Skip to content
TrustedSkillsbeta
Back to all skills

Git 2 49 Features

Listed
josiahsiegel·vlatest·backend·MIT

Extracts and summarizes features from Git commit messages formatted as `git-2-49` reports for analysis.

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 josiahsiegel/claude-plugin-marketplace --skill git-2-49-features -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

josiahsiegel

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 failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No credential access: failed

    Touches credential material in 1 place.

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

    What it found

    • plugins/git-master/skills/git-2-49-features/SKILL.md:255.netrc credentials
      # ~/.netrc

  • 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 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 josiahsiegel/claude-plugin-marketplace at 5a1b1123b9.

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

Commit
5a1b1123b9
Manifest
plugins/git-master/skills/git-2-49-features/SKILL.md
Scanned
1 file, 292 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 enables AI agents to interact with Git repositories, allowing them to clone, branch, commit changes, and manage version control workflows directly. It bridges the gap between code generation and actual repository management within an agent's operational scope.

When to use it

  • Automating repetitive version control tasks like creating feature branches after generating new code.
  • Integrating AI-generated fixes or refactors directly into a specific Git branch without manual CLI intervention.
  • Managing commit history by having the agent draft and apply commits based on generated changes.

Key capabilities

  • Cloning repositories from remote sources
  • Creating and switching between branches
  • Staging and committing file changes
  • Executing Git commands via terminal interaction

Example prompts

  • "Clone the repository at [URL], create a new branch named 'fix-login-bug', and commit the generated code."
  • "Review the changes in the current working directory, stage all modified files, and write a commit message summarizing the AI's updates."
  • "Switch to the 'develop' branch, pull the latest changes from the remote, and prepare the environment for new feature implementation."

Tips & gotchas

Ensure the AI agent has appropriate read/write permissions to the target Git repository before attempting cloning or committing. Always verify that the generated commit messages accurately reflect the code changes made by the agent to maintain a clean history.