I stopped hunting for good first issues. A Gemma inside GitHub Actions does it while I sleep

Description and use

FirstPick automates finding and explaining beginner-friendly issues in AI repositories using a local Gemma model, cutting manual search and speeding up first contributions.

Problem

Finding beginner-friendly GitHub issues in AI repos is tedious and often leads to closed or already claimed issues.

Outcome

FirstPick streamlines the process of finding and understanding beginner-friendly issues, reducing manual effort and enabling quick contributions.

Workflow

• Collect open, unassigned issues labeled good first issue / beginner / easy from 8 active Python AI repos
• Score issues against the user profile, recency, and comment count
• Re-check the top 15 live before delivery, dropping closed or claimed issues
• Explain the top 5 with a local Gemma: summary, difficulty rating, learning outcomes, and first steps

Evidence

FirstPick finds beginner-friendly GitHub issues in open-source AI repos, drops the ones someone has already taken, and hands me the 5 best, explained in plain English by Gemma running on my own laptop.

Source

Collects open, unassigned issues labeled good first issue / beginner / easy from 8 active Python AI repos

Source

Explains the top 5 with a local Gemma: a summary, a difficulty rating with the reason, what you'd learn, and 2–4 first steps.

Source

Model’s answers too: ... Ollama is called with a JSON schema, and every answer is checked again in Python: required fields, length limits, and a difficulty that must be easy, medium or tricky.

Source