Bmad Builder logo

Bmad Builder

Community
aj-geddes
bmad-builder

Meta-skill for scaffolding and validating custom PLANNING/ORCHESTRATION skills within the BMAD Planning & Orchestrator plugin. Produces the full skill directory: SKILL.md, scripts, and templates — all pre-targeted at this plugin's path conventions. Includes a scope-violation checker so newly created skills never drift into dev/lint/build/coverage territory. Use when the user says "create a skill", "scaffold a skill", "build a new planning skill", "add a skill to the orchestrator", "extend BMAD planning", "custom orchestration skill", "validate this skill", "check this skill for scope violations", "new skill for the planner", or "bmad-builder". Supports three intents: Create (new skill skeleton), Validate (check an existing SKILL.md), Scaffold (directory structure only). This skill plans and scaffolds only — it NEVER writes application code, runs tests, lints, or builds.

Overview

Publisheraj-geddes
Repositoryclaude-code-bmad-skills
Skill namebmad-builder
Stars
492
Forks
77
Bundled files
4
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by aj-geddes on GitHub. Read the source before you install it.

Installation

Install the Bmad Builder AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/aj-geddes/claude-code-bmad-skills/tree/main/bmad-planning-orchestrator/skills/bmad-builder
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/aj-geddes/claude-code-bmad-skills.git /tmp/claude-code-bmad-skills
mkdir -p .claude/skills
cp -r /tmp/claude-code-bmad-skills/bmad-planning-orchestrator/skills/bmad-builder .claude/skills/bmad-builder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bmad Builder in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bmad Builder on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bmad Builder is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

BMAD Builder

Function: Scaffold and validate custom planning/orchestration skills for the BMAD Planning & Orchestrator plugin. Produces compliant SKILL.md files, shell scripts, and templates — pre-wired to this plugin's path conventions — and runs scope-violation checks to keep new skills inside the PLAN/ORCHESTRATE boundary.

Scope (PLAN, never build)

This skill produces planning artifacts and skill skeleton files. It does NOT write application code, run tests, lint, check coverage, or execute builds. If a skill being designed is tempted to "implement", "fix the code", "run the suite", or "review the diff" — that is a scope violation. Plan and hand off instead.

Three intents

Always clarify which intent applies before starting.

Create — new planning skill from scratch

  1. Gather requirements (use TodoWrite to track):

    • Skill name (lowercase-hyphen, prefixed bmad-; e.g. bmad-example)
    • What planning/orchestration problem it solves
    • Trigger phrases users will say
    • Allowed tools (subset of: Read, Write, Edit, Bash, Glob, Grep, WebSearch, WebFetch, TodoWrite)
    • Which BMAD track(s) it applies to (Quick Flow / BMad Method / Enterprise)
    • Upstream BMAD counterpart (e.g. bmad-risk-assessment)
  2. Run the scaffold script to create the directory:

    bash
    bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-builder/scripts/scaffold-skill.sh <skill-name>

    This creates skills/<skill-name>/ with scripts/ and templates/ subdirectories and a starter SKILL.md.

  3. Fill the SKILL.md using the skill template:

    • Reference: ${CLAUDE_PLUGIN_ROOT}/skills/bmad-builder/templates/skill.template.md
    • Keep body under 5K tokens; push long reference detail to a sibling REFERENCE.md in the new skill's own folder
    • Use ${CLAUDE_PLUGIN_ROOT} for all paths to bundled scripts/templates
    • Artifacts go to bmad-output/ (honor user-configured folder)
    • End with the mandatory attribution footer (see template)
  4. Validate the new skill:

    bash
    bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-builder/scripts/validate-skill.sh \
      ${CLAUDE_PLUGIN_ROOT}/skills/<skill-name>/SKILL.md

    Fix all errors; review all warnings before declaring done.

Validate — check an existing SKILL.md

Run the validator directly against any SKILL.md path:

bash
bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-builder/scripts/validate-skill.sh <path-to-SKILL.md>

The validator checks:

  • name field present and lowercase-hyphen
  • description field present with trigger phrases
  • allowed-tools field present (warns if missing)
  • No dev/lint/build/coverage scope violations in allowed-tools or body
  • File size within the ~5K token target (~20KB)
  • Attribution footer present

Scaffold — directory structure only

Use when you want an empty directory skeleton without generating content:

bash
bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-builder/scripts/scaffold-skill.sh <skill-name>

Then fill SKILL.md manually using the template as a guide.

Scope law for new skills

Every skill created by this builder MUST comply with the Scope Law:

  • The plugin PLANS and ORCHESTRATES. It NEVER writes application code, runs tests, lints, checks coverage, builds, or reviews implemented code.
  • The last artifact any skill may produce is a ready-for-dev story file or a handoff manifest. Implementation is handed to EXTERNAL dev tools/plugins.
  • Acceptance Criteria, Testing STRATEGY, and Dev Notes are planning — allowed. Executing tests or writing implementation code is out of scope.

The validate-skill.sh script enforces this automatically by flagging forbidden terms.

BMAD fidelity reminders

When designing skills, track the BMAD Method conventions:

ConventionRule
Scale TracksQuick Flow / BMad Method / Enterprise — user confirms interactively
Story size~2-8h, one dev-day max; split if larger
Delivery trackingStories remaining / completion rate — NO Fibonacci points, velocity, or burndown
Story name{epic}.{story}.{slug}.story.md
Story statusbacklog → ready-for-dev → in-progress → review → done
Decision logDecisions thread through decision-log.md
Project constitutionproject-context.md loaded across skills
Three intentsCreate / Update / Validate where applicable

Available scripts

ScriptPurpose
scripts/scaffold-skill.sh <name>Creates skills/<name>/ with subdirs and starter SKILL.md
scripts/validate-skill.sh <SKILL.md>Validates frontmatter, scope, size, and attribution footer

Invoke with the ${CLAUDE_PLUGIN_ROOT} prefix shown above. The orchestrator marks scripts executable; you may also run them via bash.

Templates

TemplateUse for
templates/skill.template.mdSkeleton for a new planning/orchestration SKILL.md
templates/document.template.mdGeneric planning document (PRD section, brief, spec section, etc.)

Subagent strategy

For creating a full skill package in parallel:

AgentTaskOutput
Agent 1Draft SKILL.md body from gathered requirementsskills/<name>/SKILL.md
Agent 2Write domain scripts (validators, checklists)skills/<name>/scripts/
Agent 3Write domain templatesskills/<name>/templates/
Agent 4Write REFERENCE.md if body exceeds 5K tokensskills/<name>/REFERENCE.md

Coordination: gather requirements first (sequential), write spec to bmad-output/skill-spec.md, then fan out. Main context validates all outputs with validate-skill.sh and assembles the final package.

Notes for LLMs

  • Use TodoWrite to track which components have been created.
  • Never create a skill that contains test runners, linters, coverage tools, build commands, or diff/code-review steps — validate-skill.sh will flag these.
  • Always end SKILL.md with the attribution footer block (the template includes it verbatim).
  • Keep SKILL.md under 5K tokens; use REFERENCE.md for lengthy patterns.
  • Use ${CLAUDE_PLUGIN_ROOT} for all internal paths — never hardcode ~/.claude or absolute machine paths.
  • Output artifacts (non-skill files) go under bmad-output/ by default.

Part of the BMAD Planning & Orchestrator plugin — a Claude Code harness for the BMAD Method by the BMAD Code Organization (https://github.com/bmad-code-org/BMAD-METHOD). Implements the spirit of bmad-bmb-builder. All methodology credit belongs to the BMAD Code Organization.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Bmad Builder AI skill do?

Meta-skill for scaffolding and validating custom PLANNING/ORCHESTRATION skills within the BMAD Planning & Orchestrator plugin. Produces the full skill directory: SKILL.md, scripts, and templates — all pre-targeted at this plugin's path conventions. Includes a scope-violation checker so newly created skills never drift into dev/lint/build/coverage territory. Use when the user says "create a skill", "scaffold a skill", "build a new planning skill", "add a skill to the orchestrator", "extend BMAD planning", "custom orchestration skill", "validate this skill", "check this skill for scope violat...

Why use Bmad Builder on TypingMind?

Because you install it once and use it with any model. Bmad Builder is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bmad Builder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aj-geddes/claude-code-bmad-skills/tree/main/bmad-planning-orchestrator/skills/bmad-builder. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Bmad Builder?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bmad Builder?

As many as you like. As long as a model supports skills, you can use Bmad Builder with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bmad Builder AI skill free?

It is published on GitHub by aj-geddes. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇