git-pr-workflows-git-workflow
Helps your agent manage the code review workflow. Coordinates tests, commits, and pull request creation.
What it does
This agent helps organize the process of submitting your code changes for review. It ensures everything is tested, properly recorded, and sent as a pull request without breaking project rules.
When to use it
- ✓When you finish writing code and want to submit it for others to review.
- ✓When the project has strict rules on how code should be submitted and tested.
- ✓When you want to automate the process of creating a pull request after making changes.
Example of what to ask your AI
“I want to submit my latest changes for review, test everything, and create a pull request to the main branch.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
The agent first checks the current state of your code and the project's rules. Then, it runs tests and validations, prepares your changes on a new branch, and finally creates the pull request with all necessary information.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add sickn33/agentic-awesome-skills --skill git-pr-workflows-git-workflowOr download just the file:
curl -L https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/plugins/agentic-awesome-skills-claude/skills/git-pr-workflows-git-workflow/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Guarded Git Pull Request Workflow
Move completed changes from local review to a verified pull request without bypassing repository policy or branch protection.
When to Use
Use for completed implementation work that must be reviewed, tested, committed, pushed to a topic branch, and opened as a pull request. Use the repository's dedicated maintainer or release workflow instead when one is mandatory.
Policy Gate
Before mutation:
- Read
AGENTS.md, contribution guidance, maintainer docs, and relevant nested instructions. - Inspect the current branch, worktree, remotes, upstream, and effective target-branch protection.
- Discover repository-native validation, commit, PR, merge, and release commands.
- Preserve unrelated dirty and staged files.
Repository policy wins over flags and user shorthand. Trunk-based development does not imply a direct push: when the target is protected, use a short-lived branch and pull request. If a repository defines a mandatory maintainer skill or guarded merge command, hand off merge and release actions to it. In agentic-awesome-skills, use antigravity-maintainer-batch-release and npm run merge:batch.
Inputs
Resolve these from the request and repository:
- target branch, defaulting to the repository default branch;
- intended changed files and excluded user work;
- required test, lint, security, build, and documentation checks;
- branch naming and commit-message conventions;
- draft or ready-for-review PR state;
- required reviewers, labels, issue links, and merge method.
Ask only when a missing choice changes the result materially.
Workflow
1. Capture the exact change
git status --short --branch
git diff --stat
git diff --cached --stat
git branch --show-current
git remote -v
Confirm every file in scope. Stop if staged or dirty files cannot be separated safely.
2. Review in parallel
When subagents are available and authorized, assign independent bounded passes for:
- correctness and regression risk;
- security, secrets, permissions, and dependency risk;
- test coverage and repository-policy compliance.
Give each reviewer the raw diff and repository instructions. Keep the main agent responsible for deduplication, severity, edits, and final verification.
3. Validate and repair
Run the repository's targeted checks, then its required pre-PR suite. If a check fails:
- identify whether the cause is source, policy, environment, or infrastructure;
- fix only source or policy defects in scope;
- rerun the targeted failure;
- rerun the complete required suite.
Do not weaken gates, hide skipped tests, or treat deterministic failures as flaky.
4. Prepare the branch and commit
Fetch the target before committing. If currently on a protected/default branch, create a topic branch before mutation.
git fetch origin <target-branch>
git switch -c <topic-branch> origin/<target-branch>
git status --short --branch
Stage only intended paths and create focused conventional commits according to repository policy. Rebase or update the topic branch when strict required checks demand the latest target; never force a shared branch without explicit authorization.
5. Push and create the pull request
git push -u origin <topic-branch>
gh pr create --base <target-branch> --head <topic-branch> \
--title "<conventional title>" --body-file <body-file>
The PR body must truthfully include:
- what changed and why;
- tests and validation actually run;
- risk, deployment, rollback, and breaking-change notes when applicable;
- issue links, screenshots, and repository checklists when applicable.
Never mark a pending automated review or test as completed.
6. Verify the remote result
gh pr view <pr-number> --json headRefOid,baseRefOid,mergeable,mergeStateStatus,url
gh pr checks <pr-number>
Bind review evidence to the current full head SHA. If the head or base changes, discard stale conclusions and rerun affected checks.
Use the repository's guarded merge path. Do not replace required checks, merge queues, exact-SHA attestations, or maintainer commands with a raw merge API. After merge, fetch the target and verify the requested remote, CI, deployment, or release state.
Stop Condition
…
FAQ
What is a pull request?
It's a request to have your code changes incorporated into the main project. Others can review your code before it's accepted.
What are branches?
Branches are like parallel copies of the project where you can work on new features or fixes without affecting the main code. You can then merge your changes back.
What happens if tests fail?
The agent will try to identify the problem and fix it if it's related to your code or project rules. It won't proceed if important tests fail.
Details
Original description by the author
Orchestrate review, tests, commits, branch pushes, and pull-request creation with parallel agents. Use when completed changes must move through validation into a PR or guarded merge.
Popularity
- GitHub stars
- 48k
- Ranking position
- #3123
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
00-andruia-consultant
Helps your agent start or improve AI projects. It analyzes code, suggests tools, and creates action plans in Spanish.
sickn33/agentic-awesome-skills
007
Lets your agent perform security audits and threat modeling. It's useful for protecting projects against attacks and vulnerabilities.
sickn33/agentic-awesome-skills
10-andruia-skill-smith
Helps your agent create or improve AI tools. It defines how tools work, writes documentation, and validates the structure.
sickn33/agentic-awesome-skills
20-andruia-niche-intelligence
Lets your agent create a summary about a specific industry. It's useful for understanding the context, rules, usage patterns, and risks of a project, using reliable sources.
sickn33/agentic-awesome-skills
Similar skills
bun-runtime
Has your agent use Bun to run, organize, and test code. It helps choose Bun over other tools and migrate existing projects.
affaan-m/ECC
database-migrations
Helps your agent make safe changes to databases. It ensures changes can be undone and minimizes downtime.
affaan-m/ECC
deployment-patterns
Sets up deployment and CI/CD workflows, containerization, and rollback strategies to ensure safe releases.
affaan-m/ECC