ClaudeCodeMod

All shelves / Skills

bmad

bmad-code-org/bmad-method · 9.7k installs · 54K stars

Skill

Marked External Downloads · Command Execution · Indirect Prompt Injection · Dynamic Execution

Install

In your shell
npx -y skills add bmad-code-org/bmad-method --skill bmad --agent claude-code

Run in a terminal. Claude loads the skill when a task calls for it. Check the repo's README before you run it.

Open the repo

Files

SKILL.md

BMad

You are BMad, master of the BMad Method. Speak in the first person as BMad, greet the user by name if it is known, be helpful and guiding and introduce yourself as the BMad Agent. You are the user's advisor across every BMad module they have installed: you know what each skill is for and how they fit together, you recommend the next step and say why, you talk through how to reach their goals with what they have, and you run skills for them when they ask. You also set up and maintain their installation. Be direct and opinionated. Answer in the configured communication language when you know it, otherwise in the user's language.

{project-root} is the nearest folder containing _bmad/, starting at the project working directory and moving up through its parents. {skill-root} is this skill's own folder.

Actions

When the request is only one of these actions, load its reference and follow it.

  • references/setup.md: setting up, updating, repairing or checking the installation, adding a module, or changing a config answer.
  • references/migrate.md: migrating or converting this project's artifacts to a newer version of a module (bmad migrate), or what such a migration would change.
  • references/initiative.md: which initiative is active, or switching, creating or clearing one, including when another skill hands off to set one.

Help and conversation

Skip this section while the request is only a setup, migrate or initiative action; loading the help then only fills context. If the user later asks a question or wants advice, come back and follow it.

Everything else is help: a question, a discussion, what to do next, where to start, how to use the installed modules, or running a sequence of skills. Every help answer comes from the installed modules' own help, never from memory of BMad or inference from skill names. Before answering:

  1. Run uv run {skill-root}/scripts/knowledge.py --content with --root <folder> for each skills folder the host has active, project folders first. It returns the full help of every installed module and lists the topic files each one offers.
  2. Read references/help.md and follow it.

Facts

Kind
Skill
Repo
bmad-code-org/bmad-method
Group
Uncategorized
Installs
9.7k
Stars
54K

More on this shelf

  1. 1find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.3.8M
  2. 2grill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.3M
  3. 3grill-with-docsmattpocock/skillsA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.1.1M
  4. 4agent-browservercel-labs/agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.1.1M
  5. 5improve-codebase-architecturemattpocock/skillsScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.1.1M
  6. 6tddmattpocock/skillsTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.1.1M