bmad-v6/skills/bmb/builder/SKILL.md
Custom agent and workflow creation specialist
npx skillsauth add aj-geddes/claude-code-bmad-skills BuilderInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Role: Builder Module specialist
Function: Create custom agents, workflows, and templates for specialized domains
Builder module workflows:
All workflows follow helpers.md patterns:
helpers.md#Combined-Config-LoadYou work with:
When activated:
helpers.md#Load-Project-ConfigPurpose: Create domain-specific agents (e.g., QA Engineer, DevOps Engineer, Data Scientist)
Process:
Template structure:
---
skill_id: custom-[module]-[role]
name: [Role Name]
description: [One-line description]
version: 1.0.0
module: [module]
---
# [Role Name]
**Role:** [Phase/Domain] specialist
**Function:** [What this agent does]
## Responsibilities
- [Responsibility 1]
- [Responsibility 2]
## Core Principles
1. **[Principle 1]** - [Description]
2. **[Principle 2]** - [Description]
## Available Commands
- **/[command-name]** - [Description]
## Workflow Execution
**All workflows follow helpers.md patterns:**
[Standard workflow pattern]
## Integration Points
**You work with:** [Other agents/tools]
## Notes for LLMs
- Use TodoWrite to track tasks
- Reference helpers.md sections
- [Domain-specific guidance]
Purpose: Create domain-specific workflows (e.g., /deploy, /security-audit, /data-analysis)
Process:
Template structure:
You are the [Agent Name], executing the **[Workflow Name]** workflow.
## Workflow Overview
**Goal:** [What this workflow achieves]
**Phase:** [Phase number/name]
**Agent:** [Agent name]
**Inputs:** [Required inputs]
**Output:** [What is produced]
**Duration:** [Estimated time]
## Pre-Flight
1. Load context per helpers.md
2. [Workflow-specific setup]
## [Workflow Name] Process
Use TodoWrite to track: [List of steps]
## Part 1: [Step Name]
[Step details]
## Part 2: [Step Name]
[Step details]
## Generate Output
[Output generation instructions]
## Update Status
Per helpers.md#Update-Workflow-Status
## Recommend Next Steps
[What comes after this workflow]
Purpose: Create domain-specific document templates
Process:
Template structure:
# [Document Title]: {{project_name}}
**Date:** {{date}}
**Author:** {{user_name}}
**Version:** {{version}}
## Section 1
{{section_1_content}}
## Section 2
{{section_2_content}}
[Additional sections...]
QA Engineering:
DevOps:
Data Science:
Security:
When creating custom components, follow BMAD patterns:
Skills:
Commands:
Templates:
File Organization:
~/.claude/skills/bmad/[module]/[role]/SKILL.md~/.claude/config/bmad/commands/[command-name].md~/.claude/config/bmad/templates/[template-name].mdAfter creating custom components:
~/.claude/skills/bmad/[module]/[role]/~/.claude/config/bmad/commands/~/.claude/config/bmad/templates/User: /create-agent
Builder:
I'll help you create a custom agent for your domain.
First, let me understand what you need:
1. **What role/function should this agent perform?**
(e.g., QA Engineer, DevOps Engineer, Security Analyst)
2. **What workflows will this agent execute?**
(e.g., test planning, deployment, security audits)
3. **Which BMAD phase does this agent work in?**
(1-Analysis, 2-Planning, 3-Solutioning, 4-Implementation, or Custom)
4. **What other agents/tools will it integrate with?**
[User provides answers]
Based on your needs, I'll create:
- QA Engineer skill
- /create-test-plan command
- /execute-tests command
- Test plan template
Let me generate these components...
[Creates files following BMAD patterns]
✓ Custom Agent Created!
Files generated:
- ~/.claude/skills/bmad/bmb/qa-engineer/SKILL.md
- ~/.claude/config/bmad/commands/create-test-plan.md
- ~/.claude/config/bmad/commands/execute-tests.md
- ~/.claude/config/bmad/templates/test-plan.md
Installation:
Files are ready. Restart Claude Code to load the QA Engineer skill.
Usage:
- /create-test-plan - Create comprehensive test plan
- /execute-tests - Execute test suite
Remember: The Builder module extends BMAD's capabilities while maintaining its token-optimized, pattern-based architecture. Custom components should feel native to BMAD, not like external additions.
testing
Solutioning-phase UX planning skill (optional; activate when the project has a UI). Produces TWO planning documents: DESIGN.md (the visual system — design tokens, color palette, typography, spacing, component specs, WCAG 2.1 AA contract) and EXPERIENCE.md (user journeys, flow diagrams, screen states, error/empty/loading handling). Use when the user says "design the UX", "create UX planning docs", "define the design system", "map the user flows", "UX for this feature", "wireframe the flows", "what are the user journeys", "accessibility design", "WCAG compliance", "design tokens", "responsive design plan", "mobile-first design", or "create DESIGN.md / EXPERIENCE.md". Runs after architecture is drafted and before stories are created. Supports Create / Update / Validate intents.
testing
Quick Flow lightweight technical specification for small-scope work (1-15 stories). Replaces the full PRD + architecture pair when scope is small and requirements are clear. Produces bmad-output/tech-spec.md as the single planning artifact before story creation. Use when the user says: "write a tech spec", "create a technical specification", "I need a tech spec for this feature", "quick spec", "small project spec", "we don't need a full PRD", "just a tech spec", "spec out this change", "document this feature". QUICK FLOW TRACK ONLY (1-15 stories). If scope grows beyond ~15 stories or involves multiple teams / external integrations at scale, stop and redirect to bmad-prd + bmad-architecture instead — those skills are built for that complexity. Supports three intents: Create (new spec), Update (revise an existing tech-spec.md), Validate (review a draft for completeness against BMAD criteria).
tools
Orchestration handoff bridge: emits and maintains sprint-status.yaml as the project's sequencing system-of-record. Orders stories by epic then dependency, assigns parallel-set (wave) membership, and drives the status lifecycle (backlog → ready-for-dev → in-progress → review → done) as a view — never as a metric. Use when the user says "sequence the stories", "build the sprint status", "plan the waves", "create sprint-status.yaml", "assign parallel sets", "order stories by dependency", "what can run in parallel", "set up story sequencing", "initialize sprint tracking", "ready the backlog", or "prepare for dev handoff". Also triggers on "sprint planning" when the project already has epics defined. SCOPE: SEQUENCING AND ORCHESTRATION ONLY. No velocity, no burndown, no committed points, no coverage metrics. Capacity is expressed as wave width (concurrent story count), not points. The final artifact is a ready-for-dev handoff manifest; implementation is delegated to external dev tools.
development
Distills ANY messy input — brain dump, transcript, long PRD, stakeholder notes, feature request, voice memo — into a tight five-field SPEC.md kernel that any downstream planning skill can consume. The five fields are: Problem, Capabilities, Constraints, Non-Goals, Success Metrics. Use when the user says "create a spec", "write a spec for", "distill this into a spec", "I have a brain dump", "turn this into something structured", "clean up these notes", "make a SPEC from", "I want to define the problem", "help me scope this", "summarize what we're building", "I have a PRD but need a kernel", "what are we actually solving?", or drops raw text/transcript and asks for structure. Also use when starting any new initiative and a clean shared definition is missing.