bmad-code-review

Decision-grade research on a topic or this repository.

Runs the evals of a BMad skill through the agent harness the user works in and reports what they show: baseline against the bare model, variant against a…

Test a product concept with Amazon's Working Backwards method: write the press release for the finished product first, then answer hard customer and…

Test a half-formed idea in a questioning conversation, with different personas probing its weak points, until the user can act on it or drop it with confidence.

Push the LLM to reconsider, refine, and improve its recent output.

Orchestrates lively group discussions between installed BMAD agents or custom personas, and helps author custom parties.

Work out and record the architecture decisions that keep separately built parts of a system consistent, in a short architecture document.

Capture the user's UX vision in two documents: DESIGN.md for how the product looks and EXPERIENCE.md for how it behaves.

Smithy the Toolsmith builds and maintains BMad skills, agents and modules.

Runs one or more installed review lenses — adversarial critique, edge cases, verification gaps, structure, prose — and reports triaged findings.

Set up, adopt, refresh, or audit a repository's agent instructions (the AGENTS.md block) so AI agents work well in that repo.

Authors and updates customization overrides for installed BMad skills.