Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jellydn-pr-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/pr-review
What's inside
- Skill name
pr-review- Description
- Fix PR review comments by implementing requested changes
- License
- MIT
- Compatibility
- cline, claude, opencode, amp, codex, gemini, cursor, pi
- Metadata
- audience: all · workflow: code-quality
- Instructions
- 122 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (2)
- SKILL.md
- extract-pr-comments.js · scripts/
SKILL.md (first lines)
# 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
```
### 📋 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:**
- 🔴 **Critical**: security, vulnerability, exploit
- 🟠 **High**: bug, error, breaking, crash, fail
- 🟡 **Medium**: performance, improvement, refactor, optimize
- 🟢 **Low**: everything else
**Categories:**
- 🔒 Security
- ⚡ Performance
- 🔧 Maintainability
- ♿ Accessibility
- 🧪 Testing
- 📚 Documentation
- 🏷️ Typing
- 🎨 Style
- ✨ 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 → High → Medium → LowFrom jellydn/my-ai-tools, MIT.
More from jellydn/my-ai-tools
- 0.722score
visual-pr
jellydn
Posts a concise visual outline as a GitHub pull request comment.
SkillAFreshness: A★ 123Claude Code +9 - 0.722score
babysit-pr
jellydn
Use when monitoring an open GitHub PR for CI failures, review feedback, mergeability, and safe retries or fixes.
SkillAFreshness: A★ 123Claude Code +9 - 0.716score
codemap
jellydn
Create a seven-document architecture map when the user asks to map a codebase.
SkillAFreshness: A★ 123Claude Code +9 - 0.716score
draft-pull-request
jellydn
Draft pull requests with structured descriptions using gh CLI
SkillAFreshness: A★ 123Claude Code +9 - 0.714score
diagnosing-bugs
jellydn
Build a tight, red-capable feedback loop before diagnosing failures, then minimize, test ranked hypotheses, and lock the fix with a regression test.
SkillAFreshness: A★ 123Claude Code +9 - 0.711score
code-review
jellydn
Review a branch, PR, or worktree diff for repository conventions and stated intent.
SkillAFreshness: A★ 123Claude Code +9 - 0.711score
pr
jellydn
Write a fast-to-review pull request body with a visual summary, before/after evidence, and merge-risk analysis.
SkillAFreshness: A★ 123Claude Code +9 - 0.711score
plannotator-setup-goal
jellydn
Turn ideas into executable goal packages with guided interviews and codebase analysis
SkillAFreshness: A★ 123Claude Code +9 - 0.711score
blindspot-pass
jellydn
Inspect history and architecture for hidden constraints before risky cross-cutting changes.
SkillAFreshness: A★ 123Claude Code +9 - 0.711score
implementation-logger
jellydn
Log implementation decisions — tracks deviations from plan and captures rationale
SkillAFreshness: A★ 123Claude Code +9 - 0.711score
implement-spec
jellydn
Implement a complete spec from its ticket graph, using isolated workers and one integration branch.
SkillAFreshness: A★ 123Claude Code +9 - 0.711score
portless-local
jellydn
Replace port numbers with stable named .localhost URLs for local development
SkillAFreshness: A★ 123Claude Code +9
Signals
- Stars
- 123
- Forks
- 12
- Open issues
- 3
- Last commit (this folder)
- Oct 7, 2026 (21 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/jellydn/my-ai-tools
- Website
- ai-tools.itman.fyi/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from jellydn
- 0.722score
babysit-pr
jellydn
Use when monitoring an open GitHub PR for CI failures, review feedback, mergeability, and safe retries or fixes.
SkillAFreshness: A★ 123Claude Code +9 - 0.722score
visual-pr
jellydn
Posts a concise visual outline as a GitHub pull request comment.
SkillAFreshness: A★ 123Claude Code +9 - 0.716score
draft-pull-request
jellydn
Draft pull requests with structured descriptions using gh CLI
SkillAFreshness: A★ 123Claude Code +9 - 0.716score
codemap
jellydn
Create a seven-document architecture map when the user asks to map a codebase.
SkillAFreshness: A★ 123Claude Code +9 - 0.714score
diagnosing-bugs
jellydn
Build a tight, red-capable feedback loop before diagnosing failures, then minimize, test ranked hypotheses, and lock the fix with a regression test.
SkillAFreshness: A★ 123Claude Code +9 - 0.711score
code-review
jellydn
Review a branch, PR, or worktree diff for repository conventions and stated intent.
SkillAFreshness: A★ 123Claude Code +9
Cite this page
pr-review skill. Agent Mart. https://agentmart.dev/skills/jellydn-pr-review (last updated 2026-10-24)