BMad Dev Skill for Claude: Amelia, Your Test-First Engineer

Makes Claude act as Amelia, a BMad senior engineer who implements stories test-first and cites file paths and acceptance criteria.

Installs: 13.2K; on skills.sh
Stars: 54.9K; on GitHub
Files: 2; besides SKILL.md
Updated: Nov 2026; last repo commit

bmad-agent-dev turns Claude into Amelia, the Senior Software Engineer from the BMad Method. SKILL.md says she executes approved stories test-first, in red, green, refactor order, and speaks in file paths and acceptance-criteria IDs. Claude greets you as Amelia, marks messages with a laptop icon and stays in character until you dismiss her.

Ask to talk to Amelia or to the developer agent and it triggers. On start it runs two uv scripts from your project's _bmad folder and reads the active ticket, then shows a menu of four items that call other BMad skills. This skill is only the persona and menu, so you need the rest of the BMad set installed.

Good for

Developers who want Claude to implement approved stories with red, green, refactor discipline
Teams using BMad tickets and acceptance criteria to drive work
Reviewers who want a code review or epic retrospective started from one menu

Install bmad-agent-dev

Claude Code

Copy this prompt.

Install the bmad-agent-dev skill in Claude Code. Run this command:

/plugin marketplace add bmad-code-org/bmad-plugins
/plugin install bmad-method@bmad
/plugin install bmad-toolbox@bmad

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires uv.

Install the whole BMad set, not just this skill: it calls scripts and sibling skills that the set provides. After installing, open your coding tool in the project and ask the bmad skill to run bmad setup. Every route needs uv (the README says both routes need it for setup and Python scripts). This is the v7 preview alpha, so expect breaking changes between updates. Plugin names differ between sources: the BMAD-METHOD README says to install bmad-method and bmad-core-tools, but the bmad-plugins README and its marketplace manifest list bmad-method and bmad-toolbox, and the bmad skill sits in the toolbox plugin's skills folder. Use the names that /plugin shows after you add the marketplace. Pick one route, not both.

From the project README. Source.

What's in the skill

When it loads

Senior software engineer who implements stories and code changes. Use when the user asks to talk to Amelia or requests the developer agent

Sections in SKILL.md

Overview
Conventions
On Activation
Step 1: Resolve the Agent Block
Step 2: Execute Prepend Steps
Step 3: Adopt Persona
Step 4: Load Persistent Facts
Step 5: Load Config
Step 6: Greet the User
Step 7: Execute Append Steps
Step 8: Dispatch or Present the Menu

Key facts

Author: bmad-code-org (BMad Code); the plugin marketplace lists Brian (BMad) Madison as owner
License: GitHub detects none for the repo (NOASSERTION); the README and plugin marketplace say MIT
Installs on skills.sh: 13,244 as of 2026-11-02
GitHub stars: 54,859 for the whole BMAD-METHOD repo
Last commit to the repo: 2026-11-01
Files in the skill: 3 files including SKILL.md: bmod.toml, customize.toml
Needs: uv (README), plus the bmad setup skill so the _bmad/scripts folder exists
skills.sh audits: Gen Agent Trust Hub warn, Socket pass, Snyk pass

What it includes

Loads the persona, your facts and config, then greets you as Amelia.
Claude resolves the agent settings with a uv script, runs any extra steps you configured, adopts the persona, loads persistent facts and the output folder, greets you and runs the append steps.
Runs code · Activation (8 steps)
Implements a feature, fix or story through bmad-build.
Hands the work to the bmad-build skill.
Try: “Hey Amelia, let's implement the next story.”
Write · Menu: BD
Generates API and E2E tests for existing features.
Hands the work to the bmad-qa-generate-e2e-tests skill.
Write · Menu: QA
Starts a code review across several quality facets.
Hands the work to the bmad-code-review skill.
Read · Menu: CR
Reviews a finished epic against its acceptance criteria.
Hands the work to the bmad-retrospective skill for an evidence-based review.
Read · Menu: ER
Tests must pass, tasks run in order, comments explain why.
Defaults include: read the ticket in full before coding, no task complete without passing tests, red then green then refactor, and no epic or story references in code comments.
Read · Persona principles

From the official docs

Permissions

Medium risk

The menu items hand off to skills that change code in your repo, and the skill runs uv scripts from your project. Work on a branch and read the diff before you commit.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Its menu items write and change code
The menu hands off to bmad-build (implement a feature, fix or story), bmad-qa-generate-e2e-tests, bmad-code-review and bmad-retrospective. Implementing means editing files in your repo, so work on a branch and read the diff before you commit. github.com
It runs uv scripts from your project
SKILL.md tells Claude to run resolve_customization.py and resolve_config.py with uv from a _bmad/scripts folder in your project. Those scripts come from the bmad skill, not from this folder, so read them there if you want to know what they do. github.com
Project override files steer Claude
Claude reads customize.toml plus optional team and personal override files under _bmad/custom, and runs their activation steps and persistent facts. Anyone who can edit those files in your repo can change what the agent does, so review them in pull requests. github.com
The persona stays on until you dismiss it
SKILL.md says not to break character until you dismiss the persona, and the persona carries into any skill it calls. Say so plainly when you want Claude back to normal. github.com

Technical details

Sign-in and keys	SKILL.md names no sign-in or API key.
Scopes	Runs uv scripts from _bmad/scripts in your project Menu skills implement code and tests in your project

Questions

What does the bmad-agent-dev skill do?

It makes Claude play Amelia, the BMad Method's Senior Software Engineer. She works test-first from an approved ticket and offers menu items for building, E2E tests, code review and epic review.

How do I install bmad-agent-dev?

Use the install box above and install the whole BMad set. This skill runs scripts and calls skills that the set provides, so installing it alone does not work. Then ask the bmad skill to run bmad setup.

Does it need an API key?

SKILL.md names no API key. It does need uv, which the README lists as required for BMad setup and its Python scripts.

Is bmad-agent-dev safe to run?

It runs uv scripts from your project's _bmad folder and follows any steps in your customization files, so review those before you trust a repo you did not write. Amelia stays in character until you dismiss the persona. The Permissions section lists the details.

Does it work in Claude.ai, Codex or Cursor?

The README documents a Claude Code plugin, a Codex plugin and a skills CLI install that asks which coding tool to target. It says you need a coding tool that supports skills. It does not name Cursor or the Claude app, and the skill needs a local project folder and uv.

bmad-agent-dev vs bmad-build?

The agent is a persona with a menu, and bmad-build is the skill behind its BD item, which implements a feature, fix or story. You can invoke bmad-build directly without talking to Amelia.

Information

updated Nov 2, 2026

Repository: bmad-code-org/bmad-method
Folder: skills/bmad-agent-dev

bmad-code-org/bmad-method skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 5

BMAD-METHOD README · github.com
bmad-plugins README · github.com
bmad-agent-dev SKILL.md · github.com
bmad-agent-dev customize.toml · github.com
bmad skill memlog.py · github.com