Create Pr logo

Create Pr

OrganizationPopular
ueberdosis
create-pr

Create a pull request with a clear, concise description that follows the repository's current PR template. Use when asked to open a PR or prepare its title and description.

Overview

Publisherueberdosis
Repositorytiptap
Skill namecreate-pr
Stars
38.6K
Forks
3.1K
Bundled files
1
LicenseMIT
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Create 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.
    https://github.com/ueberdosis/tiptap/tree/main/skills/create-pr
  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/ueberdosis/tiptap.git /tmp/tiptap
mkdir -p .claude/skills
cp -r /tmp/tiptap/skills/create-pr .claude/skills/create-pr
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Create 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 Create 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 Create 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.

Create PR

Write for busy developers: make the change and its purpose clear before adding detail.

Read the current template

  • Find and read the repository's applicable PR template every time, including HTML comments, linked guidelines, and contribution instructions. Check the repository root, .github/, and docs/, including template directories. If several templates exist, choose the one that fits the change.
  • Use the template's current sections, order, length limits, and checklist instructions. Do not copy its structure into this skill or reuse a remembered version.
  • Prefer the actual current PR template over stale copies of its structure in other guidance; still follow any compatible contribution rules.
  • If no local template exists, check the target repository and its shared GitHub defaults. If none exists, use a compact structure suited to the change and say that no template was found.
  • Inspect the full diff against the intended base branch and the relevant issue context. Describe the final change, not the sequence of work or abandoned approaches.

Write the description

Fit the following content into the template's appropriate sections rather than adding a fixed set of headings:

  • Start the narrative with a short summary of what changed and why it matters. If the template starts with links or metadata, preserve that order and lead the first explanatory section with the summary.
  • Use short sentences, simple English, and concrete behavior. Put deeper technical detail later, only where the template permits it and reviewers need it.
  • For a bug fix, include the setup and steps to reproduce the original issue, the expected behavior, the observed behavior before the fix, and how the fix closes that gap. Keep these distinct even when expressed in a compact example. Do not claim to have reproduced an issue unless you did; label unverified steps.
  • Include brief notes on the implementation approach: the key decision and how it produces the intended behavior. Mention tradeoffs or consequences only when they affect review or users.
  • Consider a few small diagrams or code examples when they explain reproduction, before/after behavior, the approach, or consequences more clearly than prose. Prefer focused snippets or Mermaid diagrams; omit visuals that only repeat the text. Respect the template's length limits.
  • Do not add a validation or verification section, command logs, or a list of checks or tests run. You may briefly mention tests added to the codebase and the behavior they cover. This restriction concerns the description; still perform repository-required checks.
  • Preserve required checklist items and mark them truthfully. If the template explicitly requires a validation section or execution results, retain its required heading or field but omit the command/test-run report, following the user's preference. Explain that specific conflict to the user outside the PR.

Link related work

  • Include relevant issues and related PRs in the template's link section or the closest existing section. If it has no suitable section, add a small links section only if its guidelines allow it.
  • Include any Linear ticket supplied with the request in that section. Use its supplied URL, or resolve its identifier through available context or tools; never invent a workspace URL.
  • Use closing keywords only for issues this PR actually resolves. Label other issues, tickets, and PRs as related work or dependencies rather than implying that they will close.
  • Do not invent links or issue numbers. If a required link cannot be resolved, ask for the missing information; when no related work is known, follow the template's convention for an empty field.

Create the PR

  • Confirm the intended repository, base branch, and change scope from the task and repository context. Respect whether the user requested a draft or a ready PR.
  • When opening a PR is requested, carry it through using the available GitHub tools or gh. If only a description is requested, return the draft without publishing it. Commit or push only within the user's authorization and exclude unrelated changes.
  • Before publishing, compare the finished description with every template section and instruction. Confirm that claims match the diff, links are accurate, and no placeholders remain.
  • With gh, write the exact Markdown to a temporary file and use --body-file to preserve newlines and literal code.
  • Check for an existing PR for the branch before creating one. If creation has an ambiguous result, check whether it succeeded before retrying to avoid duplicates. Report unresolved authentication or permission failures instead of repeatedly retrying.
  • Return the PR link and ask the user to review it. Keep execution results and any blockers in the task response, outside the PR description.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Create Pr AI skill do?

Create a pull request with a clear, concise description that follows the repository's current PR template. Use when asked to open a PR or prepare its title and description.

Why use Create Pr on TypingMind?

Because you install it once and use it with any model. Create 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 Create Pr in TypingMind?

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

Which AI models can use Create 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 Create Pr?

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

Is the Create Pr AI skill free?

Yes. It is published on GitHub by ueberdosis under the MIT license. 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 👇