bmad-build — Claude skill: ship reviewed code
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.
npx skills add bmad-code-org/BMAD-METHOD --skill bmad-build -a claude-codeWhat bmad-build does
The skill runs render_skill.py from _bmad/scripts/ once and then follows whatever workflow the script prints. Before that, {project-root} is replaced with the nearest folder containing _bmad/, searching upward from the working directory, and {skill-root} becomes the absolute path to the skill's own directory. Don't change the working directory.
Named options get passed through as flags. A route (oneshot or full) appends --set workflow.route=; a review selection (none, quick, thorough) appends --set workflow.review=. If the script prints HALT: , the skill reports the reason and stops.
You need uv and a project where BMad is already configured. When the script is missing, the skill offers to set BMad up through the bmad skill and then retries. Any other failure, including uv not being available, ends the run with the command output reported — the workflow sources are never executed directly. Worth installing if you hand whole tasks to an agent and want review in the loop; skip it for typo or formatting edits.
What it helps with
- turn a delegated feature into working code
- fix a bug from an issue link
- run a change through review before committing
- pick the right review depth for a task
- set up BMad when the project lacks it
Example prompts for the agent
- bmad-build: add CSV export to the reports page
- bmad-build, route full, review thorough — fix the crash on an empty list
- bmad-build: here's the issue link, take it from there
How to install bmad-build
1Skills CLI (Vercel)
npx skills add bmad-code-org/BMAD-METHOD --skill bmad-build -a claude-code2Manually: put the files in place
~/.claude/skills/bmad-build/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/bmad-build/
1Skills CLI (Vercel)
npx skills add bmad-code-org/BMAD-METHOD --skill bmad-build -a codex2Manually: put the files in place
.agents/skills/bmad-build/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add bmad-code-org/BMAD-METHOD --skill bmad-build -a cursor2Manually: put the files in place
.cursor/skills/bmad-build/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install bmad-code-org/BMAD-METHOD bmad-build2Manually: put the files in place
.github/skills/bmad-build/SKILL.md1Skills CLI (Vercel)
npx skills add bmad-code-org/BMAD-METHOD --skill bmad-build -a gemini-cli2Platform CLI
gemini skills install https://github.com/bmad-code-org/BMAD-METHOD --path skills/bmad-buildManually: put the files in place
.devin/skills/bmad-build/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add bmad-code-org/BMAD-METHOD --skill bmad-build -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set25
The whole set →Similar
Questions about bmad-build
How do I install bmad-build in Claude?
Run npx skills add bmad-code-org/BMAD-METHOD --skill bmad-build -a claude-code. The skill lands at ~/.claude/skills/bmad-build/SKILL.md.
What does bmad-build do?
It takes implementation work you delegate — a feature, story, bug fix or meaningful change — and drives it to code that is reviewed and verified. A bare story or issue link is enough to trigger it.
What does bmad-build need to run?
BMad has to be set up in the project and uv must be available. If render_skill.py is missing, the skill offers to set BMad up first and then runs the command again.
Source text
SKILL.md · MIT
---
name: bmad-build
description: 'Turns implementation work into working code, reviewed and verified. Use when the user delegates a feature, story, bug fix, or meaningful change; a bare story or issue link counts. Skip obvious, low-risk mechanical maintenance such as small ignore-file, typo-only, formatting-only, or configuration-hygiene edits. Explicit BMAD requests always qualify. Do not volunteer for user-directed interactive edits or version-control operations that only record existing work.'
---
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.
```bash
uv run --no-cache "{project-root}/_bmad/scripts/render_skill.py" --project-root "{project-root}" --skill "{skill-root}"
```
- When the invocation names a route (`oneshot` or `full`), append `--set workflow.route=<value>` to the command.
- When the invocation names a review selection (`none`, `quick`, or `thorough`; "skip review" or "no review" mean `none`), append `--set workflow.review=<value>` to the command.
- 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