Gh Create Pr logo

Gh Create Pr

OrganizationPopular
CherryHQ
gh-create-pr

Create or update GitHub pull requests using the repository-required workflow and template compliance. Use when asked to create/open/update a PR so the assistant reads `.github/pull_request_template.md`, fills every template section, preserves markdown structure exactly, and marks missing data as N/A or None instead of skipping sections.

Overview

PublisherCherryHQ
Repositorycherry-studio
Skill namegh-create-pr
Stars
52.5K
Forks
5.1K
Bundled files
1
LicenseAGPL-3.0
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 CherryHQ on GitHub. Read the source before you install it.

Installation

Install the Gh 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/CherryHQ/cherry-studio/tree/main/.agents/skills/gh-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/CherryHQ/cherry-studio.git /tmp/cherry-studio
mkdir -p .claude/skills
cp -r /tmp/cherry-studio/.agents/skills/gh-create-pr .claude/skills/gh-create-pr
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gh 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 Gh 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 Gh 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.

GitHub PR Creation

Workflow

  1. Read .github/pull_request_template.md before drafting the PR body.
  2. Collect PR context from the current branch (base/head, scope, linked issues, testing status, breaking changes, release note content).
  3. Check if the current branch has been pushed to remote. If not, push it first:
    • Default remote is origin, but ask the user if they want to use a different remote.
    bash
    git push -u <remote> <head-branch>
  4. Determine the base branch:
    • Inspect the head branch before applying any default. If the head is release/v<version>, stop: never open a pull request from a release branch, especially not to main. Put an isolated fix on a topic branch and target the release branch, or let Post Release create the metadata sync branch.
    • Before defaulting an arbitrary topic branch to main, inspect its merge base and upstream. A product-code fix that started from release/v<version> must stop and be recreated from main as a hotfix; only a release-only repair or explicit backport recovery topic may target that exact release branch.
    • A backport/v<version>/pr-<number> head must target the matching release/v<version> base and its body must contain <!-- release-backport-source-pr: <number> --> on its own line for the exact source hotfix PR. A release-sync/v<version> head must target main, use the exact title chore(release): sync v<version> metadata, retain the release-metadata-boundary: v<version> body marker, and be squash-merged.
    • For official repo(CherryHQ/cherry-studio) as origin: default base is main from origin, but allow the user to explicitly indicate a base branch.
    • main is the active development line, including hotfix PRs. Do not target an old maintenance branch unless the user explicitly requests it.
    • Only classify a PR as a release hotfix when the user explicitly says it must be included in the active draft release. Use the title hotfix: <description> or hotfix(<kebab-case-scope>): <description> with a lowercase alphanumeric kebab-case scope, exactly one space after the colon, and a non-empty description. The title grammar synchronizes the hotfix label automatically. Merging opens a separate backport PR only when exactly one draft semantic-version release has a matching active release/v<version> branch; otherwise automation stops without guessing a target.
    • If the hotfix is user-facing, provide one release-note line in each language so automation can update the active draft and stable release history. Put this exact structure inside the template's existing release-note fence; do not include bullet prefixes:
      text
      <!--LANG:en-->
      [Component] English description.
      <!--LANG:zh-CN-->
      [组件] 中文说明。
      <!--LANG:END-->
    • If the hotfix has no user-facing release note, keep NONE in the template's release-note fence. The code is still backported, but release metadata is unchanged. A provided bilingual block must satisfy the exact structure above.
    • For fork repo as origin: check available remotes with git remote -v, default base may be upstream/main or another remote. Always assume that user wants to merge head to CherryHQ/cherry-studio/main, unless the user explicitly indicates a base branch.
    • Ask the user to confirm the base branch if it's not the default.
  5. Create a temp file and write the PR body using a single Bash heredoc (avoids mktemp + Write tool path-mismatch on Windows):
    bash
    pr_body_file="/tmp/gh-pr-body-$(date +%s).md"
    cat > "$pr_body_file" <<'EOF'
    ...filled template body...
    EOF
    Fill content using the template structure exactly (keep section order, headings, checkbox formatting). If not applicable, write N/A or None.
  6. Preview the temp file content via Bash cat "$pr_body_file" (the Read tool can fail on /tmp/... paths on Windows). Show the file path and ask for explicit confirmation before creating. Skip if the user explicitly waives preview (automation workflows).
  7. After confirmation, create the PR:
    bash
    gh pr create --base <base> --head <head> --title "<title>" --body-file "$pr_body_file"
    For a release hotfix, use an exact classifier-compatible title so the workflow synchronizes the label and separately validates any provided bilingual note:
    bash
    gh pr create --base main --head <head> --title "hotfix: <description>" --body-file "$pr_body_file"
    After creation, verify that the classifier added hotfix; if it did not, fix the title instead of adding the label manually. Also fix any malformed optional release-note block reported by the workflow.
  8. Clean up the temp file: rm -f "$pr_body_file"
  9. Report the created PR URL and summarize title/base/head and any required follow-up.

Constraints

  • Never skip template sections.

  • Never rewrite the template format.

  • Keep content concise and specific to the current change set.

  • PR title and body must be written in English.

  • Never use a hotfix title or label for an ordinary bug fix. It opts the PR into an automatic backport PR after merge when one matching draft release is active.

  • A release hotfix may use NONE when it has no user-facing release note. Never provide a partial, single-language, or otherwise malformed bilingual note; the backport workflow fails closed on malformed content.

  • Never default a release/v<version> head to main; a release branch is not a pull request source branch.

  • Never create the PR before showing the full final body to the user, unless they explicitly waive the preview or confirmation.

  • Never rely on command permission prompts as PR body preview.

  • Release note & Documentation checkbox — both are driven by whether the change is user-facing. Use the table below:

    Change typeRelease noteDocs [x]
    New user-facing feature / setting / UIDescribe the change✅
    Bug fix visible to usersDescribe the fix✅ if behavior changed
    Behavior change / default value changeDescribe + action required✅
    Security fix in a user-facing dependencyDescribe the fix✅ if usage changed
    CI / GitHub Actions changesNONE❌
    Internal refactoring (user cannot tell)NONE❌
    Dev / build tooling changesNONE❌
    Dev-only dependency bumpNONE❌
    Test-only / code style changesNONE❌

Command Pattern

bash
# read template
cat .github/pull_request_template.md

# show this full Markdown body in chat first
pr_body_file="/tmp/gh-pr-body-$(date +%s).md"
cat > "$pr_body_file" <<'EOF'
...filled template body...
EOF
cat "$pr_body_file"

# run only after explicit user confirmation
gh pr create --base <base> --head <head> --title "<title>" --body-file "$pr_body_file"
rm -f "$pr_body_file"

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 Gh Create Pr AI skill do?

Create or update GitHub pull requests using the repository-required workflow and template compliance. Use when asked to create/open/update a PR so the assistant reads `.github/pull_request_template.md`, fills every template section, preserves markdown structure exactly, and marks missing data as N/A or None instead of skipping sections.

Why use Gh Create Pr on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/CherryHQ/cherry-studio/tree/main/.agents/skills/gh-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 Gh 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 Gh Create Pr?

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

Is the Gh Create Pr AI skill free?

Yes. It is published on GitHub by CherryHQ under the AGPL-3.0 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 👇