Skills bmad-code-org bmad-method BMad Method
bmad-retrospective
- Use it when:
- An epic in BMad's ticket tree is built and you want to know what it really produced and whether it met its own criteria.
- It does:
- Inventories the epic's tickets, plans, diffs and commits, looks for defects no single ticket could show, and runs bmad-review on the whole diff.
- You get:
- epic-<slug>-retrospective.md in the epic folder, with sourced findings, owned action items and an accepted, accepted-with-open-items or rejected verdict.
- Proposes, not applies:
- Fixes and spec changes become action items for you; besides decision records (ADRs) you approve, the document is all it writes.
- Headless:
- With -H and a named epic it asks nothing and records every assumption in the document.
- Needs:
- uv and BMad set up in the project: run the bmad skill's setup first.
Skill 17 of 24 in the BMad Method bundle, after bmad-qa-generate-e2e-tests and before bmad-project-context.
Only works inside its bundle: Its workflow is printed by a script in the _bmad/ folder that the bmad skill's setup creates, and it reviews an epic from BMad's ticket tree, which Sofia (bmad-agent-po, not listed here) splits into tickets and the build skills carry out, so it does nothing without both. 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 retrospective reads the record an epic left behind rather than anyone's memory of it. It resolves the epic from a folder, id or slug, or offers the finished ones, and warns when tickets are still unfinished, which forces a rejected verdict unless you override it. It then lists what exists and what is missing, using a bundled script to derive each plan's diff range and commits. The analysis looks for problems that only show across the whole epic: changes to the dependency structure, the same problem solved twice, files that grew too large session by session, diverging patterns and gaps between spec and code. It hands the diff to bmad-review for adversarial, edge-case and verification-gap lenses, and exercises changed behavior end to end. A finding without a file, line, commit or log reference is dropped. On request, bmad-party-mode lets BMad's personas discuss the findings. It proposes a decision record (ADR) for each hard-to-reverse choice in the plans and writes only those you approve. The verdict judges the epic against its own requirements and done-when criteria. It also checks whether the previous retro's action items landed, and resumes from its document if interrupted.
Summarizes the skill at e734d3a.
npx skills add https://github.com/bmad-code-org/bmad-method --skill bmad-retrospective skills.sh pageSource on GitHubAll skills from bmad-code-org/bmad-method
- Total Downloads
- 11,500 on skills.sh, Nov 9, 2026
- Repo stars
- 55,140 bmad-code-org/bmad-method
- First seen
- Mar 17, 2026 on skills.sh
Weekly values
| Week to | Installs |
|---|---|
| Sep 21 | 938 |
| Sep 28 | 1,195 |
| Oct 5 | 2,311 |
| Oct 12 | 2,541 |
| Oct 19 | 1,335 |
| Oct 26 | 12 |
| Nov 2 | 195 |
| Nov 9 | 1,492 |
| 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-retrospective
description: 'Review a finished epic folder in the ticket tree against the evidence it left behind — the epic file, each ticket''s story file and plan, diffs, commits — and produce a retrospective with sourced findings, action items, and an acceptance decision. Use when the user says "run a retrospective" or "lets retro the epic [epic]". Supports -H/--headless'Run the following command exactly once without changing the current working directory.
Replace {project-root} with the nearest folder containing _bmad/, from the working directory upward.
Replace {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 does not exist, BMad is not set up in this project yet. Offer to set it up using
bmadskill, then run the command again. If you do not have thebmadskill, offer to install it first. - On any other output or failure, including
uvbeing unavailable, report the command output and stop. Do not run any workflow source directly.