bmad-retrospective
Runs a structured retrospective on a completed epic by reviewing the evidence it left behind — spec, stories, diffs, commits and sprint status — and produces sourced findings, action items and an acceptance decision. Use it at the end of an iteration when you want a defensible, evidence-based retro instead of a memory-driven discussion, so lessons and follow-ups are captured and traceable.
npx skills add https://github.com/bmad-code-org/bmad-method --skill bmad-retrospectiveBefore / After Comparison
3 组After an iteration, the team reconstructs the retro from memory and scattered chat logs, digging through commits and specs for half a day and still missing key changes.
This Skill aggregates spec, stories, diffs, commits and sprint status automatically, delivering a sourced findings list so the team walks in ready to decide.
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}"
- On success, read and follow the one absolute
workflow.mdinstruction printed to stdout. - If
{project-root}/_bmad/scripts/render_skill.pyis not found, this BMad installation is not set up yet: read the installedbmadskill's SKILL.md (a sibling of this skill's directory) and follow its setup flow, 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.
User Reviews (0)
Write a Review
No reviews yet
Statistics
User Rating
Rate this Skill