docs(customization): mention bmad-customize in author-facing guides#78
docs(customization): mention bmad-customize in author-facing guides#78
Conversation
Skill authors opt into the customization surface knowing users will hand-write TOML against it. That's now not the default user path — BMad core ships bmad-customize, a conversational authoring helper that scans customizable skills, picks scope, writes the override, and verifies the merge. Authors should pick field names and defaults that read well when a user is walked through them in that flow. Updates two bmb docs: - explanation/customization-for-authors.md: intro paragraph on the downstream authoring path - how-to/make-a-skill-customizable.md: intro note + bullet in the "What You Get" user-experience list No changes to skill source or workflows.
|
Warning Rate limit exceeded
Your organization is not enrolled in usage-based pricing. Contact your admin to enable usage-based pricing to continue reviews beyond the rate limit, or try again in 56 minutes and 30 seconds. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
WalkthroughDocumentation updates clarify that end users utilize the Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Possibly related PRs
Poem
🚥 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 |
🤖 Augment PR SummarySummary: Updates author-facing customization docs to treat 🤖 Was this summary useful? React with 👍 or 👎 |
![augmentcode[bot]](https://avatars.githubusercontent.com/in/1027498?s=60&v=4){kind=small}
|
|
||
| Shipping a `customize.toml` is opt-in per skill. This is the author-side counterpart to [How to Customize BMad](https://docs.bmad-method.org/how-to/customize-bmad/), which covers the end-user view. Read that first if you haven't; it shows what users experience when they override a skill. This guide is about deciding whether to give them that surface at all. | ||
|
|
||
| Downstream users don't hand-write TOML. BMad ships a core skill called `bmad-customize` that walks them through authoring overrides conversationally — it scans which skills are customizable, picks agent vs workflow scope, writes the override file, and verifies the merge. That affects the names and defaults you pick: a user being walked through `"set prd_template to your template path"` handles that fine; `tmpl_override` or `opt_2` makes the conversation awkward. Pick field names that read well out loud. |
There was a problem hiding this comment.
This reads a bit absolute: later docs mention users can still hand-write TOML, so saying they “don’t hand-write TOML” here could be misleading/inconsistent—consider qualifying it similarly (e.g., “don’t typically”).
Severity: medium
🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.
augmentcode review flagged the absolute phrasing as inconsistent with the sibling make-a-skill-customizable.md which says 'won't typically hand-write'. Aligning: add 'typically' and an explicit one-line note that hand-writing still works for users who prefer it. Keeps the naming-implication paragraph intact since that's the point of the note.
1 participant
Summary
bmad-customize(BMad core) as the downstream authoring path. Authors opting a skill into customization now know their users won't typically hand-write TOML — they'll walk through a conversational flow — so scalar names and defaults should read well out loud.Why
BMAD-METHOD#2289 added
bmad-customize, a core skill that scans customizable skills in a project, picks agent-vs-workflow scope, writes the override file to_bmad/custom/, and verifies the merge. Until now the author-side docs framed customization as "users will edit TOML" — that's no longer the primary path, and the shift affects naming judgment (a user being told "setprd_templateto your template path" handles that fine;tmpl_overrideoropt_2makes the conversation awkward).Changes
docs/explanation/customization-for-authors.md— intro paragraph describing thebmad-customizeauthoring flow and what it implies for field naming.docs/how-to/make-a-skill-customizable.md— intro note + new bullet in the "What You Get" user-experience list.Docs only. No changes to skills, workflows, or scripts.
Test plan
customization-for-authors.md).Summary by CodeRabbit