217 tagged deep-learning, measured the same way as everything else here.
Browse within: LLM 114agent 105machine-learning 101foundation-models 99PyTorch 43computer-vision 43claude-code-plugin 32GPU 29neural-network 29object-detection 27agents 25data-science 25face-recognition 25fine-tuning 25
Skill Claude Code
Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit apps. Also custom components, st.components.v2, HTML/JS/CSS work. Discovers and loads version-matched reference docs from the user's installed Streamlit (>=1.57). Triggers: streamlit, st.…
Skill Claude CodeCodex
Use this meta-skill instead of answering directly when the current user asks to draft or produce a new academic/research paper or LaTeX manuscript. It uses multi-skill orchestration for manuscript workflows that need source search, citation planning, experiment or figure/table placeholders, drafting, length checks…
Skill Claude CodeCodex
Redact personal data from a document through the connected Superlinked MCP edge before working with the content. Use when the user asks to redact, anonymize, scrub, de-identify, or remove PII/sensitive data from a document.
Skill Claude CodeCodex ✓ vendor
Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor…
Skill Claude CodeCodex
LLM & VLM evaluation suite for home security AI applications.
Xiangyue-Zhang/auto-deep-researcher-24x7
Skill Codex
Daily arXiv paper recommendations with automatic deduplication.
Skill Claude CodeCodex
Adversarial research analysis framework that uses structured Bull/Bear/Arbiter debates to help users make better research judgments. Maintains a belief graph as backend engine, applies statistical calibration discipline, tracks phase transitions, and detects biases. MANDATORY TRIGGERS: Use this skill whenever the user…
Skill Claude Code
Process whole-slide pathology images (WSIs) with TRIDENT: tissue segmentation, patch coordinate extraction, and patch/slide feature (embedding) extraction with foundation models (UNI, CONCH, Virchow, Gemma, Titan, GigaPath, etc.). Use when the user works with WSIs (.svs/.tiff/.ndpi/.mrxs/.czi/.dcm), mentions TRIDENT…
Skill Claude Code needs its repo
Generate a fact-checked academic personal homepage from a CV, optionally augmented by an existing manual homepage and an assets directory. Produces editable structured source files (profile.yml + publications.bib + bio.md + news.md) and a single-file HTML page. Uses Codex MCP for independent factual review against…
Skill Codex
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted…
ATOM00blue/machine-learning-library
Skill Claude Code
Retrieve and cite from this machine-learning education corpus (923 docs — arXiv papers, course lectures, explainer articles). Use when the user asks an ML/deep-learning question, wants to learn a topic, asks for sources/papers/lectures on a concept, or wants a study path grounded in this repo.
graphsignal/graphsignal-profiler
Skill Claude CodeCodex
Set up the Graphsignal Profiler for inference workloads — vLLM, SGLang, PyTorch, and dstack services. Use when the user wants GPU profiling, tracing, or monitoring for inference, asks about graphsignal-run or graphsignal.watch(), or asks about CUPTI / Prometheus / OTLP setup.
Skill Claude CodeCodex
Expert in PerforatedAI library for adding artificial dendrites to PyTorch neural networks. Triggers: 'Perforate my model' (start interactive setup), 'debug my perforated model' (debug/optimize existing integration), 'load my perforated model for inference' (deploy trained models), 'export my perforated model'…
Skill Claude CodeCodex
A Chinese-language learning assistant for MiniMind, a small language-model project, that records study notes and recognizes common machine-learning terms.
Skill Claude CodeCodex
Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo.
diegosouzapw/awesome-omni-skills
Skill Claude CodeCodex
ANDREJ KARPATHY — SKILL COMPLETA v2.0 workflow skill. Use this skill when the user needs Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo and the operator should preserve the upstream workflow, copied support…
Skill Claude CodeCodex
Use when writing Deepbox code, examples, or full projects so imports, module selection, dtypes, training loops, errors, backends, docs pages, and framework-specific patterns stay accurate.
Skill Claude Code
Guide for training PyTorch models using this template's config-driven pipeline. Use this skill whenever the user wants to: train a model, create experiment configs (run.yaml / opt.yaml / best.yaml), run hyperparameter optimization (HPO) with Optuna, extract best parameters from an HPO study, set up a new experiment…
Ztsdut/ml-architecture-diagram-skill
Skill Claude CodeCodex
Create accurate, publication-ready, editable machine-learning and deep-learning architecture diagrams from model code, configuration files, model summaries, graph exports, or written specifications. Use for neural-network figures, architecture schematics, model block diagrams, training/inference diagrams, paper…
Liu-MingH/Scientific-research-SKILL
Skill Claude CodeCodex
Structured AI-assisted scientific code generation. 6 safety guards, 8 principles, 11 prompt templates. Grounded in Nature (2026).
Skill Claude CodeCodex
Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: