jellydn/my-ai-tools/pr-review
Claude Code and agent skill by jellydn/my-ai-tools
- community
Checking that the SKILL.md file is still in the repository.
Fix PR review comments by implementing requested changes
Install
npx vskill@latest install jellydn/my-ai-tools/pr-reviewSKILL.md
Fix PR Review Comments
Fix PR review comments by implementing the requested changes.
Usage
๐ Argument Handling
The command accepts the PR identifier from $ARGUMENTS:
- PR URL: Full GitHub PR URL (e.g.,
https://github.com/owner/repo/pull/123) - PR Number: Just the PR number (e.g.,
123) - No Arguments: Auto-detect the PR associated with the current Git branch
If $ARGUMENTS is provided, use it as the PR identifier. Otherwise, auto-detect the current branch's PR using:
This extracts the PR number from the current branch's open PR for use in subsequent commands.
If no open PR is found for the current branch, show this error:
Process
- Parse
$ARGUMENTSto determine PR identifier (URL, number, or auto-detect) - Fetch PR details, review threads, issue comments, and authoritative thread-resolution state using
gh - Classify each comment as actionable, informational, disputed/ambiguous, or resolved; ask before changing disputed or ambiguous requests
- For each actionable comment, record the comment ID, planned change, and verification command
- Implement the approved fixes
- Run focused tests, then the relevant broader checks
- Recheck the comment-to-change list and confirm every actionable thread is resolved or explicitly deferred
- Commit the changes
Available Scripts
Extract PR Comments
The extract-pr-comments.js script processes GitHub PR review comments and issue comments to create actionable TODO lists.
What it does:
- Requires a threads file of GitHub review threads and skips a review comment only when its thread has
isResolved: true - Does not treat a reply as resolution; an unanswered thread stays actionable
- Classifies comments by severity (critical, high, medium, low)
- Categorizes comments (security, performance, maintainability, etc.)
- Creates 3 output files:
.ndjson- Structured comment data-todo.md- Prioritized TODO list-summary.md- Analysis summary with emojis
Severity classification:
- ๐ด Critical: security, vulnerability, exploit
- ๐ High: bug, error, breaking, crash, fail
- ๐ก Medium: performance, improvement, refactor, optimize
- ๐ข Low: everything else
Categories:
- ๐ Security
- โก Performance
- ๐ง Maintainability
- โฟ Accessibility
- ๐งช Testing
- ๐ Documentation
- ๐ท๏ธ Typing
- ๐จ Style
- โจ Code Quality
Examples
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/pr-review/SKILL.md
Popularity
- Repository stars
- 51
- Repository forks
- 9
- 7-day trend score
- 20
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 24 Mar 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/jellydn/my-ai-tools/pr-review)