Machine Learning Skills

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.

Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.

Track workouts, stats, progress over time. Identify improvement areas, plateaus, rest/recovery needs, peak performance timing, injury risk.

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

Context is the complete state available to a language model at inference time. It includes everything the model can attend to when generating responses: system instructions, tool definitions, retrieved documents, message history, and tool outputs.

Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems.

Guide to selecting and optimizing embedding models for vector search applications.

Semantic search, similar content discovery, and structured research using Exa API. Use when you need semantic/embeddings-based search, finding similar content, or searching by category (company, people, research papers, etc.).

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging...

Run workloads on Hugging Face Jobs with managed CPUs, GPUs, TPUs, secrets, and Hub persistence.

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

Automated compliance checking against CIS, PCI-DSS, HIPAA, and SOC 2 benchmarks

Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks. Use when working with AutoModel, pipelines, tokenizers, or TrainingArguments—not for general ML outside the Transformers library.

INVOKE THIS SKILL when creating evaluation datasets, uploading datasets to LangSmith, or managing existing datasets. Covers dataset types (final_response, single_step, trajectory, RAG), CLI management commands, SDK-based creation, and example management. Uses the langsmith CLI tool.

亚马逊卖家专用的 skill 创建器（中文）。当用户想把一个亚马逊运营/自媒体/日常工作流程变成可复用的 skill 时使用。触发场景包括但不限于：用户说"我想做一个 skill""把这个流程变成 skill""帮我写个自动化""优化我已有的 skill""给这个工作流做个自动化"，即使用户没用"skill"这个词，只要在描述"以后每次都这样做"的重复性工作时也应触发。本 skill 的核心差异：强制用户先回答 6 个业务问题（业务目标/过去做法/具体步骤/方法论/调用方式/期望输出）再进入创建流程，防止产出空洞 skill。Create new skills, improve existing skills, run evals and benchmarks — tailored for Amazon sellers with a Chinese-first workflow.

Stop and consult this skill whenever your response would include specific facts about Anthropic's products. Covers: Claude Code (how to install, Node.js requirements, platform/OS support, MCP server integration, configuration), Claude API (function calling/tool use, batch processing, SDK usage, rate limits, pricing, models, streaming), and Claude.ai (Pro vs Team vs Enterprise plans, feature limits). Trigger this even for coding tasks that use the Anthropic SDK, content creation mentioning Claude capabilities or pricing, or LLM provider comparisons. Any time you would otherwise rely on memory for Anthropic product details, verify here instead — your training data may be outdated or wrong.

Work with Data Commons, a platform providing programmatic access to public statistical data from global sources. Use this skill when working with demographic data, economic indicators, health statistics, environmental data, or any public datasets available through Data Commons. Applicable for querying population statistics, GDP figures, unemployment rates, disease prevalence, geographic entity resolution, and exploring relationships between statistical entities.

Heart rate variability biometrics and emotional awareness training. Expert in HRV analysis, interoception training, biofeedback, and emotional intelligence. Activate on 'HRV', 'heart rate variability', 'alexithymia', 'biofeedback', 'vagal tone', 'interoception', 'RMSSD', 'autonomic nervous system'. NOT for general fitness tracking without HRV focus, simple heart rate monitoring, or diagnosing medical conditions (only licensed professionals diagnose).

Annotated matrices for single-cell genomics. Stores X with obs/var metadata, layers, embeddings (obsm/varm), graphs (obsp/varp), uns. Use for .h5ad/.zarr I/O, concatenation, scverse integration. For analysis use scanpy; for probabilistic models use scvi-tools.

GRN inference from expression via GRNBoost2 (gradient boosting) or GENIE3 (Random Forest). Load matrix, filter by TFs, infer TF-target-importance links, save network. Dask-parallelized to single-cell scale. Core SCENIC component.

DL cell/nucleus segmentation for fluorescence and brightfield microscopy. Pre-trained models (cyto3, nuclei, tissuenet) and a generalist flow-based algorithm segment cells without retraining. Outputs label masks for morphology and tracking. Use scikit-image watershed for rule-based; Cellpose when DL generalization across staining is needed.

Automated scRNA-seq cell type annotation via pre-trained logistic regression. 45+ models: immune, gut, lung, brain, fetal, cancer microenvironments. Input normalized AnnData; outputs per-cell labels, majority-vote cluster labels, confidence scores. Use for fast, reference-backed annotation without manual marker inspection.

Parse/write FCS (Flow Cytometry) files v2.0-3.1. Events as NumPy, channel metadata, multi-dataset files, CSV/FCS export. Use FlowKit for gating/compensation.

Harmony batch correction for scRNA-seq and other omics. Removes batch effects from PCA embeddings while preserving biology. Run after PCA, before UMAP. Scales to millions of cells. Python (harmonypy, scanpy) and R (Seurat).

WSI processing for digital pathology. Tissue detection, tile extraction (random, grid, score-based), filter pipelines for H&E/IHC. For dataset prep, tile-based DL, slide QC. Use pathml for multiplexed imaging.

Multi-Omics Factor Analysis v2 (MOFA+) with mofapy2. Jointly decompose omics layers (scRNA, ATAC, proteomics, methylation) into latent factors capturing major variation. Multi-group designs. AnnData views → MOFA object → train → variance explained → correlate factors with metadata → visualize/cluster → enrich top loadings.

Multi-modal single-cell analysis with muon/MuData. Joint RNA+ATAC (10x Multiome), CITE-seq (RNA+protein), other multi-omics. MuData holds per-modality AnnData with shared obs. WNN joint embedding, per-modality preprocessing, MOFA factor analysis. Use scanpy-scrna-seq for single-modality RNA; use muon when combining 2+ omics from the same cells.

Per-feature NaN-safe Spearman/Pearson correlation across many features (genes, proteins, variants) with missing values. Covers why bulk matrix shortcuts fail, correct pairwise deletion, degenerate input filtering, and large-dataset performance. Use statistical-analysis for test choice; shap-model-explainability for interpretability.

Medical image segmentation with nnU-Net's self-configuring framework — auto-selects architecture, preprocessing, training for any modality. CT, MRI, microscopy, ultrasound in 2D, 3D full-res, 3D low-res, cascade. Pipeline: convert → plan/preprocess → train (5-fold CV) → best config → predict → ensemble. Use when classical segmentation fails and annotated data exists.

> Therapeutics Data Commons (TDC) AI-ready drug discovery datasets. Curated ADME, toxicity, DTI, DDI with scaffold/cold splits, standardized metrics, molecular oracles, and ADMET benchmarks for therapeutic ML and property prediction. For chemical database queries use chembl-database-bioactivity; for featurization use molfeat.

scRNA-seq with Scanpy: QC, normalization, HVG selection, PCA, neighborhood graph, UMAP/t-SNE, Leiden clustering, markers, cell annotation, trajectory inference. Standard scRNA-seq exploration.

Classical ML in Python: classification, regression, clustering, dim reduction, evaluation, tuning, preprocessing pipelines. Linear models, tree ensembles, SVMs, K-Means, PCA, t-SNE. Use PyTorch/TF for deep learning; XGBoost/LightGBM for scale.

Deep generative models for single-cell omics: probabilistic batch correction (scVI), semi-supervised annotation (scANVI), CITE-seq RNA+protein (totalVI), transfer learning (scARCHES), and DE with uncertainty. Unified setup→train→extract API on AnnData. Use harmony-batch-correction for fast linear correction without deep learning; muon for multi-modal MuData workflows.

Three-tiered sgRNA design guide using validated Addgene sequences, CRISPick pre-computed datasets, or de novo design rules for CRISPR experiments

Python statistical modeling: regression (OLS, WLS, GLM), discrete (Logit, Poisson, NegBin), time series (ARIMA, SARIMAX, VAR), with rigorous inference, diagnostics, and hypothesis tests. Use scikit-learn for ML; statistical-analysis for test choice.

PyTorch Geometric (PyG) for graph neural networks: node/graph classification, link prediction with GCN, GAT, GraphSAGE, GIN. Message passing, mini-batches, heterogeneous graphs, neighbor sampling, explainability. Supports molecules (QM9, MoleculeNet), social/knowledge graphs, 3D point clouds. For non-graph DL use PyTorch; for classical graph algorithms use NetworkX.

HuggingFace Transformers with biomedical LMs (BioBERT, PubMedBERT, BioGPT, BioMedLM) for scientific NLP: NER (genes, diseases, chemicals), relation extraction, QA, text classification, abstract summarization. Covers loading, biomedical tokenization, inference pipelines, fine-tuning. Alternatives: spaCy en_core_sci_lg (rule-based NER), Stanza (biomedical models), NLTK.

Build a Stockbee-style setup model book from momentum-burst screener candidates, then update 3-day and 5-day forward outcomes with MFE/MAE, stop-hit status, outcome tags, and cohort statistics. Use when the user wants to study Stockbee Momentum Burst examples, track failed candidates, build setup fluency, review A/B setup quality, or convert screener outputs into a learning loop rather than immediate trade signals.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Comprehensive toolkit for developing with the CocoIndex library. Use when users need to create data transformation pipelines (flows), write custom functions, or operate flows via CLI or API. Covers building ETL workflows for AI data processing, including embedding documents into vector databases, building knowledge graphs, creating search indexes, or processing data streams with incremental updates.

Build LLM applications with LangChain and LangGraph. Use when creating RAG pipelines, agent workflows, chains, or complex LLM orchestration. Triggers on LangChain, LangGraph, LCEL, RAG, retrieval, agent chain.

Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.

Route AI coding queries to local LLMs in air-gapped networks. Integrates Serena MCP for semantic code understanding. Use when working offline, with local models (Ollama, LM Studio, Jan, OpenWebUI), or in secure/closed environments. Triggers on local LLM, Ollama, LM Studio, Jan, air-gapped, offline AI, Serena, local inference, closed network, model routing, defense network, secure coding.

Cloud-based quantum chemistry platform with Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Use when tasks involve quantum chemistry calculations, molecular property prediction, DFT or semiempirical methods, neural network potentials (AIMNet2), protein-ligand binding predictions, or automated computational chemistry pipelines. Provides cloud compute resources with no local setup required.

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.