jellydn/my-ai-tools/pr-review

Claude Code and agent skill by jellydn/my-ai-tools

Trust tier 2
  • community
LLM review pending
Source check pending

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-review

SKILL.md

Fix PR Review Comments

Fix PR review comments by implementing the requested changes.

Usage

bash
/pr-review <PR_URL> # Review PR by URL (expects full GitHub URL)
/pr-review <PR_NUMBER> # Review PR by number (expects number, e.g., 123)
/pr-review # Auto-detect PR from current branch
๐Ÿ“‹ Argument Handling

The command accepts the PR identifier from $ARGUMENTS:

  1. PR URL: Full GitHub PR URL (e.g., https://github.com/owner/repo/pull/123)
  2. PR Number: Just the PR number (e.g., 123)
  3. 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:

bash
gh pr view --json number,url -q '.number'

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:

text
Error: No open pull request found for the current branch.
To review a specific PR:
/pr-review <PR_URL>
/pr-review <PR_NUMBER>
Or create a PR first:
gh pr create

Process

  1. Parse $ARGUMENTS to determine PR identifier (URL, number, or auto-detect)
  2. Fetch PR details, review threads, issue comments, and authoritative thread-resolution state using gh
  3. Classify each comment as actionable, informational, disputed/ambiguous, or resolved; ask before changing disputed or ambiguous requests
  4. For each actionable comment, record the comment ID, planned change, and verification command
  5. Implement the approved fixes
  6. Run focused tests, then the relevant broader checks
  7. Recheck the comment-to-change list and confirm every actionable thread is resolved or explicitly deferred
  8. 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.

bash
# Usage
node $SKILL_PATH/scripts/extract-pr-comments.js <review-comments-file> <issue-comments-file> <threads-file> [output-file]
# Example
gh api graphql \
-f owner=OWNER -f name=REPO -F number=4972 \
-f query='query($owner:String!, $name:String!, $number:Int!) { repository(owner:$owner, name:$name) { pullRequest(number:$number) { reviewThreads(first:100) { nodes { isResolved comments(first:100) { nodes { databaseId } } } } } } }' \
> pr-4972-threads.json
node $SKILL_PATH/scripts/extract-pr-comments.js \
pr-4972-review-comments-raw.json \
pr-4972-issue-comments-raw.json \
pr-4972-threads.json \
pr-4972-comments.ndjson

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:

  • ๐Ÿ”ด Critical: security, vulnerability, exploit
  • ๐ŸŸ  High: bug, error, breaking, crash, fail
  • ๐ŸŸก Medium: performance, improvement, refactor, optimize
  • ๐ŸŸข Low: everything else

Categories:

  • ๐Ÿ”’ Security
  • โšก Performance
  • ๐Ÿ”ง Maintainability
  • โ™ฟ Accessibility
  • ๐Ÿงช Testing
  • ๐Ÿ“š Documentation
  • ๐Ÿท๏ธ Typing
  • ๐ŸŽจ Style
  • โœจ Code Quality

Examples

bash
# Fix review comments for a PR using URL
/pr-review https://github.com/owner/repo/pull/123
# Fix review comments using PR number
/pr-review 123
# Auto-detect PR from current branch
/pr-review
# After extracting comments with the script, work through the TODO list
# The TODO list is ordered by priority: Critical โ†’ High โ†’ Medium โ†’ Low

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

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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/jellydn/my-ai-tools/pr-review/badge)](https://verified-skill.com/skills/jellydn/my-ai-tools/pr-review)

Something wrong with this skill or its page? Tell us.