| Machine Learning | 19 |
|---|---|
| Computer Vision | 0 |
| Data Science | 8 |
| NLP & LLMs | 51 |
| AI Agents | 63 |
| MLOps | 19 |
Each node is one domain, scored only from evidence in these public repositories. Select one to see why.
Substantial implementations with real depth.
93 public repositories → 3 with AI work, evaluated. The other 90 (repositories without AI code, forks and empty repositories) are not scored and have no effect on the result. How repositories are selected
Ordered by how much each project adds to the Atlas score, not by its own score. A project with evidence in several domains can rank above one with a slightly higher project score. Choose a domain to focus on the projects with meaningful evidence there.
51% of Atlas Score
The gh-skills repository provides a collection of 14 AI agent skills for automating GitHub pull request workflows, enabling agents to manage PRs from opening to merging and cleanup. It includes an installer, documentation, and a validation script to ensure skill correctness.
32% of Atlas Score
The SDD Training Platform is a progressive, hands-on system for learning Spec-Driven Development (SDD) through interactive exercises, automated validation, and both CLI and web interfaces.
16% of Atlas Score
The agentic-comparison repository is a Jekyll-based static site that serves as a skills marketplace and comparison tool for AI coding agents. It provides curated data on 40+ AI skills across 10+ tools, along with documentation and helper scripts for data maintenance.
