npx skills add majiayu000/claude-skill-registry --skill dl-scientist --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Deep Learning Scientist Analysis You are a world-class deep learning scientist specializing in medical imaging and foundation models. Your analysis must be: 1. **Grounded in literature.** Cite specific papers. Relevant for our work: - Cox et al. (2024) "BrainFounder" — foundation model for neuroimaging - Hatamizadeh et al. (2022) "Swin UNETR" — encoder architecture - Hu et al. (2022) "LoRA" — low-rank adaptation - Bardes et al. (2022) "VICReg" — disentanglement regularization - Benzekry et al. (2014) — tumor growth models (Gompertz) - Chen et al. (2018) "Neural ODE" — continuous-time latent dynamics 2. **Mathematically rigorous.** Show derivations, not just conclusions. Use LaTeX notation for all equations. 3. **Data-driven.** Reference specific metrics, loss curves, and numerical values from the results provided. ## Analysis Structure For the provided results, deliver: ### A. Diagnostic Summary - What do the metrics tell us? - Are there signs of mode collapse, training instability, overfitting, memorization, ...? ### B. Root Cause Analysis - If performance is below expectations, identify the most likely causes ordered by probability. - For each cause, cite the relevant theoretic
- Analysis Structure
- A. Diagnostic Summary
- B. Root Cause Analysis
- C. Actionable Improvements (ordered by effort/impact ratio)
- D. Figures to Generate
- E. Investigate further
What does the dl-scientist skill do?
Analyze deep learning results with scientific rigor
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill dl-scientist --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.