agentmods.dev

deep-learning-expert

A guide to deep learning, where neural networks learn patterns from data, with coverage of model architecture, training strategies, debugging, and research-paper interpretation. It focuses on PyTorch and TensorFlow.

In plain words
What is it for?
Use it to design, train, debug, compare, or deploy deep-learning models, and to understand or reproduce methods from research papers.
Why use it?
It helps with choosing model structures, improving training, and finding the cause of failures such as poor learning or unstable results.

Plugin for Claude Code

5 3mo ago A scan tokens not measured original MIT
View the source file Miaoge-Ge/coding-agent-skills
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add Miaoge-Ge/coding-agent-skills
agentmods
npx agentmods add plugins/miaoge-ge/coding-agent-skills/deep-learning-expert
Clone the repo
git clone --depth 1 https://github.com/Miaoge-Ge/coding-agent-skills

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 100 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

deep-learning-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/deep-learning-expert/.claude-plugin/plugin.json · 13 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "deep-learning-expert",
  "displayName": "Deep Learning Expert",
  "version": "1.0.0",
  "description": "Model architecture design, training strategies, debugging, and paper interpretation (PyTorch/TensorFlow).",
  "author": { "name": "Miaoge-Ge", "email": "[email protected]" },
  "homepage": "https://github.com/Miaoge-Ge/coding-agent-skills",
  "repository": "https://github.com/Miaoge-Ge/coding-agent-skills",
  "license": "MIT",
  "keywords": ["deep-learning", "pytorch", "tensorflow", "neural-networks", "training", "cv", "nlp"]
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 100 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 13 lines scan A ee6a2e327e20

Subscribe to this mod's changes

deep-learning-expert is a plugin published in the GitHub repository Miaoge-Ge/coding-agent-skills (5 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AIScientificaiclaude-codecoding-assistantcursorprompt-engineeringsystem-prompts
Related

Other plugins, from other repositories

anesthesiologist

Reasons from control of consciousness, analgesia, autonomic response, and oxygen delivery through the ASA Difficult Airway Algorithm, capnography and arterial-waveform trends, quantitative TOF monitoring, and ASRA/ERAS protocols while treating cannot-ventilate airways, local anesthetic systemic toxicity, malignant…

K-Dense-AI/scientific-agents · not measured

scholar-feed

Search 600,000+ CS/AI/ML papers with LLM novelty analysis, citation graph, full-text extraction, and BibTeX, without leaving Claude Code. Built for literature reviews.

YGao2005/scholar-feed-mcp · not measured

protein-design-skills marketplace

Claude Code skills for computational protein design - backbone generation, sequence design, structure prediction, and experimental validation.

adaptyvbio/protein-design-skills · not measured

geoai

18 Agent Skills covering the full geospatial data science lifecycle: data engineering, remote sensing, Earth Engine, deep learning, spatial statistics, geostatistics, terrain, networks, LiDAR, trajectories, change detection, MCDA, PostGIS, cartography, and guarded ArcGIS Pro automation.

muend/geoai-skills · not measured

tml

tuneml — a read-first advisor for training and evaluating neural networks well: the scientific method for tuning, and the speed↔quality frontier, in one place. Prices every candidate change in time-to-target-quality rather than throughput, grades the evidence behind it, and names what it would silently break. Five…

emaballarin/ccplugins · not measured

openproblems-spatial

Domain skills + MCP validation tools for OpenProblems spatial transcriptomics benchmarks (SpatialData/zarr, Viash, the iST preprocessing pipeline).

Rebell-Leader/SpatialAI_MCP · not measured