deep-learning-scientist
v1.0.0Reasons from CNN/Transformer inductive bias, Li et al. loss landscapes, grokking/mode connectivity, and Kaplan/Chinchilla scaling (~20 tokens/param); designs ResNet/ViT/DiT/MoE/FlashAttention stacks with FLOPs-matched ablations; trains AdamW+cosine/WSD via Megatron-FSDP/DeepSpeed; evaluates FID/MMLU-Pro/MMLU-CF with lm-eval decontamination and Pineau/NeurIPS reproducibility checklists.
By K-Dense-AILicense: MIT199 GitHub starsUpdated 5 days ago
Directory evidence
- Runtimes
- Claude Code and Agent Plugins
- Parsed components
- 1 skill or MCP entry
- Source updated
- Oct 2, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install deep-learning-scientist for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install deep-learning-scientist@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/K-Dense-AI/scientific-agentsClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is scientific-agents/deep-learning-scientist/.
Plugin files
├── .claude-plugin/plugin.json├── plugin.json└── skills/deep-learning-scientist/SKILL.md
Included Skills1
Think and work like an expert Deep Learning Scientist. Use when a task calls for Deep Learning Scientist judgment. Reasons from CNN/Transformer inductive bias, Li et al. loss landscapes, grokking/mode connectivity, and Kaplan/Chinchilla scaling (~20 tokens/param); designs ResNet/ViT/DiT/MoE/FlashAttention stacks with FLOPs-matched ablations; trains AdamW+cosine/WSD via Megatron-FSDP/DeepSpeed; evaluates FID/MMLU-Pro/MMLU-CF with lm-eval decontamination and Pineau/NeurIPS reproducibility checklists.
Plugin manifests2
{
"name": "deep-learning-scientist",
"version": "1.0.0",
"description": "Reasons from CNN/Transformer inductive bias, Li et al. loss landscapes, grokking/mode connectivity, and Kaplan/Chinchilla scaling (~20 tokens/param); designs ResNet/ViT/DiT/MoE/FlashAttention stacks with FLOPs-matched ablations; trains AdamW+cosine/WSD via Megatron-FSDP/DeepSpeed; evaluates FID/MMLU-Pro/MMLU-CF with lm-eval decontamination and Pineau/NeurIPS reproducibility checklists.",
"author": {
"name": "K-Dense-AI",
"url": "https://github.com/K-Dense-AI"
},
"homepage": "https://github.com/K-Dense-AI/scientific-agents",
"keywords": [
"science",
"agents-md",
"expert-profile",
"deep-learning-scientist"
]
}{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "deep-learning-scientist",
"version": "1.0.0",
"description": "Reasons from CNN/Transformer inductive bias, Li et al. loss landscapes, grokking/mode connectivity, and Kaplan/Chinchilla scaling (~20 tokens/param); designs ResNet/ViT/DiT/MoE/FlashAttention stacks with FLOPs-matched ablations; trains AdamW+cosine/WSD via Megatron-FSDP/DeepSpeed; evaluates FID/MMLU-Pro/MMLU-CF with lm-eval decontamination and Pineau/NeurIPS reproducibility checklists.",
"author": {
"name": "K-Dense",
"url": "https://www.k-dense.ai"
},
"homepage": "https://github.com/K-Dense-AI/scientific-agents",
"repository": "https://github.com/K-Dense-AI/scientific-agents",
"license": "MIT",
"keywords": [
"science",
"agents-md",
"expert-profile",
"deep-learning-scientist"
]
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[deep-learning-scientist on Agent Plugins Marketplace](https://pluginsmp.com/plugins/deep-learning-scientist)