一个技能，一个新的可能。找到适合你的 AI 工作流。
primekg
【数据与研究】Queries a pinned Precision Medicine Knowledge Graph (PrimeKG) CSV for typed gene, drug, disease, and phenotype nodes, direct associations, disease context, and one- or two-hop paths. Use for PrimeKG reproducibility, biological association lookup, and hypothesis generation with relation and data provenance preserved.
ai-agent-evaluation-benchmarking
【效率与协作】Autonomous AI agent benchmark evaluation register: task completion rates, planning accuracy, tool invocation precision, and cost benchmarks.
qdrant-search-quality
【数据与研究】Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing expected results', or asks 'how to improve search quality?', 'which embedding model?', 'should I use hybrid search?', 'should I use reranking?'. Also use when search quality …
steno-mode
【效率与协作】Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says "steno mode", "shorthand mode", "compressed responses", "token reduction", "brief structured output", or invokes /steno. Supports four compression levels: lite, brief, court, machine. Do not trigger fo…
rag-architect
【设计与创意】Use when the user asks to design a RAG pipeline, choose a chunking strategy or embedding model, pick a vector database, or evaluate retrieval quality (precision@k, recall@k, NDCG). Examples: 'design a RAG system for our docs', 'what chunk size should I use for this corpus', 'evaluate my retriever against ground truth'. NOT for general LLM cost tuning…
hqq-quantization
【部署与运维】Half-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.
huggingface-accelerate
【效率与协作】Simplest 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.
ml-training-recipes
【开发与工程】Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes…
pytorch-fsdp2
【效率与协作】Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.
benchmarking-clinical-ner
【数据与研究】Score an OpenMed clinical or biomedical NER model against a user-supplied gold corpus with entity-level precision, recall, and F1, then break errors down per label. Use when the user wants a seqeval-style scorecard, strict vs partial (relaxed) span matching, a per-label confusion matrix, false-negative / false-positive examples, or to debug why a mod…
segmenting-clinical-sections
【文档与办公】Split a clinical note into canonical sections (Chief Complaint, HPI, PMH, Medications, Allergies, Assessment & Plan, etc.) before running OpenMed NER or de-identification, so section context sharpens downstream precision. Use when the user has a free-text note or discharge summary and wants section-aware processing, header detection, mapping headers …
cublas-cudnn
【效率与协作】Expert integration with NVIDIA GPU-accelerated math libraries. Configure cuBLAS tensor core operations, generate cuBLAS GEMM calls, integrate cuDNN layers, handle algorithm selection, and support mixed-precision operations.
tensorrt-optimization
【部署与运维】NVIDIA TensorRT model optimization and deployment. Convert models to TensorRT engines, configure optimization profiles and precision modes, apply INT8 calibration, analyze kernel fusion, generate custom plugins, and profile inference performance.
css-precision-editor
【效率与协作】Precision CSS/styling modifications for pixel-perfect adjustments with Tailwind, CSS Modules, and plain CSS support
tooluniverse-cancer-variant-interpretation
【效率与协作】Clinical interpretation of somatic cancer mutations for precision oncology. Transforms a gene + variant + cancer-type input into an actionable report: clinical evidence tier (CIViC, OncoKB), therapeutic options (FDA-approved + investigational), resistance mechanisms, prognosis, and matching clinical trials. Use for tumor-board variant calls, somatic-…
tooluniverse-clinical-trial-matching
【效率与协作】AI-driven patient-to-trial matching for precision oncology and rare-disease care. Transforms a patient's molecular profile (mutations, biomarkers, expression) and clinical state into ranked clinical-trial recommendations with evidence tiers. Searches ClinicalTrials.gov, the EU CTIS register (European/EEA trials), AND the ISRCTN registry (UK/internati…
tooluniverse-precision-medicine-stratification
【数据与研究】Patient stratification for precision medicine — integrate genomic, clinical, and therapeutic data to split patients into responder/non-responder groups, risk tiers, or treatment-decision groups. Use for stratification-by-biomarker, treatment-selection logic, and personalized therapeutic strategy reports per patient subgroup.
tooluniverse-cancer-variant-interpretation
【效率与协作】Clinical interpretation of somatic cancer mutations for precision oncology. Transforms a gene + variant + cancer-type input into an actionable report: clinical evidence tier (CIViC, OncoKB), therapeutic options (FDA-approved + investigational), resistance mechanisms, prognosis, and matching clinical trials. Use for tumor-board variant calls, somatic-…