theorems-harness
claudecodexTheorem's Harness: GraphQL-first MCP for adaptive planning, context, coordination, execution, validation, memory, and learning.
37 skills · 11 commands · 10 agents · 1 MCP server · hooks
0
claude
ml-pro
ML engineering plugin: build, train, debug, and deploy machine learning systems with verified API knowledge. 5 domain-expert agents (model-architect, training-engineer, ml-debugger, graph-engineer, systems-optimizer), 6 reference files, 5 runnable templates, and 4 workflow commands.
/
Plugin ml-pro from marketplace codex-marketplace in Travis-Gilbert/claude-marketplace. Commands read from the repo's manifest — 1 month ago.
What it installs
Slash commands (5)
/ml-pro:learnEnd-of-session learning. Saves what happened, updates
/ml-pro:ml-buildBuild an ML system from a handoff document or problem description
/ml-pro:ml-debugDiagnose and fix ML training failures using the 5-step protocol
/ml-pro:ml-deployExport, optimize, and deploy a trained model
/ml-pro:ml-trainGenerate a complete training pipeline for a model
Subagents (5)
graph-engineerSpecializes in graph ML: GNN architecture, PyG data handling, message passing, knowledge graph embeddings, link prediction, node classification. Route here for: any GNN task, "graph neural network," "knowledge graph," "link prediction," "node classification," "message passing," "PyG," "PyKEEN," or a
ml-debuggerDiagnoses and fixes ML training failures. Follows a systematic protocol: overfit-one-batch, loss curve analysis, gradient inspection, data pipeline verification, simplification. Route here for: "training isn't working," "loss is stuck," "loss is NaN," "model isn't learning," "overfitting," or any tr
model-architectDesigns ML model architectures. Selects layers, dimensions, activations, normalization, and skip connections. Produces complete nn.Module code with parameter counts and shape annotations. Route here for: "build a model," "design the architecture," "what layers should I use," or any request to create
systems-optimizerOptimizes ML systems for production. Mixed precision, torch.compile, distributed training, quantization, profiling, memory optimization, inference serving. Route here for: "make this faster," "reduce memory," "deploy this model," "optimize inference," "distributed training," "quantize," "profile," o
training-engineerBuilds complete training pipelines. Data loading, loss functions, optimizers, schedulers, training loops, validation, checkpointing, and experiment tracking. Route here for: "write the training loop," "set up training," "train this model," or any request to create or modify training infrastructure.
More from Travis-Gilbert/claude-marketplace
All 21 plugins →js-pro
claudeJavaScript expertise plugin with 27 specialist agents covering frontend frameworks, D3.js visualization (force tuning, hierarchy, annotations, clustering, interaction, labels, style presets), Three.js / React Three Fiber / Drei 3D development, and access to real framework source code. Includes skills for JS design patterns, D3 standards, Three.js design, component APIs, and framework migration.
5 skills · 1 command · 27 agents
0
theseus-pro
claudecodexIntelligence engineering plugin for building systems that learn from their own operation. Successor to SciPy-Pro v4. Provides 7 workflow commands (/reason, /graph, /train, /architect, /simulate, /measure, /learn), 24 domain-expert agents across three tiers, and compound-learning + enrichment-pipeline guidance for EpiGNN, KGE RotatE, SBERT, GL-Fusion, model-swarm routing, and network effects.
1 skill · 7 commands · 24 agents
0
animation-pro
claudeAnimation & motion expertise across four domains: UI motion, creative/generative, 3D animation, and programmatic video. Backed by 21 reference source repos and specialized agents grounded in real implementations.
4 skills · 9 commands · 10 agents
0
swift-pro
claudeNative iOS and macOS development plugin with deep expertise in SwiftUI, Swift 6 concurrency, SwiftData, XcodeBuildMCP integration, and Apple platform conventions.
12 commands · 9 agents · hooks
0
django-engine-pro
claudeDjango backend mastery: model architecture, ORM optimization, API design (DRF + Ninja), django-polymorphic patterns, MCP server construction, scientific Python integration, and Pydantic v2 mapping. Source-code-backed with Django ORM internals, DRF, Ninja, django-polymorphic, django-mcp-server, django-model-utils, django-pandas, django-filter, Pydantic v2, PydanticAI, and dj-notebook.
1 skill · 9 commands · 7 agents
0
Similar plugins
dominodatalab
claudeFull Domino Data Lab platform support — workspaces, jobs, model deployment, experiment tracking, GenAI tracing, Spark/Ray/Dask, and app deployment for data science teams
26 skills · 4 commands · 3 agents · 1 MCP server
anthropics/claude-plugins-official 47,076
deep-learning-book
claudeStudy companion for the Deep Learning textbook by Goodfellow, Bengio & Courville (MIT Press, 2016), free to read at deeplearningbook.org. Twenty chapter files, a glossary, patterns and a cheatsheet index the whole book, and a delta reference dates it against 2026 practice with per-claim confidence levels: double descent qualifying the U-curve, AdamW splitting weight decay from L2, transformers displacing Chapter 10's recurrence, diffusion growing out of Chapter 18's score matching. Four stdlib tools make it executable — a prerequisite-closed reading-path planner that refuses goals the book does not cover, a training diagnostic running Chapter 11's rules in priority order so a NaN is never reported as overfitting, a capacity planner that ranks 'shrink the model' last when overparameterized, and a parameter/FLOP/activation-memory calculator that refuses a stack whose shapes do not connect. A companion, not a compilation: the book is copyrighted, so nothing here reproduces its text.
1 skill · 3 commands · 1 agent
alirezarezvani/claude-skills 29,725
voltagent-data-ai
claudeData engineering, ML, and AI specialists - data pipelines, machine learning, LLM architecture
VoltAgent/awesome-claude-code-subagents 26,513
distributed-training
claudeMulti-GPU and multi-node training including DeepSpeed, PyTorch FSDP, Accelerate, Megatron-Core, PyTorch Lightning, and Ray Train. Use when training large models across GPUs.
98 skills
Orchestra-Research/AI-Research-SKILLs 14,502
mistral-pack
claudeOperator-grade Mistral skill pack with 24 current API, security, reliability, governance, and migration workflows
24 skills
jeremylongshore/tons-of-skills-marketplace 2,917
coreai-skills
claudecodexSkills for authoring, exporting, compiling, and running PyTorch models on Apple silicon via Core AI.
3 skills
apple/coreai-models 2,312
Maintain ml-pro?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.
claude & codex plugins21 plugins