skills.rest
ncptuan
ncptuanCOMMUNITY
Explore all skills by this author →
GitHub

bmad-agent-builder

Build, edit, and quality-analyze AI agent Skills via conversational discovery.

Updated Apr 23, 2026
Search Tags:#workflow automation#prompt engineering#skill generation#autonomous agents#quality analysis#agent builder#memory agents
One-click install
npx skills add https://github.com/ncptuan/stock_backtest_project --skill bmad-agent-builder-ncptuan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-agent-builder
Source: https://github.com/ncptuan/stock_backtest_project/tree/main/.claude/skills/bmad-agent-builder
Command: npx skills add https://github.com/ncptuan/stock_backtest_project --skill bmad-agent-builder-ncptuan

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps you create, edit, rebuild, and quality-check AI agent Skills without manually designing every file, prompt, template, and memory structure yourself. It turns vague agent ideas into structured, outcome-driven agent packages with clear personas, capabilities, optional memory, and autonomous behavior.

Core Features & Use Cases

  • Conversational Agent Building: Guides users through a multi-phase discovery process to define an agent's identity, mission, capabilities, activation flow, and customization surface.
  • Supports Multiple Agent Types: Builds stateless agents, memory agents with sanctum files, and autonomous agents with Pulse behavior for headless operation.
  • Editing and Rebuilding Existing Agents: Analyzes an existing agent as intent material, then either makes targeted edits or fully rethinks the design around core outcomes.
  • Quality Analysis Workflow: Runs deterministic scans and orchestrates deeper quality reviews for structure, prompt craft, execution efficiency, sanctum architecture, customization, and enhancement opportunities.
  • Use Case: Ideal when a team wants to create a reusable internal AI agent, convert a verbose prompt into a maintainable skill, or audit an existing agent for over-specification and structural issues.

Quick Start

Ask the bmad-agent-builder skill to create a new agent for your use case, or give it an existing agent path and ask it to analyze, edit, or rebuild it.

Frequently Asked Questions about bmad-agent-builder

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

FAQPage Schema
How do I build an autonomous AI agent with memory and headless behavior?▼

You can build autonomous AI agents with memory and headless behavior using guided conversational discovery to define personas, capabilities, and sanctum scaffolding. This process generates structured YAML-frontmatter skills, template-based files, and script-assisted validation for stateless, memory, and autonomous agents.

What is the best way to convert a verbose prompt into a maintainable AI agent skill?▼

Converting a verbose prompt into a maintainable skill involves analyzing the existing prompt as intent material, then rethinking the design around core outcomes. This creates a structured agent package with clear personas, capabilities, and optional memory without manual file design.

How do I audit an existing AI agent for over-specification and structural issues?▼

Auditing an existing AI agent for over-specification requires running deterministic scans and orchestrating deeper quality reviews. This workflow checks structure, prompt craft, execution efficiency, sanctum architecture, customization, and identifies enhancement opportunities.

Can I edit and rebuild existing agent packages without starting from scratch?▼

Yes, you can edit and rebuild existing agent packages by providing the agent path. The system analyzes the existing agent as intent material, then either makes targeted edits or fully rethinks the design around core outcomes to generate a new structured package.

Do I need pyyaml to generate AI agent skills with YAML frontmatter?▼

Yes, pyyaml is required as a dependency to generate AI agent skills with YAML frontmatter. This dependency supports the script-assisted validation and template-based file creation needed for structured agent packages.

Related Skills

Explore More Software Engineering Skills→
JkkerJkker

tanstack-intent

Map TanStack Intent skills from installed npm packages to agent tasks.

Community
Advanced
GraffiohGraffioh

improve-skill

Analyze coding agent session transcripts to generate SKILL.md improvements.

Community
Intermediate
arbazkhan971arbazkhan971
26

agent

Design and validate autonomous AI agents with tool orchestration and guardrails.

Community
Advanced
markaheskethmarkahesketh

agent-skill

Guide users through building structured Claude Code agent skills interactively.

Community
Advanced