skills.rest
ImaginerLabs
ImaginerLabsOFFICIAL
Explore all skills by this author →
GitHub

bmad-agent-builder

Build, edit, and analyze AI agent skills with conversational discovery and scaffolding.

Updated Apr 10, 2026
Search Tags:#headless#quality-analysis#agent-builder#template-scaffolding#sanctum#init-scripts#conversational-discovery
One-click install
npx skills add https://github.com/ImaginerLabs/skill-manager --skill bmad-agent-builder
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-agent-builder
Source: https://github.com/ImaginerLabs/skill-manager/tree/main/.trae/skills/bmad-agent-builder
Command: npx skills add https://github.com/ImaginerLabs/skill-manager --skill bmad-agent-builder

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Helps creators and engineers rapidly design, convert, and quality-check AI agent skills by running a structured conversational discovery process and producing a ready-to-use skill bundle. It removes the manual toil of scaffolding persona, capabilities, memory sanctum templates, and headless execution paths so agents are consistent, outcome-focused, and IDE-ready.

Core Features & Use Cases

  • Conversational Discovery & Build: Guided six-phase discovery that turns a user's vision into a stateless, memory, or autonomous agent with seeded sanctum templates.
  • Edit, Analyze, Rebuild: Convert or improve existing agents through targeted analysis, pruning over-specification, and regenerating lean capability prompts.
  • Headless & Reports: Support for --headless automation, init-sanctum scaffolding, and quality-analysis report generation for CI or scheduled runs.
  • Use Case: Convert a verbose agent into an outcome-driven memory agent with seeded PERSONA/CREED/BOND files, capability prompts in references/, and an init script to create the sanctum.

Quick Start

Ask the builder to create or analyze an agent by saying a natural command like: create an agent that is a concise Python code reviewer with optional memory and headless report generation.

Frequently Asked Questions about bmad-agent-builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I scaffold an AI agent with seeded memory templates?▼

You can scaffold an AI agent with seeded memory templates through a conversational discovery process that generates persona, creed, and bond files alongside capability prompts. This produces a ready-to-use skill bundle with init-sanctum templates for immediate IDE synchronization.

What is conversational discovery for building outcome-driven agents?▼

Conversational discovery is a guided six-phase process that turns your agent vision into a stateless, memory, or autonomous agent. It removes manual toil by automatically scaffolding sanctum templates and capability prompts to ensure agents are consistent and outcome-focused.

Can I convert an existing verbose agent into a lean, outcome-driven build?▼

Yes, you can convert existing agents by running targeted analysis to prune over-specification and regenerate lean capability prompts. This rebuilds verbose agents into outcome-driven memory agents with properly seeded reference files and sanctum templates.

Does the agent builder support headless automation for CI pipelines?▼

The agent builder supports headless automation through a dedicated --headless mode. It generates quality-analysis reports and outputs complete skill structures suitable for CI pipelines or scheduled runs without interactive input.

Do I need pyyaml installed to run the agent scaffolding scripts?▼

Yes, pyyaml is a required dependency for running the agent scaffolding scripts. The skill relies on it to parse bmad configuration files and process the YAML structures needed for sanctum template seeding.

When should I use headless mode versus interactive conversational discovery?▼

Use interactive conversational discovery when designing new agents or converting existing ones visually. Use headless mode when automating quality-analysis report generation, running scheduled CI checks, or producing builds without interactive user input.

Related Skills

Explore More Software Engineering Skills→
mol4mol4
1

bmad-agent-builder

Build, analyze, and edit BMad agent skills from SKILL.md files.

Community
Advanced
b566776b566776

bmad-agent-builder

Build, edit, and analyze agent skills through guided conversational discovery.

Community
Advanced
escarfaceescarface

senior-devops

Automate CI/CD pipelines, Terraform scaffolding, and deployments across AWS, GCP, and Azure.

Community
Advanced
markaheskethmarkahesketh

agent-skill

Guide users through building structured Claude Code agent skills interactively.

Community
Advanced