PR Review

What it does

When your agent uses it

• Tasks that involve Pull requests

Example prompts

• “/pr-review”

Requirements

• Node.js
• Compatibility (from SKILL.md): cline, claude, opencode, amp, codex, gemini, cursor, pi

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1PR URL: Full GitHub PR URL (e.g., https://github.com/owner/repo/pull/123)
2. 2PR Number: Just the PR number (e.g., 123)
3. 3No Arguments: Auto-detect the PR associated with the current Git branch

What it can do on your machine

Read from SKILL.md and the folder at commit 62c9227. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (JavaScript), which the agent can run.

  Shell commands in SKILL.md call:

  • gh
  • node

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  cline, claude, opencode, amp, codex, gemini, cursor, pi

  From compatibility in the SKILL.md frontmatter.

Context cost

PR Review loads about 1.1k tokens when it runs. Until then it costs about 17 tokens; SKILL.md has 309 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~17

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from jellydn/my-ai-tools at commit 62c9227, republished under its MIT licence (© jellydn). 309 words, ~1,063 tokens.

name

pr-review

description

Fix PR review comments by implementing requested changes

compatibility

cline, claude, opencode, amp, codex, gemini, cursor, pi

license

MIT

hint

Use when fixing PR review comments or addressing review feedback. Accepts PR URL, PR number, or auto-detects from current branch

user-invocable

true

metadata.audience

all

metadata.workflow

code-quality

/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

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

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

# 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

# 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 → Low

© jellydn, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in skills/pr-review of jellydn/my-ai-tools.

• SKILL.md
• scripts/extract-pr-comments.js

Open the folder on GitHubat commit 62c9227