Prp Pr logo

Prp Pr

CommunityPopular
Wirasm
prp-pr

Creates and opens GitHub pull requests. Always use when creating a PR on GitHub, when the user explicitly asks to create or open a PR, when another PRP workflow reaches its PR-creation step, or when the user invokes /prp-pr.

Overview

PublisherWirasm
Repositoryprp
Skill nameprp-pr
Stars
2.2K
Forks
607
Bundled files
Instructions only
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.

  • Self-contained

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

  • Open source

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

Installation

Install the Prp 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/Wirasm/prp.git /tmp/prp
mkdir -p .claude/skills
cp -r /tmp/prp/plugins/prp-core/skills/prp-pr .claude/skills/prp-pr
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Prp 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 Prp 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 Prp 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 Pull Request

Create a clear, reviewer-friendly GitHub pull request for the completed work on the current branch.

Arguments: $ARGUMENTS

Scope

Run this at the PR-creation step after the requested work has been done by the current agent, a subagent, or another collaborator. Ensure every change belonging to that work is committed before opening the PR. If intended changes remain uncommitted, invoke /prp-commit with a natural-language target that identifies only those changes, then verify the resulting commit. Never sweep unrelated worktree changes into the commit.

The pull request itself is the artifact; do not create a separate local PR document.

1. Establish the PR target

Inspect the current branch, repository instructions, remote branches, and Git history. Determine the base in this order:

  1. An explicit --base <branch>.
  2. The base recorded on an existing PR for this branch.
  3. The repository's documented development flow.
  4. Branch ancestry against likely integration branches such as development, dev, and the remote default branch.
  5. The remote default branch as a fallback.

Use the same resolved base for every log, diff, and PR command. Never assume main. If the evidence is genuinely ambiguous, stop and ask rather than opening the PR against a guessed target.

Check whether any open or closed PR already exists for the current branch. If one exists, return its URL and state instead of creating a duplicate.

2. Validate the committed work

  • Re-read git status and the diff after any commit to confirm no intended changes were omitted.
  • Confirm the current branch is not the resolved base and contains commits ahead of it.
  • Fetch current remote state, then read the complete merge-base diff and commit range against the resolved base—not only the file list or diff stat.
  • Compare the diff with the user's requested outcome and repository instructions. Stop if the branch does not contain the intended work or includes unexplained scope.
  • Find the repository's pull request template in its supported root, .github, or docs locations. If several templates could apply and the correct one cannot be inferred, ask which to use.

3. Write the pull request

Treat repository rules as syntax constraints, not as the writing-quality standard. Write in plain, natural language. Cut filler, generic praise, formulaic transitions, and vague claims. Use the repository's exact terms and name concrete behavior and evidence.

Title

  • Write a concise, human-readable title describing the meaningful outcome.
  • Preserve enforced repository syntax such as required types, scopes, or issue identifiers.
  • Do not imitate vague or implementation-focused titles merely because they appear in repository history.
  • Use Conventional Commit style only when the repository requires or consistently uses it.

Bad: feat(core): add child run traversal and parent event aggregation

Good: feat(core): workflows can now include a child workflow in the parent run

Description

Use the repository's pull request template whenever one exists. Preserve its structure and fill every applicable section with concrete information from the request, diff, commits, and validation evidence.

If no template exists, use this fallback:

markdown
## Problem

{Explain the original problem and why it matters to the user.}

## Solution

{Briefly explain how the change resolves it, focusing on behavior rather than an inventory of files and functions.}

## Validation

- `{actual command}` — passed
- {Concrete manual verification, when applicable}

{Fixes/Closes/Relates to #N when supported}
{Plan: <verified published-plan URL> when supplied}
  • Lead with the problem, then the solution. Do not lead with an implementation inventory.
  • Report only validation that actually ran. If none ran, say so and explain why; never add generic unchecked boxes as evidence.
  • Add Fixes or Closes only when the PR fully resolves the referenced issue. Use Relates to for a non-closing relationship. Do not infer issue linkage from an unexplained bare number.
  • When a verified published-plan URL is supplied, link it in the repository template's Links or planning context section. This is the reviewer-accessible implementation contract; never substitute a local plan path.
  • Never add AI attribution, a generated-by footer, a robot emoji, or Co-Authored-By: Claude.

4. Push and create

Push the current branch with upstream tracking when needed. If the remote branch has diverged or the push is rejected, stop and report the conflict; do not rebase or force-push as part of this skill.

Create a ready-for-review PR against the resolved base. Use --draft only when the user explicitly requests a draft. Pass the prepared title and body to gh pr create without opening an interactive editor.

5. Verify and report

Read the created PR back from GitHub and verify its number, URL, title, base, head, draft state, and open state. Check CI status without waiting for pending jobs.

Return the PR URL first, followed by the verified title, base <- head, ready/draft state, and current checks. Keep the report concise.

Do not report success until GitHub confirms the PR exists with the intended base and head.

Frequently asked questions

What does the Prp Pr AI skill do?

Creates and opens GitHub pull requests. Always use when creating a PR on GitHub, when the user explicitly asks to create or open a PR, when another PRP workflow reaches its PR-creation step, or when the user invokes /prp-pr.

Why use Prp Pr on TypingMind?

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

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

Which AI models can use Prp 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 Prp Pr?

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

Is the Prp Pr AI skill free?

Yes. It is published on GitHub by Wirasm 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 👇