he-yufeng

GitSense — AI skill for Claude Code

AI community

AI-powered open source contribution finder and repo radar.

How to install GitSense

This entry records only its repository, not the path inside it, so there is no exact command to give. Open he-yufeng/GitSense and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What GitSense does

AI-powered open source contribution finder and repo radar.

Alternatives in AI

  • Multica — Make humans and AI agents work as one team — open-source and self-hostable 47.8k ★
  • Invisible Dots — Open-source, self-hosted alternative to OpenAI Dots, Meta Muse, Grok Bot, Manus Cue and Claude Cowork 31.8k ★
  • AIHawk — Open-source AI browser agent: describe any task in plain language and it autonomously browses, clicks, types a 30.3k ★

README

GitSense — find your next open-source contribution

Tell it your skills → it searches GitHub for open issues you can fix → ranks them by match → scores repos by maintainer responsiveness and PR merge patterns.

[![PyPI](https://img.shields.io/pypi/v/gitsense-radar.svg)](https://pypi.org/project/gitsense-radar/) [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE) [![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/) [![CI](https://github.com/he-yufeng/GitSense/actions/workflows/ci.yml/badge.svg)](https://github.com/he-yufeng/GitSense/actions)

**[English](README.md) · [中文](README_CN.md)**  ·  [Quick Start](#quick-start) · [Demo](#demo) · [How It Works](#how-it-works)


The Problem

You want to contribute to open source, but finding the right issue is painful. You scroll through hundreds of issues on GitHub, most of which are either claimed, too vague, out of your skill range, or just not worth the effort. By the time you find something decent, you've burned an hour on browsing alone.

**GitSense** does the searching for you. It queries GitHub for open, unassigned issues across thousands of repos, then uses an LLM to rank them by how well they match YOUR specific skills and tell you exactly how to get started.

The new Radar mode answers the next question: is this repo actually worth your PR? It checks public PR history, stale backlog, open-to-merged PR pressure, outsider merge ratio, and maintainer response time before you invest a weekend in a repo that might ignore good work.

Quick Start

pip install gitsense-radar
# Find open issues that match your skills, ranked by an LLM
gitsense find --skills python,llm,cuda

# Scan one repo, or score repos before you invest a weekend
gitsense scan vllm-project/vllm --skills python,cuda
gitsense radar vllm-project/vllm microsoft/qlib