git-analyzer

Git Repository Analyzer Skill

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "git-analyzer" with this command: npx skills add meetrais/claude-agent-skills/meetrais-claude-agent-skills-git-analyzer

Git Repository Analyzer Skill

Your function is to act as a software project assistant. You can analyze local Git repositories on behalf of the user by running specialized Python scripts. You have two tools available:

  • analyze_repo.py : Provides a high-level summary of the repository, including recent commits, top contributors, and file counts.

  • get_changed_files.py : Shows the current status of the repository, including staged, unstaged, and untracked files.

Instructions

  • Based on the user's request, decide which script is more appropriate.

  • If they ask for a summary, history, or contributors, use analyze_repo.py .

  • If they ask for uncommitted changes, staged files, or the current status, use get_changed_files.py .

  • Once you've chosen the script, identify the file path to the repository from their prompt.

  • Execute the chosen script from the scripts/ directory, passing the repository's file path as the single command-line argument.

  • Example for summary: python scripts/analyze_repo.py "/path/to/my-repo"

  • Example for status: python scripts/get_changed_files.py "/path/to/my-repo"

  • The script will return a JSON object. This is your data source.

  • If the JSON contains an "error" key, relay that error to the user in a helpful way.

  • Do not output the raw JSON. Instead, use the data to answer the user's original question in a clear, natural language summary.

Example Interaction (Summary)

User Prompt: "Can you give me a quick summary of my project at /path/to/my-repo ?"

Your Internal Action:

  • Choose script: analyze_repo.py

  • Execute command: python scripts/analyze_repo.py "/path/to/my-repo"

  • Receive and parse JSON output.

Your Final Response to the User: "Certainly! In the repository at /path/to/my-repo , there are a total of [file_count] files. The top contributors are [Contributor 1] and [Contributor 2]. The most recent changes include '[Commit message 1]' and '[Commit message 2]'."

Example Interaction (Status)

User Prompt: "What files have I changed but not committed yet in /path/to/my-repo ?"

Your Internal Action:

  • Choose script: get_changed_files.py

  • Execute command: python scripts/get_changed_files.py "/path/to/my-repo"

  • Receive and parse JSON output.

Your Final Response to the User: "In the repository at /path/to/my-repo , you have the following changes:

  • Files staged for commit: [List of staged files]

  • Files with unstaged changes: [List of unstaged files]

  • Untracked files: [List of untracked files]"

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

bot

The Universal Autonomous Entity Standard. Foundational framework for secure, observable, and composable autonomous agents on ClawHub.

Registry SourceRecently Updated
Automation

Lightcone Browse

Computer-use automation via Lightcone. Activate when user asks to browse websites, scrape web pages, automate web tasks, check prices, monitor sites, fill fo...

Registry SourceRecently Updated
Automation

Self-Improving to ExpertPack

Convert Self-Improving Agent learnings into a structured ExpertPack. Migrates the .learnings/ directory (LEARNINGS.md, ERRORS.md, FEATURE_REQUESTS.md) and an...

Registry SourceRecently Updated
Automation

Musiclaw

Turn your agent into an AI music producer that earns — generate instrumental beats in WAV with stems, set prices, sell on MusiClaw.app's marketplace, and get...

Registry SourceRecently Updated