Skip to content

PR Labeling for skills CLI

Automatically labels skills CLI pull requests as bug, documentation, or enhancement.

Stars
37,724
Licence
MIT
Files
1 file

What it does

This skill tells an AI agent how to triage pull requests in the vercel-labs skills CLI repository. The agent reads a pull request's title, description, existing labels and code changes, then picks one label: documentation, bug, or enhancement. It skips pull requests that already have one of those labels, and it stops without labeling when the change is unclear or the patch is incomplete, instead of guessing from the title.

Great for

  • Maintainers of the skills CLI repository who want consistent first-pass labels on incoming pull requests
  • Teams building automated triage bots that need a clear labeling rubric as a starting point

Skip it if

  • Repositories other than skills CLI, since the label rules and file paths are specific to this project
  • Cases where a human must make the final call on priority or ownership, because the agent applies labels without review and may misclassify mixed changes

Try asking

  • “Label pull request #123 for the skills CLI repository”
  • “Classify the latest pull request triggered by this automation and add one label”
  • “Check whether pull request 456 already has a maintainer label before doing anything”
Step-by-step guide: how to use PR Labeling for skills CLIInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    pr-labeling.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip pr-labeling.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip pr-labeling.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Make sure the automation supplies the pull request number and triggering commit so the head-commit check can work
  • Review labels the agent adds on mixed or large pull requests, since the rubric asks it to pick only one primary label

What's inside

  • SKILL.md

Redistributed unmodified from vercel-labs/skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.