Skip to content
TrustedSkillsbeta
Back to all skills

Git Workflows

Checked
autumnsgrove·vlatest·backend

Automates common Git workflows like branching, merging, pull requests, and commits based on natural language instructions.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add autumnsgrove/lattice --skill git-workflows -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

autumnsgrove

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned autumnsgrove/groveengine at edebdc71a7.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
edebdc71a7
Manifest
.claude/skills/git-workflows/SKILL.md
Scanned
1 file, 169 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill automates common Git and GitHub workflows, such as branching, merging, pull requests, commits, and issue management. It leverages Grove Wrap (gw) to provide a safe and controlled environment for version control operations. All interactions with Git and GitHub are mediated through gw, preventing direct use of raw git or gh commands. The system enforces safety tiers and Conventional Commits formatting to ensure code quality and security.

When to use it

  • Making commits, pushing changes, pulling updates, branching, or stashing code.
  • Creating, reviewing, or merging pull requests.
  • Managing GitHub issues (creating, viewing, closing).
  • Checking the status of CI/workflow runs.
  • Reviewing Git history, diffs, or blame information.
  • Resolving merge conflicts.
  • Performing any version control operation.

Key capabilities

  • Safe Workflow Execution: All Git and GitHub operations are handled through Grove Wrap (gw) for enhanced safety.
  • Three-Tiered Safety Model: Commands require flags (--write, --force) to control access levels (READ, WRITE, DANGEROUS).
  • Protected Branch Enforcement: Force pushing is prohibited on main, master, production, and staging branches.
  • Conventional Commits Validation: Commit messages are automatically validated against the Conventional Commits format (<type>(<scope>): <description>).
  • Dry Run Support: Use --dry-run to preview command actions before execution.
  • Agent Mode: Enhanced security and limitations for agents like Claude Code (stricter row limits, blocked force operations, audit logging).

Example prompts

  • "gw git status" - Check the current Git status.
  • "gw git commit --write -m 'feat: add user profile page'" - Commit changes with a Conventional Commits message.
  • "gw gh pr create" - Create a new pull request.

Tips & gotchas

  • Always use gw: Direct Git or GitHub commands are not permitted.
  • Understand Safety Tiers: Be mindful of the required flags (--write, --force) for different operations.
  • Conventional Commits: Adhere to the Conventional Commits format for commit messages.