fix: remove legacy slash commands that conflict with unified skills system #347
+25
−23
Conversation
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
📝 WalkthroughWalkthroughRemoves three legacy slash-command docs and related YAML front-matter that disabled model invocation; updates README wording to reference skills instead of commands and adds a v4.2.0 Breaking Changes section in RELEASE-NOTES with mappings from old slash commands to new skill names. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes Possibly related issues
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. 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 |
Anthropic unified commands and skills in Claude Code, making the /brainstorm, /write-plan, and /execute-plan command wrappers redundant. These caused `disable-model-invocation` errors when Claude tried to invoke them via the Skill tool, confusing users. The underlying skills (brainstorming, writing-plans, executing-plans) continue to work and trigger automatically. - Remove commands/brainstorm.md, write-plan.md, execute-plan.md - Update README verify section to reference skills instead of commands - Add breaking change entry to RELEASE-NOTES.md Fixes obra#345 Fixes obra#222 Fixes obra#244 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
skyvanguard
force-pushed
the
fix/remove-legacy-slash-commands
branch
from
fc78199 to
a18c07d
Compare
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Fix all issues with AI agents
In `@README.md`:
- Around line 53-58: Update the fenced code block in README.md to include a
language specifier to satisfy markdownlint; change the opening triple-backticks
for the block that contains the commented "Should see skills like:" lines to
"```text" so the block reading "# Should see skills like:" and the three "#
superpowers:..." lines is a fenced text block.
In `@RELEASE-NOTES.md`:
- Line 7: Replace the bolded section title "**Removed legacy slash commands**"
with a proper Markdown heading (for example "## Removed legacy slash commands"
or "### Removed legacy slash commands") so the section uses a heading token
instead of emphasis-as-heading; locate the exact bold text in RELEASE-NOTES.md
and update it to the chosen heading level to satisfy markdownlint.
Comment on lines
53
to
58
| ``` | ||
| # Should see: | ||
| # /superpowers:brainstorm - Interactive design refinement | ||
| # /superpowers:write-plan - Create implementation plan | ||
| # /superpowers:execute-plan - Execute plan in batches | ||
| # Should see skills like: | ||
| # superpowers:brainstorming - Explores user intent, requirements and design before implementation | ||
| # superpowers:writing-plans - Create detailed implementation plan with bite-sized tasks | ||
| # superpowers:executing-plans - Execute plan in batches with review checkpoints | ||
| ``` |
There was a problem hiding this comment.
Specify a language for the fenced block.
Markdownlint flags code fences without a language; use text for console output.
🔧 Suggested fix
-```
+```text
# Should see skills like:
# superpowers:brainstorming - Explores user intent, requirements and design before implementation
# superpowers:writing-plans - Create detailed implementation plan with bite-sized tasks
# superpowers:executing-plans - Execute plan in batches with review checkpoints</details>
<details>
<summary>🧰 Tools</summary>
<details>
<summary>🪛 markdownlint-cli2 (0.18.1)</summary>
53-53: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
</details>
</details>
<details>
<summary>🤖 Prompt for AI Agents</summary>
In @README.md around lines 53 - 58, Update the fenced code block in README.md to
include a language specifier to satisfy markdownlint; change the opening
triple-backticks for the block that contains the commented "Should see skills
like:" lines to "```text" so the block reading "# Should see skills like:" and
the three "# superpowers:..." lines is a fenced text block.
</details>
<!-- fingerprinting:phantom:triton:eagle -->
<!-- This is an auto-generated comment by CodeRabbit -->
- Use #### heading instead of **bold** for section title - Use fenced code block with language specifier for migration mapping Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Owner
|
I am planning on doing something like this for the next release. |
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.
Summary
Fixes #345, #222, #244
Anthropic unified commands and skills in Claude Code — they're now the same thing. The three legacy slash command wrappers (
/brainstorm,/write-plan,/execute-plan) became redundant and actively harmful:superpowers:prefixdisable-model-invocationerrorsuperpowers:brainstorm) and the working skill (superpowers:brainstorming)Changes
commands/brainstorm.md,commands/write-plan.md,commands/execute-plan.mdMigration for users
The underlying skills continue to work exactly as before — they trigger automatically based on context. Users who typed
/superpowers:brainstormshould now use the skill namesuperpowers:brainstorming(or just let it trigger automatically).Context
This follows the direction set in v4.0.2 (where
disable-model-invocation: truewas added as a partial fix) and the owner's comment on #345:Test plan
brainstorming,writing-plans,executing-plans) remain unchangedSummary by CodeRabbit
Breaking Changes
Documentation
✏️ Tip: You can customize this high-level summary in your review settings.