Claude Code Machine Learning skills :)
Flowy lists 238 skills in the Machine Learning category for Claude Code, across 22 plugins. A skill is a folder of instructions an agent loads while you work. Every one here shows what is inside before you install, who wrote it, and whether it is Auto-invoked, meaning a FLOW.md router fires it as you prompt.
hf-cli
Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and…
@huggingfaceInstall Skillhf-cloud-aws-context-d…
Discover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use…
@huggingfaceInstall Skillhf-cloud-python-env-se…
Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill…
@huggingfaceInstall Skillfeast-architecture
Internals of the Feast codebase — how each component works, where the key abstractions live, and the data flow through the…
@feast-devInstall Skillfeast-dev
Development guide for contributing to the Feast codebase. Covers environment setup, testing, linting, project structure, and PR…
@feast-devInstall Skillfeast-testing
How to test and debug Feast — running targeted tests, writing unit tests for new components, debugging registry and online store…
@feast-devInstall Skill
accessing-mlflow
Query and browse evaluation results stored in MLflow. Use when the user wants to look up runs by invocation ID, compare metrics…
@nvidiaInstall Skillbenchmark-model-kernel…
Inspect Hugging Face decoder layers on meta tensors and plan or run per-rank BF16, FP8, and NVFP4 GEMM or fused-MoE…
@nvidiaInstall Skillcommon
Shared ModelOpt support files. Use only when another ModelOpt skill directs you here.
@nvidiaInstall Skilldev-stack
Start, monitor, restart, or stop the local OpenRAG dev stack (Docker infra + host backend + host frontend). Use when the user…
@langflow-aiInstall Skillinstall
Plan and execute a minimal OpenRAG installation with requirement drafting, task tracking, configuration guidance, and local…
@langflow-aiInstall Skillsdk
Guide developers through integrating the OpenRAG SDK into applications with code examples, configuration, and best practices
@langflow-aiInstall Skillnemotron-add-model
Onboard a new model family (Nemotron or third-party) into skills/ — paper chunks, recipe summaries, context packs, and model…
@nvidia-nemoInstall Skillnemotron-add-pattern
Add a cross-cutting decision pattern under src/nemotron/steps/patterns/. Use when a recurring ML decision (tokenizer lock, eval…
@nvidia-nemoInstall Skillnemotron-add-step
Add a new step under src/nemotron/steps/<category>/<step_id>/ — manifest (step.toml), runner glue, configs, and per-step…
@nvidia-nemoInstall Skillclaude-vision-skill
Use when the user shares, pastes, or references an image (local path or URL) and you need to describe, analyze, or recognize its…
@asuojunInstall Skillconfigs
How the prime-rl config system works — TOML files, CLI overrides, composition, and special patterns. Use when creating configs,…
@primeintellect-aiInstall Skilldashboard
Find, start, use, and stop the local run dashboard for metrics, configs, traces, logs, and reports. Use when asked for its URL,…
@primeintellect-aiInstall Skilleval
Launch and monitor prime-rl evals — the `uv run eval` entrypoint, its config and CLI shorthands, run directory, resume, logs and…
@primeintellect-aiInstall Skillllm-pipeline-analysis
Inspect LLM torch profiler traces at forward-pass, layer, and kernel level. Use when you need layer timings, anchor-kernel…
@bbufInstall Skillllm-serving-auto-bench…
Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, TokenSpeed, or another serving…
@bbufInstall Skillllm-serving-capacity-p…
Parse SGLang/vLLM startup logs to explain GPU memory use and request capacity. Use for KV cache budget, mem-fraction-static…
@bbufInstall Skillauthor-environment
Create or modify Isaac Lab-Arena environments, scenes, tasks, completion predicates, placement constraints, and environment…
@isaac-simInstall Skillcommit-and-pr
Creates Arena-conformant commits and pull requests. Enforces DCO sign-off (git commit -s), no AI attribution lines (no…
@isaac-simInstall Skilldev-container
Bootstraps and maintains the Docker environment used when contributing to Isaac Lab-Arena. Use when preparing a checkout for…
@isaac-simInstall Skillconfiguration
Install/update Sparkrun 0.4.0, configure host clusters and SSH, check setup, manage plugins/features, and inspect or clean model…
@spark-arenaInstall Skillregistry
Browse Sparkrun 0.4.0 recipe registries and benchmark profiles; inspect, export, validate, or author recipes.
@spark-arenaInstall Skillworkloads
Launch, inspect, log, stop, benchmark, and manage inference workloads with Sparkrun 0.4.0, including gateways and optional daemon…
@spark-arenaInstall Skillcheck-release
Verifies that a TorchJD release was published correctly by checking the docs site, installing from PyPI, and smoke-testing newly…
@simplexlabInstall Skillimplement-method
Implements a new method (scalarizer or aggregator) in TorchJD, starting from the research produced by the research-method skill…
@simplexlabInstall Skillprepare-release
Prepares a torchjd package release by verifying the changelog, README, bumping the version in pyproject.toml, and opening a…
@simplexlabInstall Skillkarpathy-skill
Andrej Karpathy的思维框架与表达方式。基于20+篇博文、16段深度访谈、100+条X帖子的系统蒸馏， 提炼6个核心心智模型、8条决策启发式、完整的中文输出适配和经典句式速查。…
@alchaincyfInstall Skilldspy-advanced-workflow
Build DSPy 3.2.x programs through spec, program, metric and baseline; extend to optimization and export when requested and…
@intertwineInstall Skilldspy-evaluation-harnes…
Build DSPy evaluation harnesses with rich-feedback metrics that are essential for GEPA optimization. Use when writing a metric…
@intertwineInstall Skilldspy-fundamentals
Write idiomatic DSPy 3.2.x programs — typed Signatures, dspy.Module subclasses, Predict/ChainOfThought/ReAct/ProgramOfThought,…
@intertwineInstall Skillapplication-flow
High-level overview of a typical ovrtx application lifecycle. Use when user asks how to structure an ovrtx program, what the main…
@nvidia-omniverseInstall Skillasync-operations
Asynchronous operation patterns including polling, timeouts, and non-blocking workflows. Use when user asks about async…
@nvidia-omniverseInstall Skillattribute-bindings
Replacing persistent ovrtx attribute bindings with reusable ovstage queries for repeated writes or maps. Use when user asks about…
@nvidia-omniverseInstall Skilllaya-integration
Add fast, local, typed decisions to any project with Laya, an open-source non-generative decision model (pip install laya). It…
@wdobryInstall Skilldistil-cli
Use when building or training a model on the distil labs platform end to end: preparing a dataset (config.yaml,…
@distil-labsInstall Skillbuilding-with-typesafe…
Use when code needs a judgment about natural language that rules or regex cannot make (classify, route, triage, moderate, score,…
@aaddrickInstall Skillthorlabs-blender-optic…
Design, reconstruct from photographs or schematics, correct, audit, and present Blender optical systems using provenance-bound…
@k-teluxInstall Skillboltzgen
BoltzGen is an all-atom diffusion model that generates antibody, nanobody, and de novo miniprotein backbones conditioned on a…
@001tmfInstall Skillby-campaign-manager
Plan, execute, monitor, and assess protein/antibody design campaigns. This skill governs how to size a campaign, track run state,…
@001tmfInstall Skillby-campaign-optimizer
Multi-round design campaigns generate scored designs at every iteration. This skill turns that scoring history into actionable…
@001tmfInstall Skillhf-cloud-sagemaker-dep…
Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host,…
@huggingfaceInstall Skillhf-cloud-sagemaker-iam…
Ensure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker…
@huggingfaceInstall Skillhf-cloud-sagemaker-pro…
Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging…
@huggingfaceInstall Skillfeast-user-guide
Guide for working with Feast (Feature Store) — defining features, configuring feature_store.yaml, retrieving features…
@feast-devInstall Skillcompare-results
Establish baseline-vs-candidate evaluation plans, delegate missing evaluations, compare validated results, and decide…
@nvidiaInstall Skillday0-release
Deterministic end-to-end driver for day-0 quantized-checkpoint releases — chains PTQ → evaluation → comparison with enforced…
@nvidiaInstall Skilldebug
Run commands inside a remote Docker container via the file-based command relay (tools/debugger). Use when the user says "run in…
@nvidiaInstall Skillnemotron-customize
Configure and chain repo-native Nemotron steps for curation, tokenizer extension, SDG/BYOB, training, conversion, optimization,…
@nvidia-nemoInstall Skillnemotron-lightning35
Reference desk for NVIDIA Nemotron 3.5 Lightning (30B-A3B), a hybrid Mamba-Transformer MoE with MTP built from Nano 3 Base by…
@nvidia-nemoInstall Skillnemotron-nano3
Reference desk for Nemotron 3 Nano / Llama-Nemotron Nano 3 — architecture, training data, recipes, evaluation, quantization,…
@nvidia-nemoInstall Skillinstall
How to install prime-rl and its optional dependencies. Use when setting up the project, installing extras like DeepEP for…
@primeintellect-aiInstall Skillkernels
How prime-rl vendors, builds, and ships CUDA kernels (the `deps/prime-kernels` submodule and the `prime-kernels` wheel). Use when…
@primeintellect-aiInstall Skillmodel-factory
Launch and monitor prime-rl runs on Model Factory with prime train, and retrieve their traces. Use for requests such as "run this…
@primeintellect-aiInstall Skillllm-torch-profiler-ana…
Analyze existing Torch Profiler Chrome traces or capture from SGLang, vLLM, TensorRT-LLM and TokenSpeed servers. Return kernel…
@bbufInstall Skillmodel-architecture-dia…
Return public original model architecture diagrams for user-specified LLM, VLM, MoE, diffusion, OCR, and SGLang/sgl-cookbook…
@bbufInstall Skillmodel-compute-simulati…
Build an operator-level compute template for an LLM and estimate FLOPs/MFU for a serving shape. Use when you need tensor shapes,…
@bbufInstall Skilldownload-osmo-evaluati…
Downloads Isaac Lab-Arena OSMO workflow output (evaluation results, videos, HDF5 demos) to a local folder with `osmo data…
@isaac-simInstall Skilldraft-pr-review
Turns review findings from a local or agent-assisted code review into a pending GitHub pull request review that the reviewer…
@isaac-simInstall Skillrun-experiment
Runs existing Isaac Lab-Arena Experiment Definitions locally with experiment_runner.py in a ready native or Docker runtime,…
@isaac-simInstall Skillresearch-method
Researches about a new method (scalarizer or aggregator) from the scientific literature and how to integrate it to TorchJD. Use…
@simplexlabInstall Skilldspy-gepa-optimizer
Optimize DSPy programs with dspy.GEPA — a reflective/evolutionary optimizer to consider against task-specific baselines within an…
@intertwineInstall Skilldspy-rlm-module
Use dspy.RLM (Recursive Language Model) for reasoning over contexts too large to fit in an LLM's working window — entire…
@intertwineInstall Skillbinding-materials
Binding materials to prims at runtime. Use when user asks to assign a material, change a material, set material binding, or swap…
@nvidia-omniverseInstall Skillcamera-outputs-rt2
Available camera render outputs for Real-Time Path-Tracing (RT2) mode. Use when user asks what AOVs/render vars are available,…
@nvidia-omniverseInstall Skillcloning-prims
Cloning USD subtrees to create copies at new paths. Use when user asks to clone, duplicate, copy a prim, or create instances of…
@nvidia-omniverseInstall Skillby-causal-reasoning
Most "AI scientist" demos fake reasoning by chaining LLM calls and calling the chain a hypothesis. This skill does the opposite:…
@001tmfInstall Skillby-database
Use the BY MCP database tools to query PDB, UniProt, and SAbDab for target characterization, antibody scaffold selection, and…
@001tmfInstall Skillby-deploy-compute
BY is a **local-first** agent. The default compute provider is `"local"` (see `.by/config.json` → `compute.default_provider`).…
@001tmfInstall Skillhf-cloud-serving-image…
Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about…
@huggingfaceInstall Skillhf-mcp
Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run…
@huggingfaceInstall Skillhf-mem
Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub
@huggingfaceInstall Skill142 more in Machine Learning. See them all →