Conversation
silv-io
requested review from
anisaoshafi and
carole-lavillonniere
as code owners
📝 WalkthroughWalkthroughAdds five new AI assistant skill documentation files under Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes 🚥 Pre-merge checks | ✅ 2✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Tip Try Coding Plans. Let us write the prompt for your AI agent so you can ship faster (with fewer bugs). 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: 2
🧹 Nitpick comments (1)
.claude/skills/create-pr/SKILL.md (1)
17-25: Use the selected base branch in the example commands too.The instructions say
$ARGUMENTScan overridemain, but the concrete commands still diff/log againstmain. That makes the workflow internally inconsistent and can produce the wrong PR context for release or hotfix branches.Suggested fix
-Run these to understand what's being submitted: +Resolve the base branch first (`main` by default, or `$ARGUMENTS` when provided), then run:-git log main..HEAD --oneline
-git diff main...HEAD --stat
-git diff main...HEAD
+git log ..HEAD --oneline
+git diff ...HEAD --stat
+git diff ...HEAD
git branch --show-current- -If `$ARGUMENTS` is provided, use it as the base branch instead of `main`. +If `$ARGUMENTS` is provided, use it as `<base-branch>` instead of `main`.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.claude/skills/create-pr/SKILL.md around lines 17 - 25, Update the example git commands to use the chosen base branch variable instead of hardcoding "main": replace occurrences of `main` in the `git log main..HEAD --oneline`, `git diff main...HEAD --stat`, and `git diff main...HEAD` examples so they reference the selected base branch (e.g., `$ARGUMENTS` or a `<base-branch>` placeholder) and update the explanatory sentence to say "use `$ARGUMENTS` as `<base-branch>` instead of `main`" so the examples remain consistent when a non-main base is provided.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.claude/skills/create-pr/SKILL.md:
- Around line 17-22: Add the shell language identifier to both fenced code
blocks containing the git/gh command lists so markdownlint MD040 is satisfied;
specifically update the block that starts with "git log main..HEAD --oneline /
git diff ..." and the block that starts with "git push -u origin HEAD / gh pr
create ..." to use ```shell as the opening fence (leave the closing fence
unchanged).
- Line 6: The allowed-tools list in .claude/skills/create-pr/SKILL.md omits
basic git commands needed by the documented commit flow (git status, git add,
git commit), causing the skill to fail on a dirty branch; update the
allowed-tools entry that currently lists "Bash(git log *), Bash(git diff *),
Bash(git branch *), Bash(git push -u origin HEAD), Bash(gh pr create *),
mcp__plugin_linear_linear__get_issue" to include "Bash(git status *)", "Bash(git
add *)", and "Bash(git commit *)", and make the same addition to the
corresponding allowed-tools block covering lines 75-82 so the skill can stage
and commit changes as described.
---
Nitpick comments:
In @.claude/skills/create-pr/SKILL.md:
- Around line 17-25: Update the example git commands to use the chosen base
branch variable instead of hardcoding "main": replace occurrences of `main` in
the `git log main..HEAD --oneline`, `git diff main...HEAD --stat`, and `git diff
main...HEAD` examples so they reference the selected base branch (e.g.,
`$ARGUMENTS` or a `<base-branch>` placeholder) and update the explanatory
sentence to say "use `$ARGUMENTS` as `<base-branch>` instead of `main`" so the
examples remain consistent when a non-main base is provided.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI (base), Organization UI (inherited)
Review profile: CHILL
Plan: Pro
Run ID: e61a10a6-d177-4cab-bb6e-2efadd76c18f
📒 Files selected for processing (1)
.claude/skills/create-pr/SKILL.md
carole-lavillonniere
approved these changes
Mar 9, 2026
This was referenced Mar 18, 2026
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.
Motivation
Add Claude Code skills to encode architectural patterns and reduce friction when scaffolding new features. Claude doesn't always follow CLAUDE.md reliably for multi-step scaffolding tasks — skills with explicit step-by-step instructions and anti-pattern lists address this.
Changes
/add-command— scaffolds a new CLI subcommand (cmd wiring, domain logic, tests), asks clarifying questions first, challenges architectural decisions/add-event— adds a new output event type with format parity across plain and TUI sinks/add-component— scaffolds a new Bubble Tea TUI component with styles and tests/review-pr— reviews a PR against the lstk architectural checklist/create-pr— creates a PR with conventional Motivation/Changes/Tests/Todo/Related format, fetches Linear ticket context via MCPTests
Manual verification — invoked skills in a live session to validate structure and behavior.
Todo
Related