review my work", "QA my work", "validate changes".
  • Phase 0 auto-collects GOAL, CONSTRAINTS, BACKGROUND, changed files, diff and the run command, and insists you review branches from a dedicated git worktree rather than the main checkout.
  • Phase 1 launches five background agents in a single turn:
    1. Goal & constraint verification (every explicit/implied requirement marked ACHIEVED/MISSED/PARTIAL, plus scope-creep and edge-case passes)
    2. Hands-on QA that actually runs the app (brainstorm 15–30 scenarios → augment → task list → execute P0 first with evidence capture)
    3. Code quality review across 10 dimensions with CRITICAL/MAJOR/MINOR/NITPICK severities
    4. Supplementary security audit (injection, authn/authz, secrets, dependency CVEs, path traversal, error leakage)
    5. Context mining across git log/blame, gh issues and PRs, Slack/Notion MCP tools, and codebase cross-references
  • Phases 2–3 store each lane's verdict independently, never treat a timeout or empty reply as PASS (it becomes INCONCLUSIVE and gets a smaller respawn), and emit a final report with aggregated blocking issues and a prioritized fix list.

Who it's for

  • Engineers and tech leads who want a hard quality gate before merging.
  • Users on harnesses with parallel sub-agents (oh-my-openagent, Codex multi_agent_v1/v2, OpenCode).
  • Teams that keep shipping implied-requirement misses, regressions, or security slips.

Example uses

  • Pre-PR gate: say "review changes" on a feature branch and get a five-lane verdict table plus exactly what to fix, in order.
  • Requirement drift check: the goal verifier decomposes the original request and flags the sub-requirement you only half-implemented, with code evidence.
  • Real QA run: web apps get browser-driven clicks and form fills, CLIs get argument/exit-code sweeps, APIs get curl payload matrices — failures come back with screenshots or terminal output.

· · · 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/code-yeongyu/oh-my-openagent/HEAD/packages/shared-skills/skills/review-work/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 packages/shared-skills/skills/review-work folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/review-work/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/code-yeongyu/oh-my-openagent.git /tmp/oh-my-openagent && mkdir -p ~/.claude/skills/review-work && cp -r /tmp/oh-my-openagent/packages/shared-skills/skills/review-work/* ~/.claude/skills/review-work/

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

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/code-yeongyu/oh-my-openagent.git /tmp/oh-my-openagent
  3. Create the skill folder: mkdir -p ~/.claude/skills/review-work
  4. Copy the files: cp -r /tmp/oh-my-openagent/packages/shared-skills/skills/review-work/* ~/.claude/skills/review-work/
  5. Restart Claude Code and confirm review-work appears in your skill list.
  6. From inside a git project, trigger it with "review my work" or "post-implementation review".
  7. If your environment lacks parallel sub-agent spawning, ask the assistant to run the five lanes sequentially or pick only the lanes you need.
View source on GitHub ↗License: NOASSERTION