bmad-agent-dev

Implements approved stories with test-first discipline as a senior software engineer persona.

Updated Jul 2, 2026
One-click install
npx skills add https://github.com/tuanpa-nhg-eng/nhg-ipms --skill bmad-agent-dev-tuanpa-nhg-eng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bmad-agent-dev
Source: https://github.com/tuanpa-nhg-eng/nhg-ipms/tree/main/.claude/skills/bmad-agent-dev
Command: npx skills add https://github.com/tuanpa-nhg-eng/nhg-ipms --skill bmad-agent-dev-tuanpa-nhg-eng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Executing approved user stories requires disciplined, test-driven implementation that satisfies every acceptance criterion, and ad-hoc coding often skips verification steps or loses project context. ## Core Features & Use Cases - Persona Activation: Adopts the Amelia senior software engineer persona with a customizable role, communication style, principles, and persistent facts loaded from TOML configuration layers. - Test-First Story Execution: Follows red-green-refactor discipline to implement stories so every acceptance criterion is verified by passing tests. - Capability Menu: Dispatches to related workflows including story implementation, E2E test generation, code review, sprint planning, and epic retrospectives. - Use Case: A developer says "hey Amelia, let's implement the next story" and the agent loads project config, persistent facts, and project context files, then executes the story tasks in sequence with tests written first. ## Quick Start Ask Amelia to implement the next approved story from your sprint plan using test-driven development.

Frequently Asked Questions about bmad-agent-dev

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

FAQPage Schema
How do I implement a story with test-driven development using an AI agent?

Invoke the developer agent and name the story to implement. It follows red-green-refactor discipline, executing tasks in the written sequence and requiring passing tests before any task is marked complete.

How do I customize the Amelia developer agent persona?

Create team overrides in _bmad/custom/bmad-agent-dev.toml or personal overrides in a .user.toml file. Scalars override, arrays append, and menu items merge by code, letting you adjust role, style, principles, and menu entries.

What workflows can the developer agent dispatch to?

The menu dispatches to story implementation, API and E2E test generation, multi-facet code review, sprint plan generation, and evidence-based epic retrospectives. You can select by number, code, or a fuzzy description.

Does the agent add story or epic references to code comments?

No. Its principles explicitly forbid epic or story references as inline code comments. Comments must explain why, not what, and generated code must be free of AI workflow metadata and planning references.

What happens if the customization resolver script fails?

The agent falls back to manually reading the base customize.toml, team override, and user override files in order, applying the same structural merge rules itself, so activation continues without the script.