fcakyon/phd-skills

1

paper-writing Use when the user wants to write, structure, or revise academic paper sections, improve notation consistency, or refi…

fcakyon/phd-skills

144

2

literature-research Use when the user wants to find related work, survey a research area, identify literature gaps, or discover open-sour…

fcakyon/phd-skills

70

3

reproduce End-to-end paper reproduction from arxiv URL through smoke runs to replication experiments. Handles missing or partia…

fcakyon/phd-skills

70

4

paper-verification Use when the user wants to verify paper claims against code or data, audit numerical accuracy, check formula-code ali…

fcakyon/phd-skills

63

5

experiment-design Use when the user wants to design experiments, plan ablation studies, structure baselines, or create incremental eval…

fcakyon/phd-skills

59

6

reviewer-defense Use when the user wants to anticipate reviewer questions, select the strongest ablations to present, prepare rebuttal…

fcakyon/phd-skills

58

7

dataset-curation Use when the user wants to analyze dataset bias, create stratified samples, evaluate fairness, or plan dataset collec…

fcakyon/phd-skills

54

8

research-publishing Use when the user wants to prepare code for open-source release, create reproducible research artifacts, or structure…

fcakyon/phd-skills

54

9

latex-setup Use when the user wants to set up or troubleshoot a LaTeX environment, choose between biber and bibtex, install packa…

fcakyon/phd-skills

53

10

compare Same-epoch comparison of training runs across wandb, neptune, tensorboard, or mlflow. Aligns runs at the student's cu…

fcakyon/phd-skills

51

11

debug Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list, d…

fcakyon/phd-skills

51

12

launch Pre-flight checklist for long-running ML training jobs covering config diff, run naming, path verification, monitorin…

fcakyon/phd-skills

50