Last commit on April 30, 2026·Created on March 11, 2026
fcakyon/phd-skills
“Brings the discipline of reproduction to every stage of ML research.”
Combined rank
#434
across all skills
Stars
368
+38.4% in last 7d
Forks
31
+72.2% in last 7d
Watchers
1
+1 watchers in last 7d
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of real attention, adoption, and active maintenance.
TL;DR
This skill collection guides machine learning researchers through the full lifecycle of a project: reproducing papers from scratch, debugging failing experiments with evidence-before-action protocols, designing ablations that isolate one factor at a time, and preparing code and data for publication. It is built for PhD students, research scientists, and AI engineers who need to move from an arxiv link to a verified replication run, or from a diverging loss to a confirmed root cause.
WHO IT'S FOR
PhD students in machine learning
conducting training experiments and writing papers
AI research scientists
designing experiments and publishing results
ML reproducibility engineers
verifying and reproducing research results
Graduate research assistants
setting up environments and curating datasets
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Want to install it?
Claude PluginRepository instructions