Pr logo

Pr

OrganizationPopular
tldraw
pr

Create or update a pull request for the current branch in the tldraw repository. Use when the user invokes pr, asks to create a PR, update an existing PR, push current branch changes for review, or prepare a pull request.

Overview

Publishertldraw
Repositorytldraw
Skill namepr
Stars
50.4K
Forks
3.5K
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by tldraw on GitHub. Read the source before you install it.

Installation

Install the Pr AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/tldraw/tldraw.git /tmp/tldraw
mkdir -p .claude/skills
cp -r /tmp/tldraw/skills/pr .claude/skills/pr
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pr in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pr on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pr is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PR

Create or update a pull request for the current branch.

Use ../write-pr/SKILL.md as the standards reference for PR titles, descriptions, release notes, API changes, code changes tables, and human-note preservation.

Workflow

  1. Gather context:
    • Current branch: git branch --show-current
    • Working tree: git status --short
    • Existing PR: gh pr view --json number,title,url 2>/dev/null
    • Recent branch commits: git log main..HEAD --oneline 2>/dev/null || git log -3 --oneline
  2. Check for overlapping work so we don't step on a teammate's toes:
    • List open PRs touching the same area: gh pr list --state open --json number,title,url,author,headRefName,updatedAt, and search for related work: gh pr list --search "<keywords>" --state open.
    • Compare their changed files against ours (gh pr diff <number> --stat) to judge real overlap, not just a shared filename.
    • If someone already has a PR open for this: prefer building on their work over racing it. Offer to base our branch on theirs, contribute a review or a follow-up commit, or hand our changes over. Only open a competing PR when the approaches genuinely diverge, and when we do, link to theirs and explain how ours differs so the choice is easy for reviewers.
    • Surface what you found to the user before proceeding when there's meaningful overlap.
  3. Prepare the branch:
    • If on main, create a new branch with a descriptive name.
    • Commit relevant changes, excluding secrets and explicitly private content.
    • Push the branch to the remote. Never force push.
  4. Run an initial review pass before asking a human to look. Spin out a few subagents in parallel over the diff (git diff main...HEAD), each with a focused lens, then fold their findings into concrete fixes:
    • Does the change actually solve the stated problem, end to end, rather than papering over a symptom?
    • Does it leave the codebase better than we found it — clearer names, no dead or duplicated code, no drive-by regressions?
    • Any weird abstractions, premature generality, or unnecessary code that a reviewer would flag? Prefer the smaller, more direct version.
    • Sweep the diff's added comments for slop, following ../write-pr/SKILL.md § The comment sweep. On an update, this catches whatever the branch grew since the PR was opened, which on a long-lived branch is most of it.
    • Fix what's clearly worth fixing so the human review starts from a strong diff. If a finding needs a product or design call, raise it with the user instead of guessing.
    • Commit and push any fixes from this pass so the remote branch matches before the PR is created, updated, or shared. Never force push.
  5. If no PR exists, create one with gh pr create.
  6. If a PR exists, read it with gh pr view --json title,body,labels,number and inspect the changed-file summary with gh pr diff --stat.
  7. Update the title or body with gh pr edit if the existing PR does not match the current diff or the write-pr standards.
  8. Search for related issues and link them in the PR description with Closes #123 or Relates to #123 where appropriate.
  9. Share the PR URL with the user.

Handling problems

Committing automatically runs hooks. Fix formatting, lint, type, or import issues when the fix is mechanical.

If a hook failure requires meaningful product or implementation decisions, stop and ask the user how to proceed.

Never force commit or force push.

Rules

  • Follow ../write-pr/SKILL.md for all PR content standards.
  • Do not include AI attribution in commit messages, PR titles, or PR descriptions.
  • Do not add yourself or an AI tool as a co-author.

Frequently asked questions

What does the Pr AI skill do?

Create or update a pull request for the current branch in the tldraw repository. Use when the user invokes pr, asks to create a PR, update an existing PR, push current branch changes for review, or prepare a pull request.

Why use Pr on TypingMind?

Because you install it once and use it with any model. Pr is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pr in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tldraw/tldraw/tree/main/skills/pr. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pr?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pr?

As many as you like. As long as a model supports skills, you can use Pr with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pr AI skill free?

It is published on GitHub by tldraw. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇