Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

bmad-code-review — Claude skill: parallel code review

This skill runs several independent reviewers in parallel, then triages their findings. Useful when you want changes checked before a merge.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add bmad-code-org/BMAD-METHOD --skill bmad-code-review -a claude-code
Open on GitHub

What bmad-code-review does

bmad-code-review comes from the BMAD-METHOD repo. It fans out your code changes to several independent reviewers at once, then collects and triages what they found. Trigger it with something like "run code review" or "review this code".

There is one step inside: the agent runs render_skill.py from _bmad/scripts/, the script prints the skill's workflow, and the agent follows it. Modes include quick and thorough (appended as --set workflow.review=), a no-code mode with --set workflow.fixes=handoff, and a non-interactive run via --set workflow.interactive=false for CI or a bot.

You need uv and BMad already set up in the project — the _bmad/ folder has to exist. If the script is missing, the skill offers to set BMad up first through the bmad skill. Install it if you already use BMAD-METHOD; otherwise you have to stand the method up first.

What it helps with

  • run changes past several reviewers at once
  • collect review notes into one list
  • run a review with no prompts inside CI
  • pick between a quick and a thorough pass
  • hand fixes off to a separate step

Example prompts for the agent

  • run code review
  • review this code, quick
  • do a thorough review of these changes

How to install bmad-code-review

1Skills CLI (Vercel)

npx skills add bmad-code-org/BMAD-METHOD --skill bmad-code-review -a claude-code

2Manually: put the files in place

~/.claude/skills/bmad-code-review/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/bmad-code-review/

From the same set25

The whole set →
bmad bmad-code-org Coordinates BMad Method modules, recommends the next skill, and tracks project initiatives. Useful when setting up or repairing your workflow. Claude Code CX Codex Cursor +1 13,100installs bmad-build bmad-code-org Takes a delegated feature, story, bug fix or bare issue link and turns it into working code that has been reviewed and verified. Needs BMad set up in the project. Claude Code CX Codex Cursor +1 12,400installs bmad-architecture bmad-code-org Writes a short architecture document that pins down only the invariants keeping independently built parts of a system from diverging. Claude Code CX Codex Cursor +1 11,800installs bmad-agent-pm bmad-code-org Activates John, a product manager persona for PRD creation and requirements discovery. It breaks down product ideas into deliverable tickets. Claude Code CX Codex Cursor +1 11,800installs bmad-agent-architect bmad-code-org This skill turns ticket requirements into technical architecture with explicit trade-offs. Use it when you want to work with Winston as the architect. Claude Code CX Codex Cursor +1 11,800installs bmad-brainstorming bmad-code-org The skill runs a brainstorming session: the agent asks one question at a time, rotates creative techniques and logs ideas to a memlog. Useful when you want more options than you'd get alone. Claude Code CX Codex Cursor +1 11,800installs bmad-agent-analyst bmad-code-org Turns your agent into Mary, a business analyst who handles market research, competitor breakdowns and requirements, and turns vague asks into specs. Claude Code CX Codex Cursor +1 11,700installs bmad-agent-dev bmad-code-org Activates Amelia, a senior software engineer persona executing stories through red, green, refactor and acceptance criteria. Claude Code CX Codex Cursor +1 11,700installs

Similar

claude-automation-recommender official Anthropic Analyzes a codebase and recommends Claude Code hooks, subagents, skills, plugins, and MCP servers. Useful when setting up a project or refining an existing workflow. Claude Code 9,057installs do thedotmack The skill runs an implementation plan in phases through subagents. Use it when a plan needs execution with checks after each phase. Claude Code CX Codex Cursor +1 7,000installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. Claude Code 1,163,035installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. Claude Code 1,141,062installs triage Matt Pocock This skill moves issues and external PRs through triage states, verification, and agent briefs. It fits maintainers managing an issue queue. Claude Code 990,453installs codebase-design Matt Pocock This skill helps design modules with small interfaces and hidden complexity. Use it when refactoring code, choosing a seam, or making tests easier to write. Claude Code 850,344installs code-review Matt Pocock Reviews changes from a chosen reference point against repository standards and the originating spec. Use it for a branch, PR, or work in progress. Claude Code 789,521installs implement Matt Pocock Implements work from a specification or tickets, following a test-driven flow and ending with review and a commit. Use it when a coding task needs a defined delivery routine. Claude Code 774,700installs

Questions about bmad-code-review

How do I install bmad-code-review in Claude?

Run npx skills add bmad-code-org/BMAD-METHOD --skill bmad-code-review -a claude-code. The skill lands at ~/.claude/skills/bmad-code-review/SKILL.md.

What does bmad-code-review do?

It runs several independent reviewers in parallel, then triages and presents their findings on your code changes.

What does the skill need to run?

uv plus BMad set up in the project — the _bmad/ folder with scripts/render_skill.py. Without them the skill offers to install BMad first.

Source text

SKILL.md · MIT 
---
name: bmad-code-review
description: 'Review code changes with several independent reviewers in parallel, then triage and present the findings. Use when the user says "run code review" or "review this code"'
---

Run the following command exactly once without changing the current working directory.

Replace `{project-root}` with the nearest folder containing `_bmad/`, from the working directory upward.
Replace `{skill-root}` with the absolute path to this skill's directory.

If the invocation asks for a `quick` or `thorough` review, append `--set workflow.review=<value>` to the command.
If the invocation asks for a `no-code` review, append `--set workflow.fixes=handoff` to the command.

If the invocation is clearly non-interactive -- it says not to ask questions, or a bot, a CI job or another workflow is running the review -- append `--set workflow.interactive=false`. When in doubt, don't.

```bash
uv run --no-cache "{project-root}/_bmad/scripts/render_skill.py" --project-root "{project-root}" --skill "{skill-root}"
```

- The command prints the skill's workflow: follow it. `HALT: <reason>`: report the reason and stop.
- If the script does not exist, BMad is not set up in this project yet. Offer to set it up using `bmad` skill, then run the command again. If you do not have the `bmad` skill, offer to install it first.
- On any other output or failure, including `uv` being unavailable, report the command output and stop. Do not run any workflow source directly.

© bmad-code-org · MIT · bmad-code-org/BMAD-METHOD

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor