Github Pr Workflow logo

Github Pr Workflow

Community
AlexAI-MCP
github-pr-workflow

Run a disciplined GitHub pull request workflow from branch creation through merge. Use when opening a PR, updating a PR after review, preparing review-ready diffs, managing draft versus ready states, or landing changes with clear validation and risk notes.

Overview

PublisherAlexAI-MCP
Repositoryhermes-CCC
Skill namegithub-pr-workflow
Stars
134
Forks
22
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 AlexAI-MCP on GitHub. Read the source before you install it.

Installation

Install the Github Pr Workflow 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/AlexAI-MCP/hermes-CCC/tree/master/skills/github-pr-workflow
  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/AlexAI-MCP/hermes-CCC.git /tmp/hermes-CCC
mkdir -p .claude/skills
cp -r /tmp/hermes-CCC/skills/github-pr-workflow .claude/skills/github-pr-workflow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Github Pr Workflow 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 Github Pr Workflow 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 Github Pr Workflow 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 Workflow

Purpose

  • Keep pull requests reviewable and easy to merge safely.
  • Separate implementation from presentation and merge hygiene.
  • Make reviewer intent clear through titles, descriptions, and test plans.
  • Reduce merge friction by handling updates systematically.
  • Preserve traceability between issue, code, and validation.

Activation Signals

  • Use this skill when opening a new branch for changes.
  • Use this skill when preparing a PR for review.
  • Use this skill when updating a PR after feedback.
  • Use this skill when turning a draft into a merge-ready PR.
  • Use this skill when planning labels, reviewers, and merge strategy.

Core Workflow

  1. Start from the correct base branch.
  2. Keep the branch scope tight.
  3. Make coherent commits.
  4. Validate before opening the PR.
  5. Open a draft PR if the implementation is not review-ready.
  6. Write a useful PR title and description.
  7. Address review comments with focused follow-up commits.
  8. Re-validate before merge.
  9. Merge with the right strategy.

Branch Rules

  • Branch from the intended base, not a stale local branch.
  • Name the branch after the work, not the date.
  • Keep unrelated changes out of the branch.
  • Avoid force-push unless the team allows it and history cleanup is worth it.

Commit Rules

  • One logical change per commit when practical.
  • Use commit messages that explain intent, not just files touched.
  • Avoid mixing refactor and bug fix unless inseparable.
  • Keep WIP commits local when possible.

Pre-PR Validation

  • run targeted tests
  • run lint if relevant
  • check formatting if the repo enforces it
  • read the diff yourself before asking others to do it
  • note any unverified areas explicitly

PR Title Rules

  • Lead with the user-visible or system-visible change.
  • Keep it specific.
  • Avoid "misc fixes".
  • Prefer imperative summaries such as "Fix auth redirect loop during token refresh".

PR Description Template

markdown
## Summary
- ...

## Why
- ...

## Testing
- `pytest tests/test_auth.py::test_login_redirect_does_not_loop_when_session_is_hydrated -vv`

## Risks
- ...

Draft Versus Ready

  • Open as draft when the implementation is incomplete.
  • Open as draft when feedback on direction is needed before polishing.
  • Convert to ready only after validation and self-review.
  • Do not ask for full review while the branch still contains known broken paths.

Review Update Procedure

  1. Group comments by theme.
  2. Resolve the highest-risk comments first.
  3. Make focused follow-up commits.
  4. Reply with what changed and where.
  5. Re-run the relevant validation.
  6. Avoid "fixed" with no evidence.

Merge Strategy

  • Use merge commit when preserving branch history matters.
  • Use squash when the branch contains several noisy intermediate commits.
  • Use rebase when the repository prefers linear history and the branch is clean.
  • Follow repo policy when it is explicit.

Useful Commands

bash
git checkout -b fix-auth-redirect-loop
git status --short
git diff --stat
gh pr create --draft --title "Fix auth redirect loop during token refresh" --body-file PR_BODY.md
gh pr view --web

Reviewer Experience Rules

  • Keep the diff small enough to review in one sitting.
  • Explain why the change exists.
  • State how you validated it.
  • Admit unknowns.
  • Link related issues or incidents.

Anti-Patterns

  • giant PRs with mixed concerns
  • vague PR titles
  • empty descriptions
  • no testing notes
  • force-pushing away reviewer context without warning
  • mixing comment resolution with unrelated cleanup

Output Contract

When reporting PR progress, include:

  • branch name
  • PR state: draft or ready
  • summary of changes
  • validation performed
  • remaining risks or blockers

Example Status Block

markdown
PR workflow status:
- Branch: fix-auth-redirect-loop
- State: draft
- Summary: auth middleware now waits for hydrated session token before redirecting
- Validation: targeted auth regression test passed
- Remaining blocker: reviewer input needed on fallback behavior during refresh timeout

Decision Rules

  • If the diff is large, split before asking for review when possible.
  • If the PR changes behavior, tests should usually change too.
  • If validation is partial, state the gap explicitly.
  • If the branch drifted from base, rebase or merge base before final review.

Recovery Moves

  • If review comments are scattered, create a comment-response checklist.
  • If the branch became messy, squash or reorder before final merge if policy allows.
  • If new scope appears, consider a follow-up PR instead of growing the current one.
  • If CI fails, fix CI before asking for another full review pass.

Checklist

  1. Start from the correct base branch.
  2. Keep scope tight.
  3. Self-review the diff.
  4. Validate locally.
  5. Open draft or ready appropriately.
  6. Write a strong title and description.
  7. Address feedback in focused updates.
  8. Re-validate before merge.

Frequently asked questions

What does the Github Pr Workflow AI skill do?

Run a disciplined GitHub pull request workflow from branch creation through merge. Use when opening a PR, updating a PR after review, preparing review-ready diffs, managing draft versus ready states, or landing changes with clear validation and risk notes.

Why use Github Pr Workflow on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/github-pr-workflow. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Github Pr Workflow?

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 Github Pr Workflow?

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

Is the Github Pr Workflow AI skill free?

Yes. It is published on GitHub by AlexAI-MCP 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 👇