BMAD Brainstorming
BMad Code OrgFacilitates BMad brainstorming sessions with selectable stances, creative techniques, persistent session logs and optional convergence.
By agent · OpenClaw
Skills in the open SKILL.md format that OpenClaw reads. Each one has a plain-language summary and the command to install it.
$ npx skills add <author>/<skill> --agent openclawReplace the placeholder with the author and skill name from the skill's page. Start a new OpenClaw session afterwards so the skill is picked up.
Facilitates BMad brainstorming sessions with selectable stances, creative techniques, persistent session logs and optional convergence.
Implements approved BMAD stories and code changes with test-first development, acceptance-criteria checks and verified delivery.
Guides the BMAD Method's Mary business analyst through market research, competitive analysis and requirements work from a project-aware menu.
Turns delegated BMAD implementation work into code through a rendered workflow with review and verification for features, stories and bug fixes.
Creates, updates and validates product briefs through guided discovery, source review, decision logging and right-sized documentation.
Acts as BMAD's UX designer, translating user needs into interaction designs and UX specifications through a configured design persona and workflow.
Creates concise BMad architecture spines that record cross-component invariants, boundaries, state ownership and deferred decisions from ideas, specs or codebases.
Distils ideas, briefs, PRDs and mixed notes into a lean BMad requirements specification with stable capabilities, constraints and validation.
Creates, updates and validates product requirements documents in the BMad Method, with guided discovery, research, review and finalisation.
Assesses significant sprint changes in the BMAD Method across requirements, architecture and UX, then produces an actionable change proposal.
Generates automated API and end-to-end tests for implemented features in the BMAD Method, using the project's existing test framework and patterns.
Reviews a finished BMAD epic against its plans, diffs and commits, then produces sourced findings, action items and an acceptance decision.
Captures a product's UX vision in BMad through paired design and experience specifications, guided discovery, user journeys and validation.
Runs configurable BMAD review lenses over code or documents, combining adversarial, edge-case, verification, structure and prose findings into a triaged report.
Maintains a repository's AGENTS.md guidance by setting up, adopting, refreshing or auditing instructions and recording agent mistakes as pitfalls.
Pressure-tests a developing idea through focused questions and contrasting personas, then records its outcome and optional planning brief in BMad.
Researches decisions through drafted prompts, parallel web searches or cited summaries of existing reports in the BMad workflow.
Runs one unattended development-loop iteration through BMad, with optional route and review selections.
Drafts and revises pull request descriptions using the repository's template, verified branch facts, validation results and reviewer guidance.
Creates a HyperFrames title animation in which glass shards fly through fog and assemble into a headline before flying out.
Creates a 12-second HyperFrames title sequence where sweeping leaves reveal two headlines, with adjustable typography and motion.
Creates a HyperFrames carousel of bevelled 3D cuboids that move through a timed sequence, with customisable cards, lighting, camera and geometry.
Creates an 8-second HyperFrames title animation that bursts through a wireframe portal and transforms into a replacement phrase.
Creates an 8-second HyperFrames hero animation that flips square headline tiles under a sweeping depth field to reveal a second headline.
Questions
Often. A skill is a folder of instructions and scripts in the open SKILL.md format, which OpenClaw reads. A skill that depends on tools only one agent provides will not carry over, so read the skill's source before you rely on it.
Each skill page has an install command. Run it in a terminal, then start a new OpenClaw session so the skill is picked up.
An instructions file is loaded in every session and describes the project. A skill is loaded only when a task calls for it, so it can be long and specific without costing context on every turn.