docs: update terminology from commands to skills#1850
Merged
alexeyv merged 1 commit intobmad-code-org:mainfrom Mar 7, 2026
Merged
docs: update terminology from commands to skills#1850alexeyv merged 1 commit intobmad-code-org:mainfrom
alexeyv merged 1 commit intobmad-code-org:mainfrom
Conversation
🤖 Augment PR SummarySummary: Updates BMad Method documentation to reflect the v6 skills-based architecture (vs. legacy “commands” / “slash commands”). Changes:
Why: Keep docs consistent with the installer-generated skills and the post-#1834 skills-first UX so users don’t follow outdated command names. 🤖 Was this summary useful? React with 👍 or 👎 |
![augmentcode[bot]](https://avatars.githubusercontent.com/in/1027498?s=60&v=4){kind=small}
📝 WalkthroughWalkthroughThis PR updates documentation across the BMAD project to reflect a terminology shift from "commands" to "skills" and standardizes workflow names with consistent Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Suggested reviewers
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 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.
Actionable comments posted: 13
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (9)
docs/reference/testing.md (1)
54-54:⚠️ Potential issue | 🟡 MinorDocument the Code Review skill ID alongside the trigger.
Line 54 references the
CRtrigger but doesn't mention the corresponding skill ID (bmad-code-review). Given that this PR is migrating documentation to "skills" terminology, this line should clarify that users can invoke either via theCRmenu trigger or the fullbmad-code-reviewskill ID, consistent with line 29's pattern for Quinn.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/reference/testing.md` at line 54, Update the sentence that currently references only the `CR` trigger to mention both the trigger and the full skill ID: state that users can invoke the Code Review workflow via the `CR` menu trigger or the `bmad-code-review` skill ID (mirroring the pattern used for Quinn). Modify the line mentioning "Quinn generates tests only. For code review and story validation, use the Code Review workflow (`CR`) instead." to append or replace with the explicit skill ID so it reads that Code Review can be invoked as `CR` or `bmad-code-review`.docs/how-to/get-answers-about-bmad.md (1)
21-33:⚠️ Potential issue | 🔴 CriticalSelf-contradictory guidance on skill invocation syntax.
Line 21 says "Run it with just the skill name:" (implying no slash), but lines 24-33 immediately show
/bmad-helpwith a leading slash in all examples. This is a direct contradiction within the same section.Either:
- Change line 21 to "Run it with the skill:" and keep the slashes, or
- Remove the slashes from lines 24-33 to match "just the skill name"
The current phrasing tells users to do one thing, then demonstrates the opposite.
Proposed fix to align instruction with examples
-Run it with just the skill name: +Run the skill directly:or remove slashes from examples:
-/bmad-help
+bmad-help🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/how-to/get-answers-about-bmad.md` around lines 21 - 33, The guidance is contradictory: the header says "Run it with just the skill name:" but the examples use "/bmad-help" with a leading slash; fix by making the instruction and examples consistent—either change the header text to "Run it with the skill:" (keep the examples as "/bmad-help" and the other slash-prefixed examples) or remove the slashes from each example (replace "/bmad-help" with "bmad-help" and similarly for the other examples) so the phrase and the examples match; update whichever you choose throughout this section including every occurrence of "/bmad-help" or "bmad-help".docs/how-to/shard-large-documents.md (1)
44-44:⚠️ Potential issue | 🟠 MajorSlash usage inconsistency across documentation.
Line 44 shows
/bmad-shard-docwith a slash in the bash block, which contradictsdocs/how-to/project-context.mdlines 80 and 90 where bash blocks showbmad-generate-project-contextWITHOUT a slash. Within this same file, line 8 showsbmad-shard-docwithout a slash.Are these skill invocations slash-commands (IDE/chat-specific) or command-line utilities? The documentation provides no guidance on when the slash is required, creating confusion for users trying to invoke skills.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/how-to/shard-large-documents.md` at line 44, The docs use inconsistent slash prefixes for skill invocations (e.g. `/bmad-shard-doc` vs `bmad-shard-doc` and `bmad-generate-project-context`); decide whether these are CLI commands or chat/IDE slash-commands, then make the docs consistent: remove the leading slash from all bash/code block usages (e.g. change `/bmad-shard-doc` to `bmad-shard-doc`) if they are CLI tools, or keep the slash only where you explicitly show chat/IDE slash-command examples; update docs/how-to/shard-large-doc and docs/how-to/project-context.md (and any other occurrences) and add a short clarifying note near the top of each how-to stating when to use the slash form (chat/IDE) versus the plain form (terminal/CLI) with one example of each.docs/tutorials/getting-started.md (5)
156-173:⚠️ Potential issue | 🟠 MajorThe solutioning steps still document deprecated invocation syntax.
Both architecture and readiness examples keep the slash-prefixed form even though the same page now introduces skills as bare invocations.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/tutorials/getting-started.md` around lines 156 - 173, Update the documented invocation syntax to the new bare skill form: replace all slash-prefixed commands in these steps (e.g., "/bmad-architect", "/bmad-create-architecture", "/bmad-pm", "/bmad-create-epics-and-stories", "/bmad-check-implementation-readiness") with their bare counterparts (bmad-architect, bmad-create-architecture, bmad-pm, bmad-create-epics-and-stories, bmad-check-implementation-readiness) so the Architecture, Epics/Stories, and Implementation Readiness sections use the same bare invocation style introduced earlier on the page.
61-63:⚠️ Potential issue | 🟠 MajorThis tip reintroduces slash-command syntax right after you replaced it.
Lines 40-49 already establish
bmad-helpas the skill invocation format. Sending readers back to/bmad-helphere makes the migration look half-done.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/tutorials/getting-started.md` around lines 61 - 63, The tip block reintroduces slash-command syntax by referencing `/bmad-help`; update that reference to the new invocation format `bmad-help` so it matches the earlier lines (40-49) and preserves consistency—modify the text inside the tip (the :::tip[...] block) to remove the leading slash and use `bmad-help` as the skill invocation.
23-27:⚠️ Potential issue | 🟠 MajorThe first-run shortcut still teaches the deprecated slash form.
The page later switches to bare skill invocation, but the "Easiest Path" still tells readers to ask via
/bmad-help. New users will copy the first example they see.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/tutorials/getting-started.md` around lines 23 - 27, Update the "Easiest Path" tip so it no longer shows the deprecated slash command form; replace the `/bmad-help what should I do first?` example with the current bare skill invocation (e.g., `bmad-help what should I do first?`) in the tip block so it matches the later examples and prevents readers from copying the deprecated form.
104-111:⚠️ Potential issue | 🟠 MajorThe post-install step is still documented in the old invocation format.
This is another place where the tutorial tells users to run
/bmad-helpinstead of invoking thebmad-helpskill directly.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/tutorials/getting-started.md` around lines 104 - 111, The tutorial still shows the old slash-invocation "/bmad-help"; update the text to instruct users to invoke the bmad-help skill directly by replacing "/bmad-help" with "bmad-help" (e.g., "Invoke the bmad-help skill" or "Run the bmad-help skill in your AI IDE") in the docs/tutorials/getting-started.md content around the tip block so the messaging matches the new invocation format.
252-273:⚠️ Potential issue | 🟠 MajorThe help and takeaway sections still teach
/bmad-help.Ending the tutorial with the old slash form makes the entire migration look inconsistent, even after earlier sections introduced
bmad-helpcorrectly.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/tutorials/getting-started.md` around lines 252 - 273, The docs still reference the old slash command `/bmad-help`; update the tutorial text to use the new command name without the leading slash (replace `/bmad-help` with `bmad-help`) in the headings and Key Takeaways (the instances in the "Run `/bmad-help` anytime" line and "Start with `/bmad-help`" bullet) so the language matches the earlier sections that use `bmad-help`.docs/_STYLE_GUIDE.md (1)
246-256:⚠️ Potential issue | 🟠 MajorDefine one canonical skill invocation format here.
These templates now expose
Skillas a first-class field, but they never pin down whether invocation examples must be bare skill names or slash-prefixed commands. That ambiguity is already showing up indocs/tutorials/getting-started.md, which mixes both on the same page.Also applies to: 283-284
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/_STYLE_GUIDE.md` around lines 246 - 256, Define and enforce a single canonical skill-invocation format for the templates: decide whether the `Skill` field examples should use bare names (e.g., "translate") or slash-prefixed commands (e.g., "/translate"), then update the "Item Deep-Dive Reference" template and any template examples that surface `Skill` so they consistently use that chosen format; also sweep tutorial content (the getting-started examples that currently mix both forms) and replace mismatched examples to match the canonical form to avoid ambiguity.
🧹 Nitpick comments (3)
docs/reference/workflow-map.md (1)
87-87: Inconsistent invocation pattern in context generation.Line 87 says "Run
bmad-generate-project-context" using "Run" as the verb, but throughout the other files we've seen "invoke" (quick-fixes.md), and the skills terminology document doesn't standardize on a verb. The doc should pick one verb and stick with it: "invoke a skill", "run a skill", or "use a skill".🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/reference/workflow-map.md` at line 87, Replace the inconsistent verb "Run" in the workflow-map entry for the command `bmad-generate-project-context` with the project's chosen verb "Invoke" to match other docs (e.g., quick-fixes.md and the skills terminology document); update the line to read "Invoke `bmad-generate-project-context` to auto-generate from your architecture or codebase" so the invocation pattern is consistent across documents.docs/how-to/quick-fixes.md (1)
33-47: Inconsistent verb choice muddles the mental model.Lines 33-41 establish "invoke" as the verb for starting a skill. But line 47 says "Once the Solo Dev agent is loaded" — suddenly using "loaded" instead. This inconsistency matters because "invoke a skill" and "load an agent" could be different operations in the user's mental model. Stick to one verb throughout the section.
♻️ Proposed consistency fix
-Once the Solo Dev agent is loaded, describe your change and ask it to create a **quick-spec**. +Once the Solo Dev agent is invoked, describe your change and ask it to create a **quick-spec**.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/how-to/quick-fixes.md` around lines 33 - 47, The section uses mixed verbs ("invoke" in the headings and examples like "bmad-dev" and "bmad-quick-flow-solo-dev" but then switches to "loaded" in the sentence "Once the Solo Dev agent is loaded"), so update the wording to use a single consistent verb (preferably "invoke") throughout: change "Once the Solo Dev agent is loaded" to "Once the Solo Dev agent is invoked" and scan nearby sentences in the "Invoke the DEV Agent" block to ensure all references to starting or activating the agent use "invoke" (references: heading "Invoke the DEV Agent", commands "bmad-dev" and "bmad-quick-flow-solo-dev", and the phrase "Once the Solo Dev agent is loaded").docs/explanation/quick-flow.md (1)
33-35: Inconsistent naming: header vs. skill ID.Line 33 header says "quick-spec: Plan" but line 35 says to run
bmad-quick-spec. This discrepancy matters: if a user reads just the header, they might try to invoke "quick-spec" (without the bmad- prefix) and fail. Either use the full skill ID in headers or add a note that headers use short names.♻️ Proposed fix
-### quick-spec: Plan +### bmad-quick-spec: Plan -Run `bmad-quick-spec` and Barry (the Quick Flow agent) walks you through a conversational discovery process: +Barry (the Quick Flow agent) walks you through a conversational discovery process:🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/explanation/quick-flow.md` around lines 33 - 35, The header "quick-spec: Plan" and the invocation `bmad-quick-spec` are inconsistent; update the header to use the full skill ID "bmad-quick-spec: Plan" or add a one-line note under the header clarifying that headers show a short name while commands use the full skill ID (e.g., "Run `bmad-quick-spec`"); edit the header text "quick-spec: Plan" or insert the clarification immediately after it so readers won't try the wrong command.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@docs/_STYLE_GUIDE.md`:
- Around line 62-69: The guide mixes legacy "Command" terminology with the
standardized "Skill" term; update the docs to remove all uses of "Command"
(e.g., the earlier heading or section titled "Command/response examples") and
replace them with "Skill" (e.g., "Skill/response examples") so terminology is
consistent with the "Skills" table shown; search for and replace occurrences of
"Command" and "Command/response examples" in the file and adjust any surrounding
examples or labels to use "Skill" and "Skill/response" instead.
In `@docs/explanation/quick-flow.md`:
- Around line 48-49: The examples omitted the required skill prefix so users
copying commands like quick-dev tech-spec-auth.md or quick-dev "refactor..."
will get "skill not found"; update the doc to use the full skill name
bmad-quick-dev in both example commands (e.g., bmad-quick-dev tech-spec-auth.md
and bmad-quick-dev "refactor the auth middleware") or alternatively add a
one-line note explaining that the prefix may be omitted only when using shell
tab-completion/alias and is not supported by copy-paste.
In `@docs/how-to/established-projects.md`:
- Around line 71-73: The examples using "bmad-help I have an existing Rails
app..." are ambiguous about the interaction model; update the examples that
contain the phrases "bmad-help I have an existing Rails app", "bmad-help What's
the difference between quick-flow and full method?", and "bmad-help Show me what
workflows are available" to explicitly show whether they are literal CLI
commands or chat/IDE prompts—for CLI show the exact command syntax (e.g.,
command name and quoted argument) and mark it as a shell example, or else
rephrase to "In IDE chat, ask: 'I have an existing Rails app...'" and label it
as an IDE/chat example so readers know how to invoke bmad-help.
In `@docs/how-to/install-bmad.md`:
- Around line 56-58: The "Enabling Skills" note is circular and unhelpful;
update it to include explicit steps or direct links for each supported IDE
(Claude Code, Cursor, Windsurf) rather than suggesting users "ask your AI
assistant." Replace the vague sentence with either (1) short, actionable
instructions for where to toggle/enable skills in each IDE's settings, or (2)
hyperlinks to the official docs/tutorial pages for enabling skills on Claude
Code, Cursor, and Windsurf, and add a brief sentence telling users what to do if
their platform is not listed (e.g., contact support or consult platform docs).
- Line 81: The example lists an undocumented skill folder "bmad-persona/";
either remove "bmad-persona/" from the installed-skills example or add
documentation for that skill by updating skills.md (explain its commands and
purpose) and workflow-map.md (show where it fits in workflows). Ensure the
example and the docs remain consistent so readers don't see "bmad-persona/"
without an explanation.
In `@docs/how-to/quick-fixes.md`:
- Around line 41-47: Clarify the relationship and decision guidance between the
agent and the workflow skill: explicitly state that bmad-quick-flow-solo-dev is
an interactive agent that runs a full solo dev loop (drafts spec, implements
change, runs tests, self-reviews) and that bmad-quick-spec is a standalone
workflow skill used when you only need an automated quick-spec artifact (no
automated implementation/testing); add a short sentence telling readers when to
choose each (use bmad-quick-spec if you only want a spec to hand to a dev or
another workflow, use bmad-quick-flow-solo-dev if you want the agent to draft
the spec and continue to implement and test automatically), and update the
paragraph referencing lines that mention creating a quick-spec to point to
bmad-quick-spec as the skill to call directly when appropriate.
In `@docs/how-to/upgrade-to-v6.md`:
- Line 38: The current line "look for any nested folders that start with bmad
and remove them" is too vague and risky; update the doc sentence under "Manually
remove legacy v4 IDE commands/skills" to provide a safe, precise procedure:
instruct users to first make a backup (zip or git commit), then define "nested"
as "any depth under the IDE workspace", show how to identify candidates by
matching the exact prefix "bmad-" (not any folder containing "bmad"), recommend
a dry-run search (e.g., list matches before deletion), instruct them to skip
folders that match known custom patterns like "bmad-custom-*" or confirm intent
before removal, and add an example confirming how to restore from the backup if
something is accidentally removed.
- Around line 36-45: The sentence mixes terminology ("legacy v4 IDE
commands/skills") creating ambiguity; update the text to use consistent terms
per version by stating that v4 used "commands" and v6 uses "skills" (e.g.,
replace "legacy v4 IDE commands/skills" with "legacy v4 IDE commands" and ensure
the rest of the paragraph refers to v6 as "skills"), and keep the example folder
names `.claude/commands/` for v4 and `.claude/skills/` for v6 so the mapping is
explicit and unambiguous.
- Around line 36-45: After removing the legacy .claude/commands/ folders and
installing new v6 skills into .claude/skills/, add a verification step
instructing users to run a simple help or listing command (for example
"bmad-help" or the CLI's equivalent) to confirm the new skills are accessible
and loaded; update the doc to show the exact command to run (e.g., bmad-help)
and what a successful output looks like so users can detect failures quickly if
no skills are listed.
In `@docs/reference/agents.md`:
- Line 26: The table row for "Quick Flow Solo Dev (Barry)" incorrectly uses the
agent ID `bmad-master`; replace that with the canonical ID
`bmad-quick-flow-solo-dev` so it matches the agent manifest
`bmad-skill-manifest.yaml` (and update any other occurrences in the same
document), ensuring the displayed ID exactly matches the manifest's canonical ID
to avoid invocation failures.
In `@docs/tutorials/getting-started.md`:
- Around line 241-245: The FAQ still uses slash-command notation; replace the
user-facing references '/bmad-correct-course' and '/bmad-brainstorming' with the
agent/workflow names without slashes (e.g., SM agent “bmad-correct-course” and
Analyst agent “bmad-brainstorming”), updating the text and any inline links so
they read as agent/workflow names rather than slash commands; specifically edit
the lines mentioning "/bmad-correct-course" and "/bmad-brainstorming" to remove
the leading slash and ensure the surrounding phrasing references the SM agent
and Analyst agent by name.
- Line 129: The tutorial text still shows the old slash-command syntax; update
the line so it references the skill invocation without a leading slash and
clarifies generation location: change "/bmad-generate-project-context" to
"bmad-generate-project-context" and ensure the sentence reads that running the
bmad-generate-project-context skill will generate
_bmad-output/project-context.md (with a link to
../explanation/project-context.md left intact).
- Around line 181-193: The table under "The Build Cycle" still uses the outdated
header "Command"; update that header to "Skill" (or "Invocation") and adjust
surrounding text to use the new terminology (e.g., change "run
`bmad-sprint-planning`" / "Command" to "invoke the `bmad-sprint-planning` skill"
or similar). Ensure the table rows referencing `/bmad-create-story`,
`/bmad-dev-story`, `/bmad-code-review`, and `/bmad-retrospective` remain as the
example skill invocations (keep the leading slashes) and update any
earlier/later sentences that call them "commands" (including the lines that
reference the SM agent `/bmad-sm`) to use "skill"/"invoke" language for
consistency.
---
Outside diff comments:
In `@docs/_STYLE_GUIDE.md`:
- Around line 246-256: Define and enforce a single canonical skill-invocation
format for the templates: decide whether the `Skill` field examples should use
bare names (e.g., "translate") or slash-prefixed commands (e.g., "/translate"),
then update the "Item Deep-Dive Reference" template and any template examples
that surface `Skill` so they consistently use that chosen format; also sweep
tutorial content (the getting-started examples that currently mix both forms)
and replace mismatched examples to match the canonical form to avoid ambiguity.
In `@docs/how-to/get-answers-about-bmad.md`:
- Around line 21-33: The guidance is contradictory: the header says "Run it with
just the skill name:" but the examples use "/bmad-help" with a leading slash;
fix by making the instruction and examples consistent—either change the header
text to "Run it with the skill:" (keep the examples as "/bmad-help" and the
other slash-prefixed examples) or remove the slashes from each example (replace
"/bmad-help" with "bmad-help" and similarly for the other examples) so the
phrase and the examples match; update whichever you choose throughout this
section including every occurrence of "/bmad-help" or "bmad-help".
In `@docs/how-to/shard-large-documents.md`:
- Line 44: The docs use inconsistent slash prefixes for skill invocations (e.g.
`/bmad-shard-doc` vs `bmad-shard-doc` and `bmad-generate-project-context`);
decide whether these are CLI commands or chat/IDE slash-commands, then make the
docs consistent: remove the leading slash from all bash/code block usages (e.g.
change `/bmad-shard-doc` to `bmad-shard-doc`) if they are CLI tools, or keep the
slash only where you explicitly show chat/IDE slash-command examples; update
docs/how-to/shard-large-doc and docs/how-to/project-context.md (and any other
occurrences) and add a short clarifying note near the top of each how-to stating
when to use the slash form (chat/IDE) versus the plain form (terminal/CLI) with
one example of each.
In `@docs/reference/testing.md`:
- Line 54: Update the sentence that currently references only the `CR` trigger
to mention both the trigger and the full skill ID: state that users can invoke
the Code Review workflow via the `CR` menu trigger or the `bmad-code-review`
skill ID (mirroring the pattern used for Quinn). Modify the line mentioning
"Quinn generates tests only. For code review and story validation, use the Code
Review workflow (`CR`) instead." to append or replace with the explicit skill ID
so it reads that Code Review can be invoked as `CR` or `bmad-code-review`.
In `@docs/tutorials/getting-started.md`:
- Around line 156-173: Update the documented invocation syntax to the new bare
skill form: replace all slash-prefixed commands in these steps (e.g.,
"/bmad-architect", "/bmad-create-architecture", "/bmad-pm",
"/bmad-create-epics-and-stories", "/bmad-check-implementation-readiness") with
their bare counterparts (bmad-architect, bmad-create-architecture, bmad-pm,
bmad-create-epics-and-stories, bmad-check-implementation-readiness) so the
Architecture, Epics/Stories, and Implementation Readiness sections use the same
bare invocation style introduced earlier on the page.
- Around line 61-63: The tip block reintroduces slash-command syntax by
referencing `/bmad-help`; update that reference to the new invocation format
`bmad-help` so it matches the earlier lines (40-49) and preserves
consistency—modify the text inside the tip (the :::tip[...] block) to remove the
leading slash and use `bmad-help` as the skill invocation.
- Around line 23-27: Update the "Easiest Path" tip so it no longer shows the
deprecated slash command form; replace the `/bmad-help what should I do first?`
example with the current bare skill invocation (e.g., `bmad-help what should I
do first?`) in the tip block so it matches the later examples and prevents
readers from copying the deprecated form.
- Around line 104-111: The tutorial still shows the old slash-invocation
"/bmad-help"; update the text to instruct users to invoke the bmad-help skill
directly by replacing "/bmad-help" with "bmad-help" (e.g., "Invoke the bmad-help
skill" or "Run the bmad-help skill in your AI IDE") in the
docs/tutorials/getting-started.md content around the tip block so the messaging
matches the new invocation format.
- Around line 252-273: The docs still reference the old slash command
`/bmad-help`; update the tutorial text to use the new command name without the
leading slash (replace `/bmad-help` with `bmad-help`) in the headings and Key
Takeaways (the instances in the "Run `/bmad-help` anytime" line and "Start with
`/bmad-help`" bullet) so the language matches the earlier sections that use
`bmad-help`.
---
Nitpick comments:
In `@docs/explanation/quick-flow.md`:
- Around line 33-35: The header "quick-spec: Plan" and the invocation
`bmad-quick-spec` are inconsistent; update the header to use the full skill ID
"bmad-quick-spec: Plan" or add a one-line note under the header clarifying that
headers show a short name while commands use the full skill ID (e.g., "Run
`bmad-quick-spec`"); edit the header text "quick-spec: Plan" or insert the
clarification immediately after it so readers won't try the wrong command.
In `@docs/how-to/quick-fixes.md`:
- Around line 33-47: The section uses mixed verbs ("invoke" in the headings and
examples like "bmad-dev" and "bmad-quick-flow-solo-dev" but then switches to
"loaded" in the sentence "Once the Solo Dev agent is loaded"), so update the
wording to use a single consistent verb (preferably "invoke") throughout: change
"Once the Solo Dev agent is loaded" to "Once the Solo Dev agent is invoked" and
scan nearby sentences in the "Invoke the DEV Agent" block to ensure all
references to starting or activating the agent use "invoke" (references: heading
"Invoke the DEV Agent", commands "bmad-dev" and "bmad-quick-flow-solo-dev", and
the phrase "Once the Solo Dev agent is loaded").
In `@docs/reference/workflow-map.md`:
- Line 87: Replace the inconsistent verb "Run" in the workflow-map entry for the
command `bmad-generate-project-context` with the project's chosen verb "Invoke"
to match other docs (e.g., quick-fixes.md and the skills terminology document);
update the line to read "Invoke `bmad-generate-project-context` to auto-generate
from your architecture or codebase" so the invocation pattern is consistent
across documents.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: c99a9e4d-5efe-4a19-a2a2-420cbca8b22a
📒 Files selected for processing (19)
docs/_STYLE_GUIDE.mddocs/explanation/brainstorming.mddocs/explanation/party-mode.mddocs/explanation/preventing-agent-conflicts.mddocs/explanation/project-context.mddocs/explanation/quick-flow.mddocs/how-to/established-projects.mddocs/how-to/get-answers-about-bmad.mddocs/how-to/install-bmad.mddocs/how-to/project-context.mddocs/how-to/quick-fixes.mddocs/how-to/shard-large-documents.mddocs/how-to/upgrade-to-v6.mddocs/index.mddocs/reference/agents.mddocs/reference/commands.mddocs/reference/testing.mddocs/reference/workflow-map.mddocs/tutorials/getting-started.md
…tion Align documentation with the skills-based architecture migration by replacing references to "commands", "slash commands", and legacy command names with the new "skills" terminology and skill names.
alexeyv
force-pushed
the
skills-aftermath
branch
from
d0bcaba to
986477f
Compare
This was referenced Mar 9, 2026
Open
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
1 participant
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.
Summary
Test plan