All authors
Claude Skills by huang-sh
github.com/huang-sh313 skills2 installs363 views
- Bio Workflows Scrnaseq PipelineEnd-to-end single-cell RNA-seq workflow from 10X Genomics data to annotated cell types. Covers QC, normalization, clustering, marker detection, and cell type annotation. Use when analyzing single-cell RNA-seq data.Votes: 0GitHub stars: 4
- Bio Workflows Smrna PipelineEnd-to-end small RNA-seq analysis from FASTQ to differential miRNA expression and target prediction. Use when analyzing miRNA, isomiR, tRF, or piRNA sequencing data through preprocessing, quantification, discovery, DE, and targets.Votes: 0GitHub stars: 4
- Bio Workflows Somatic Variant PipelineChains a somatic (tumor-normal) SNV/indel and structural-variant pipeline end to end with GATK Mutect2 (or Strelka2), wiring the somatic-specific machinery - panel-of-normals and gnomAD germline-resource priors, GetPileupSummaries/CalculateContamination, and LearnReadOrientationModel FFPE/oxoG orientation-bias filtering fed into FilterMutectCalls. Use when calling somatic mutations from a tumor-normal pair (or tumor-only with PoN caveats), deciding which artifact filter removes which class of...Votes: 0GitHub stars: 4
- Bio Workflows Spatial PipelineEnd-to-end spatial transcriptomics workflow for Visium/Xenium data. Covers data loading, preprocessing, spatial analysis, domain detection, and visualization with Squidpy. Use when analyzing spatial transcriptomics data.Votes: 0GitHub stars: 4
- Bio Workflows Tcr PipelineOrchestrates an end-to-end immune-repertoire pipeline from FASTQ to clonotypes, diversity, overlap, somatic hypermutation and lineages, routing on two forks. Use when deciding bulk vs single-cell (bulk amplicon/RNA-seq -> MiXCR analyze preset -> VDJtools/immunarch depth-normalized diversity and overlap -> figures; 10x paired VDJ -> MiXCR 10x preset or Cell Ranger -> scirpy gene-expression integration, chain QC, clonotype clusters); and TCR vs BCR (TCR -> exact CDR3-nt+V/J clonotypes, VDJtools...Votes: 0GitHub stars: 4
- Bio Workflows Timecourse PipelineEnd-to-end bulk time-course analysis from an expression matrix to temporal gene modules and per-cluster pathway enrichment. Orchestrates temporal DE (limma splines or DESeq2 LRT), Mfuzz/tslearn soft clustering of expression-profile shapes, GAM trajectory fitting, per-cluster GO enrichment against a temporal-gene background, and an OPTIONAL circadian rhythm-detection branch (MetaCycle/CosinorPy) that runs only when the design covers >=2 full cycles with >=6-8 evenly spaced samples per cycle. U...Votes: 0GitHub stars: 4
- DaskDistributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.Votes: 0GitHub stars: 4
- GeopandasPython library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. Use when working with geographic data for spatial analysis, geometric operations, coordinate transformations, spatial joins, overlay operations, choropleth mapping, or any task involving reading/writing/analyzing vector geographic data. Supports PostGIS databases, interactive maps, and integration with matplotlib/folium/cartopy. Use for tasks like buffer analysis, spatial joins between ...Votes: 0GitHub stars: 4
- Hdf5 Pde Data LoadingPatterns for loading PDE simulation datasets (PDEBench, PhiFlow, JAX-CFD) from HDF5 files. Handles layout detection (single tensor vs separate variables), spatial/temporal downsampling, multi-variable systems, HuggingFace and DaRUS data sources, and efficient PyTorch DataLoader creation. Use when preparing PDE data for neural operator training.Votes: 0GitHub stars: 4
- PolarsFast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.Votes: 0GitHub stars: 4
- Ray DataScalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.Votes: 0GitHub stars: 4
- VaexUse this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.Votes: 0GitHub stars: 4
- Zarr PythonChunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.Votes: 0GitHub stars: 4
- ChromaOpen-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.Votes: 0GitHub stars: 4
- ClipOpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.Votes: 0GitHub stars: 4
- FaissFacebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.Votes: 0GitHub stars: 4
- GuidanceControl LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation frameworkVotes: 0GitHub stars: 4
- Huggingface TokenizersFast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.Votes: 0GitHub stars: 4
- InstructorExtract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output libraryVotes: 0GitHub stars: 4
- LangchainFramework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.Votes: 0GitHub stars: 4
- LlamaindexData framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.Votes: 0GitHub stars: 4
- Llm As Judge EvaluationEvaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.Votes: 0GitHub stars: 4
- OutlinesGuarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation libraryVotes: 0GitHub stars: 4
- QdrantHigh-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.Votes: 0GitHub stars: 4
- SentencepieceLanguage-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.Votes: 0GitHub stars: 4
- Stable 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 translation, inpainting, or building custom diffusion pipelines.Votes: 0GitHub stars: 4
- WhisperOpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.Votes: 0GitHub stars: 4
- GgufGGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.Votes: 0GitHub stars: 4
- Llama CppRuns LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.Votes: 0GitHub stars: 4
- PhoenixOpen-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.Votes: 0GitHub stars: 4
- SglangFast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.Votes: 0GitHub stars: 4
- Tensorrt LlmOptimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.Votes: 0GitHub stars: 4
- VllmServes LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.Votes: 0GitHub stars: 4
- AccelerateSimplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.Votes: 0GitHub stars: 4
- AwqActivation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.Votes: 0GitHub stars: 4
- AxolotlExpert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal supportVotes: 0GitHub stars: 4
- Bigcode Evaluation HarnessEvaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.Votes: 0GitHub stars: 4
- 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. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.Votes: 0GitHub stars: 4
- DeepspeedExpert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attentionVotes: 0GitHub stars: 4
- GenimlThis 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 ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.Votes: 0GitHub stars: 4
- GptqPost-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.Votes: 0GitHub stars: 4
- Grpo Rl TrainingExpert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model trainingVotes: 0GitHub stars: 4
- HqqHalf-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.Votes: 0GitHub stars: 4
- Knowledge DistillationCompress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.Votes: 0GitHub stars: 4
- Llama FactoryExpert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal supportVotes: 0GitHub stars: 4
- Lm Evaluation HarnessEvaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.Votes: 0GitHub stars: 4
- Ml Benchmark EvaluationRigorous methodology for evaluating ML models on established benchmarks. Covers proper train/val/test splits, baseline verification from original papers, exact metric formula discrepancies, data-leak detection checklist, multi-seed robustness, and honest reporting templates. Use when claiming to beat published baselines, writing methods papers, or auditing existing results.Votes: 0GitHub stars: 4
- MlflowTrack ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platformVotes: 0GitHub stars: 4
- Model EconomicsCost modeling and ROI analysis for specialized LLM development. Use when deciding whether to train a custom model, estimating total cost, or calculating break-even vs frontier APIs. Covers training costs, inference costs, and time-to-ROI projections.Votes: 0GitHub stars: 4
- Model MergingMerge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.Votes: 0GitHub stars: 4