Skills bmad-code-org bmad-method BMad Method
bmad-walkthrough
- Use it when:
- You want to review a commit, PR, file or directory yourself, with the agent as guide, rather than have it review for you.
- It does:
- Splits the target into blocks: its intent, its broad strokes, one slice per concern, then the periphery, and stays on each until you say it's done.
- You get:
- A review narrative with a checkbox per block and a separate log of findings, decisions, edits and tests, in a walkthrough folder.
- Moves:
- A second opinion, a formal review, testing, a demo, a diagram or driving the app; none starts unless you pick it.
- Runs:
- Only when invoked by name.
- Needs:
- uv and BMad set up in the project: run the bmad skill's setup first.
Skill 15 of 24 in the BMad Method bundle, after bmad-code-review and before bmad-qa-generate-e2e-tests.
Only works inside its bundle: Its workflow is printed by a script in the _bmad/ folder that the bmad skill's setup creates, so it does nothing without that setup. Install BMad Method instead.
Needs uv and BMad set up in the project: it runs scripts from the _bmad/ folder that the bmad skill's setup creates.
TL;DR
BMad's walkthrough treats your attention as scarce: it shows only what you need to see and keeps its bookkeeping out of the session. It first works out what the target is and what it's for, reading the ticket when one covers it, then the plan, PR description and commit messages, and asks until it knows. The narrative opens with the intent, quoted from the ticket when there is one, then three to five entry points to open first, then one block per concern that leads with the mechanism and links the exact places, and ends with docs and other small enablers. Every file reference is clickable. On each block it suggests one to three moves, answers your questions with references, and rewrites a block in another shape if you ask, remembering that for later blocks. When you finish a block it shows the next one, checks the finished one off, and asks whether to commit if the tree is dirty. A background subagent writes the files when one is available. At the end it guesses the follow-through, such as merging the PR, and asks before doing it.
Summarizes the skill at e734d3a.
npx skills add https://github.com/bmad-code-org/bmad-method --skill bmad-walkthrough skills.sh pageSource on GitHubAll skills from bmad-code-org/bmad-method
- Total Downloads
- 14,100 on skills.sh, Nov 9, 2026
- Repo stars
- 55,140 bmad-code-org/bmad-method
- First seen
- Aug 28, 2026 on skills.sh
Weekly values
| Week to | Installs |
|---|---|
| Sep 21 | 957 |
| Sep 28 | 1,191 |
| Oct 5 | 2,286 |
| Oct 12 | 2,530 |
| Oct 19 | 1,461 |
| Oct 26 | 1,631 |
| Nov 2 | 1,430 |
| Nov 9 | 1,482 |
| Category |
Find root causes, review code and test what you built. Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills. |
|---|---|
| Type |
A multi-step process the agent follows: interview, debug, run a TDD loop, review. |
| Effect |
Its own steps create or change files, git state or local tools. |
| Needs |
A specific command-line tool or desktop app must be installed, such as gh, agent-browser, LibreOffice, Obsidian or a vendor CLI. |
| Publisher |
Everyone else. Unverified vendor claims default to community. |
| Topics |
SKILL.md
From bmad-code-org/bmad-method at e734d3a. Checked daily, last changed Nov 6, 2026.
Frontmatter
name: bmad-walkthrough
description: 'Guide a human review of a commit, PR, file, or directory. Use when invoked by name'Run the following command exactly once without changing the current working directory. Replace {project-root} with the absolute path to the project root and {skill-root} with the absolute path to this skill's directory:
uv run --no-cache "{project-root}/_bmad/scripts/render_skill.py" --project-root "{project-root}" --skill "{skill-root}"
- The command prints the skill's workflow: follow it.
HALT: <reason>: report the reason and stop. - If the script is not found, BMad is not set up here. Offer to run the
bmadskill's setup, installingbmadfirst if you do not have it (npx skills add bmad-code-org/BMAD-METHOD --skill bmad), then run the command above once more. - On any other failure (including
uvbeing unavailable), report the command output and HALT. Do not run any workflow source directly.