feat(bmm): add improve architecture skill#2474
Open
kylewvl-ship-it wants to merge 2 commits into
Open
Conversation
📝 WalkthroughWalkthroughAdds a new Changesbmad-improve-architecture skill
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
🧹 Nitpick comments (1)
src/bmm-skills/3-solutioning/bmad-improve-architecture/LANGUAGE.md (1)
33-36: 💤 Low valueReduce repetitive sentence starters in LANGUAGE.md and SKILL.md.
Both files open multiple consecutive rules or questions with the same word, creating monotonous repetition flagged by style analysis.
src/bmm-skills/3-solutioning/bmad-improve-architecture/LANGUAGE.md#L33-L36: Lines 33–35 in the Rules section all begin with "Use." Rephrase one or two to vary sentence structure.src/bmm-skills/3-solutioning/bmad-improve-architecture/SKILL.md#L149-L154: Lines 150–152 in the grilling loop all begin with "Which." Rephrase one or two to improve readability.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@src/bmm-skills/3-solutioning/bmad-improve-architecture/LANGUAGE.md` around lines 33 - 36, Reduce repetitive sentence starters across two files. In src/bmm-skills/3-solutioning/bmad-improve-architecture/LANGUAGE.md at lines 33-36, the first three rules all begin with "Use" which creates monotonous repetition—rephrase one or two of these rules to vary the sentence structure (for example, rephrasing one to use imperative phrasing or a different grammatical construction). In src/bmm-skills/3-solutioning/bmad-improve-architecture/SKILL.md at lines 149-154, the grilling loop questions at lines 150-152 all begin with "Which" in a similar repetitive pattern—rephrase one or two of these questions to improve readability by using alternative question structures or starting words.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Nitpick comments:
In `@src/bmm-skills/3-solutioning/bmad-improve-architecture/LANGUAGE.md`:
- Around line 33-36: Reduce repetitive sentence starters across two files. In
src/bmm-skills/3-solutioning/bmad-improve-architecture/LANGUAGE.md at lines
33-36, the first three rules all begin with "Use" which creates monotonous
repetition—rephrase one or two of these rules to vary the sentence structure
(for example, rephrasing one to use imperative phrasing or a different
grammatical construction). In
src/bmm-skills/3-solutioning/bmad-improve-architecture/SKILL.md at lines
149-154, the grilling loop questions at lines 150-152 all begin with "Which" in
a similar repetitive pattern—rephrase one or two of these questions to improve
readability by using alternative question structures or starting words.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 3444f18d-de66-4b1e-8442-456c31b0dabe
⛔ Files ignored due to path filters (1)
src/bmm-skills/module-help.csvis excluded by!**/*.csv
📒 Files selected for processing (5)
src/bmm-skills/3-solutioning/bmad-improve-architecture/DEEPENING.mdsrc/bmm-skills/3-solutioning/bmad-improve-architecture/INTERFACE-DESIGN.mdsrc/bmm-skills/3-solutioning/bmad-improve-architecture/LANGUAGE.mdsrc/bmm-skills/3-solutioning/bmad-improve-architecture/SKILL.mdsrc/bmm-skills/3-solutioning/bmad-improve-architecture/customize.toml
Collaborator
|
@kylewvl-ship-it there are some really good ideas in here, i dont think this needs to be a separate skill though, this could be another mode progressively disclosed if chosen or if an existing architecture is input. could you rework this as a feature of the new bmad-architecture that routes to if user wants to do this. im not sure of the terminology deepen, have never heard that in regards to architecture - maybe there is some more common verbiage. one of the goals with the evolving bmad-architecture and upcoming v7 approach is altitude appropriate decisioning at each layer for the architecture, producing an architectural spine and optional other artifact or deep dive into certain areas as needed. but generally that can be done further down the tree in individual epics, keeping the highest level architecture focused on the invariants and decisions that must be made so lower levels do not make conflicting decisions. |
Author
|
Thank you for the feedback.Im still quite new to this so it helps massively.
…On Thu, Jun 18, 2026 at 5:27 AM Brian ***@***.***> wrote:
*bmadcode* left a comment (bmad-code-org/BMAD-METHOD#2474)
<#2474 (comment)>
@kylewvl-ship-it <https://github.com/kylewvl-ship-it> there are some
really good ideas in here, i dont think this needs to be a separate skill
though, this could be another mode progressively disclosed if chosen or if
an existing architecture is input. could you rework this as a feature of
the new bmad-architecture that routes to if user wants to do this.
im not sure of the terminology deepen, have never heard that in regards to
architecture - maybe there is some more common verbiage.
one of the goals with the evolving bmad-architecture and upcoming v7
approach is altitude appropriate decisioning at each layer for the
architecture, producing an architectural spine and optional other artifact
or deep dive into certain areas as needed. but generally that can be done
further down the tree in individual epics, keeping the highest level
architecture focused on the invariants and decisions that must be made so
lower levels do not make conflicting decisions.
—
Reply to this email directly, view it on GitHub
<#2474?email_source=notifications&email_token=B4S4GWQGFRMV4O32NJZDRZL5ANOTJA5CNFSNUABFM5UWIORPF5TWS5BNNB2WEL2JONZXKZKDN5WW2ZLOOQXTINZTG42TKMRYHA22M4TFMFZW63VHNVSW45DJN5XKKZLWMVXHJLDGN5XXIZLSL5RWY2LDNM#issuecomment-4737552885>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/B4S4GWQP6WCURI6ZIYETKDT5ANOTJAVCNFSNUABFKJSXA33TNF2G64TZHM4TMNJWGE2TCOJQHNEXG43VMU5TINRXGI2DSNJVHE3KC5QC>
.
Triage notifications, keep track of coding agent tasks and review pull
requests on the go with GitHub Mobile for iOS
<https://github.com/notifications/mobile/ios/B4S4GWTICBWGE3XPLIHEWR35ANOTJA5CNFSNUABFM5UWIORPF5TWS5BNNB2WEL2JONZXKZKDN5WW2ZLOOQXTINZTG42TKMRYHA22M4TFMFZW63VHNVSW45DJN5XKKZLWMVXHJKTGN5XXIZLSL5UW64Y>
and Android
<https://github.com/notifications/mobile/android/B4S4GWT6PBKSMU2LETQHW7D5ANOTJA5CNFSNUABFM5UWIORPF5TWS5BNNB2WEL2JONZXKZKDN5WW2ZLOOQXTINZTG42TKMRYHA22M4TFMFZW63VHNVSW45DJN5XKKZLWMVXHJLTGN5XXIZLSL5QW4ZDSN5UWI>.
Download it today!
You are receiving this because you were mentioned.Message ID:
***@***.***>
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Adds bmad-improve-architecture as a built-in BMM skill in the framework source so it is installed with BMAD instead of requiring separate module registration. It also registers the skill in the BMM help catalog so it appears as a first-party solutioning workflow.
Why
This is needed to make the architecture-improvement capability part of the normal BMAD install experience, with the skill already baked into BMM. It removes the extra install/setup step and makes the workflow available immediately in projects that install BMAD.
How
Added a new built-in skill at src/bmm-skills/3-solutioning/bmad-improve-architecture/ with SKILL.md, LANGUAGE.md, DEEPENING.md, INTERFACE-DESIGN.md, and customize.toml.
Adapted the skill to the framework’s built-in BMM workflow model by reading standard BMM config and writing artifacts under {planning_artifacts}/architecture-review.
Registered the new skill in src/bmm-skills/module-help.csv so the installer-generated help/catalog includes it at install time.
Testing
Ran npm ci successfully and ran npm run test:install, which passed. I also attempted the full repo validation path, but npm run quality and npm run validate:skills are currently blocked by existing repo-baseline issues unrelated to this change.