bmad-build-auto
bmad-code-org/bmad-method
Execute one iteration of an unattended BMad development loop with configurable workflow routes and review levels.
What is bmad-build-auto?
bmad-build-auto runs a single cycle of the BMad automated development workflow. Use it when you need to execute build, test, or deployment steps unattended, with optional routing (oneshot or full) and review settings (none, quick, or thorough).
- Executes a single iteration of the BMad development loop without manual intervention
- Supports workflow route selection (oneshot or full) via command-line flags
- Supports review level configuration (none, quick, or thorough) via command-line flags
- Outputs a workflow.md instruction file on success that must be read and followed
- Requires BMad to be installed and configured in the project
How to install bmad-build-auto
npx skills add https://github.com/bmad-code-org/bmad-method --skill bmad-build-auto- BMad must be installed and configured in the project root
- uv package manager must be available
- Project must have _bmad/scripts/render_skill.py present
How to use bmad-build-auto
- 1.Invoke the skill by name to run one development loop iteration
- 2.Optionally append --set workflow.route=oneshot or --set workflow.route=full to select a workflow route
- 3.Optionally append --set workflow.review=none, --set workflow.review=quick, or --set workflow.review=thorough to set review level
- 4.Read the workflow.md instruction printed to stdout on success and follow it exactly
- 5.If the script is not found, run the bmad skill setup first, then retry
Use cases
- Running automated build and test cycles in CI/CD pipelines
- Executing development workflows with minimal human oversight
- Chaining multiple development iterations with different review levels
- Integrating BMad workflows into agent-driven development loops
- Developers using BMad for automated development workflows
- CI/CD pipeline engineers integrating BMad automation
- Coding agents executing unattended development tasks
bmad-build-auto FAQ
The skill will detect the missing render_skill.py script and offer to run the bmad skill's setup, which installs BMad first if needed.
Yes, invoke the skill multiple times. Each invocation runs exactly one iteration of the development loop.
oneshot and full are different workflow execution paths; consult your BMad configuration for their specific behaviors.
The skill will report the command output and halt without running workflow source directly, allowing you to diagnose the issue.
No; you can set workflow.review=none to skip review entirely, or choose quick or thorough for different review depths.
Full instructions (SKILL.md)
Source of truth, from bmad-code-org/bmad-method.
name: bmad-build-auto description: 'One iteration of an unattended development loop. Use when invoked by name'
Run the following command exactly once without changing the current working directory. Replace {project-root} with the absolute path to the project root and {skill-root} with the absolute path to this skill's directory:
uv run --no-cache "{project-root}/_bmad/scripts/render_skill.py" --project-root "{project-root}" --skill "{skill-root}"
- When the invocation names a route (
oneshotorfull), append--set workflow.route=<value>to the command. - When the invocation names a review selection (
none,quick, orthorough; "skip review" or "no review" meannone), append--set workflow.review=<value>to the command. - On success, read and follow the one absolute
workflow.mdinstruction printed to stdout. - If the script is not found, BMad is not set up here. Offer to run the
bmadskill's setup, installingbmadfirst if you do not have it (npx skills add bmad-code-org/BMAD-METHOD --skill bmad), then run the command above once more. - On any other failure (including
uvbeing unavailable), report the command output and HALT. Do not run any workflow source directly.
Related skills
More from bmad-code-org/bmad-method and the wider catalog.
bmad-code-review
Review code changes with multiple independent reviewers in parallel, then triage findings.
bmad-correct-course
Assess sprint change impact across PRD, epics, architecture, and UX; produce a structured change proposal.
bmad-create-epics-and-stories
Break requirements into epics and user stories with detailed acceptance criteria.
bmad-customize
Author and update customization overrides for BMad agent and workflow skills.
bmad-deep-recon
Research a topic to support a decision: draft prompts, process reports, or run parallel web searches.
bmad-forge-idea
Pressure-test half-formed ideas through questioning conversations until you can act on them or drop them with confidence.