Category · 87 guides
ai-ml skills
Install ai-ml skills for Claude Code. Browse source-linked guides, scan signals, and installation commands.
ai-mlAI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.fal-audioText-to-speech and speech-to-text using fal.ai audio modelsshapModel interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importancai-mlAI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.pytdcTherapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological predictionpathmlFull-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph constructifal-workflowGenerate workflow JSON files for chaining AI modelsgtarsHigh-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenizatgenimlThis skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAopenai-whisperYour own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞fal-generateGenerate images and videos using fal.ai AI modelsdeepchemMolecular machine learning toolkit. Property prediction (ADMET, toxicity), GNNs (GCN, MPNN), MoleculeNet benchmarks, pretrained models, featurization, for drug discovery ML.molfeatMolecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.umap-learnUMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.agentdb-learningCreate and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when buildingmodalRun Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or torchdrugGraph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, GNNs (GIN, GAT, SchNetmlops-engineerBuild comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. Implements automated training, deployment, and monitoringreasoningbank-agentdbImplement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.data-scientistExpert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence. Use PROACTIreasoningbank-intelligenceImplement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workfltransformersThis skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, clfal-image-editAI-powered image editing with style transfer and object removalnano-banana-proGenerate or edit images via Gemini 3 Pro Image (Nano Banana Pro).julia-proMaster Julia 1.10+ with modern features, performance optimization, multiple dispatch, and production-ready practices.lambda-labs-gpu-cloudReserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performapeftParameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of paramflow-nexus-neuralTrain and deploy neural networks in distributed E2B sandboxes with Flow NexuscirqGoogle quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google scikit-survivalComprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-segment-anything-modelFoundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generaaccelerateSimplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precisioai-mlAI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.autoresearchOrchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loazure-aiUse for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, querygenimlThis skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAgtarsHigh-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenizatml-paper-writingWrite publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparinaudiocraftPyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effeccaveman-statsShow real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injechqqHalf-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflomegatron-coreTrains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiemolfeatMolecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.nnsightProvides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experimentsopenrlhfHigh-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChapyveneProvides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, saelensProvides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering inteai-analyzerAI驱动的综合健康分析系统,整合多维度健康数据、识别异常模式、预测健康风险、提供个性化建议。支持智能问答和AI健康报告生成。bitsandbytesQuantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. SupporcirqGoogle quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google deepchemMolecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization optionflash-attentionOptimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountmambaState-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_statenemo-evaluatorEvaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Sstable-diffusionState-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translatiotransformer-lensProvides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when refal-audioText-to-speech and speech-to-text using fal.ai audio modelshistolabA set of ready to use scientific skills for Claudeaidlc-bugfixRun the AI-DLC workflow with the bugfix scope baked in — no scope detection. Fix a specific bug. Packaging over `/aidlc --scope bugfix`, which works without this skill.aidlc-expressRun the AI-DLC workflow with the express scope baked in — no scope detection. Lightest run: requirements to deploy, no design pass, no reviewers. Packaging over `/aidlc --scope expaidlc-featureRun the AI-DLC workflow with the feature scope baked in — no scope detection. Full lifecycle for new features, practical depth. Packaging over `/aidlc --scope feature`, which worksaidlc-mvpRun the AI-DLC workflow with the mvp scope baked in — no scope detection. Skip operations, ship the core. Packaging over `/aidlc --scope mvp`, which works without this skill.aidlc-security-patchRun the AI-DLC workflow with the security-patch scope baked in — no scope detection. CVE response. Packaging over `/aidlc --scope security-patch`, which works without this skill.experiment-tracking-swanlabProvides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.llm-prompt-optimizerUse when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce hallucinations, and cut token usage.syllabusGenerates a curated supplementary reading list from any course syllabus using Consensus academic search. Grill-me intake (syllabus input format + course audience + year range) plustorchdrugPyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Bestvector-index-tuningOptimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.cirqGoogle quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google deepchemMolecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization optiongenimlUse Geniml for audited local genomic-interval workflows: validate BED and universe contracts, plan Region2Vec or scEmbed runs, inspect model/tokenizer compatibility, and assess conml-paper-writingWrite publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparinmolfeatFeaturizes small molecules with Molfeat for QSAR/QSPR, chemical similarity, virtual screening, and molecular ML. Covers ECFP/MACCS fingerprints, RDKit descriptors, pharmacophores, onnx-converterConvert onnx converter operations. Auto-activating skill for ML Deployment. Triggers on: onnx converter, onnx converter Part of the ML Deployment skill category. Use when working wshow-me-your-workKeep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewerfal-aiGenerate images, videos, and audio via fal.ai API (FLUX, SDXL, Whisper, etc.)ml-auditorAudit ML methodology: leakage, splits, baselines, evaluation validity.book-sft-pipelineThis skill should be used when the user asks to "fine-tune on books", "create SFT dataset", "train style model", "extract ePub text", or mentions style transfer, LoRA training, boocaption-stylesSeventeen animated caption looks for talking heads, podcasts, ads, lyric and short-form videos (karaoke fill, active-word pop and colour, sliding pill, word tiles, frosted glass, nconfidence-scoringSee the main Model Explainability skill for comprehensive coverage of confidence scoring and calibration.cross-validation-setupCross Validation Setup - Auto-activating skill for ML Training. Triggers on: cross validation setup, cross validation setup Part of the ML Training skill category.deepchemBuilds molecular property prediction and MoleculeNet workflows with DeepChem, including SMILES featurization, scaffold or grouped holdouts, masked labels, graph models and explicitdetecting-anomalies-in-industrial-control-systemsThis skill covers deploying anomaly detection systems for industrial control environments using machine learning models trained on OT network baselines, physics-based process modeldetecting-business-email-compromise-with-aiDeploy AI and NLP-powered detection systems to identify business email compromise attacks by analyzing writing style, behavioral patterns, and contextual anomalies that evade tradifootage-effectsEight effects for footage you already have, each as tested ffmpeg filter chains plus HyperFrames and Remotion equivalents: glow and bloom (soft, film halation, sci-fi, sunset, anamgenimlSupports audited local Geniml genomic-interval workflows: validate BED and universe contracts, plan Region2Vec or scEmbed runs, inspect model/tokenizer compatibility, and assess co