效率提升技能

Guides agents using the datamol Python package for RDKit-first molecular IO, preparation, fingerprints, similarity, structure generation, visualization, and utility workflows.

中文简介正在准备中。当前显示原文说明。

Route DataFlow workflows for pipelines, text and document processing, serving, evaluation, and Ray acceleration.

中文简介正在准备中。当前显示原文说明。

Use this repo skill for Dask, the Python parallel computing library, when working with lazy task graphs, schedulers, Dask Array, Dask DataFrame, Dask Bag/bytes IO, configuration, diagnostics, CLI usage, or contributor validation.

中文简介正在准备中。当前显示原文说明。

Routes Darkflow object-detection, training, and export workflows for the legacy YOLO package.

中文简介正在准备中。当前显示原文说明。

Route D-FINE object-detection setup, training, architecture inspection, inference, export, and troubleshooting workflows.

中文简介正在准备中。当前显示原文说明。

Guides CUDA-accelerated cuRobo v2 robotics workflows for robot models, differentiable kinematics, collision-aware IK and motion planning, trajectory optimization, MPC, perception mapping, and motion retargeting.

中文简介正在准备中。当前显示原文说明。

DeepPavlov package routing for config-driven NLP workflows, model-family selection, and serving.

中文简介正在准备中。当前显示原文说明。

Use this DeepCTR repo skill for CTR/recommender feature columns, Keras models, sequence/session models, multitask models, and legacy TensorFlow Estimator workflows.

中文简介正在准备中。当前显示原文说明。

Routes DataChain operating guidance for Python SDK pipelines, query expressions, CLI and Studio commands, agent-harness knowledge workflows, and repository maintenance.

中文简介正在准备中。当前显示原文说明。

Route DeepLabCut markerless pose-estimation workflows, project setup, PyTorch training/inference, maDLC tracking, Model Zoo, post-processing, 3D, and export tasks.

中文简介正在准备中。当前显示原文说明。

Use ColabFold for protein structure prediction workflows: validate FASTA/CSV/A3M inputs, generate MSAs, plan batch predictions, inspect outputs, and troubleshoot optional AlphaFold, MMseqs2, JAX, GPU, and OpenMM dependencies.

中文简介正在准备中。当前显示原文说明。

Use ClawBio for local-first bioinformatics agent workflows: install and run its skill library, route genomic or omics inputs, create reproducible reports, connect optional MCP or Nextflow integrations, and author or validate skills.

中文简介正在准备中。当前显示原文说明。

Routes Chinese-LLaMA-Alpaca-2 training, inference, serving, evaluation, and integration workflows.

中文简介正在准备中。当前显示原文说明。

Use CellTypist for single-cell RNA-seq cell type annotation, model management, custom classifier training, CLI usage, and result visualization workflows.

中文简介正在准备中。当前显示原文说明。

Use Brian2 for clock-driven spiking-neural-network modeling, simulation, synaptic connectivity, input generation, recording, physical-unit equations, spatial neurons, runtime code generation, and C++ standalone workflows.

中文简介正在准备中。当前显示原文说明。

Use CausalML for causal inference, uplift modeling, matching, validation, interpretation, and treatment optimization workflows.

中文简介正在准备中。当前显示原文说明。

Use ColossalAI for distributed PyTorch training, large-model parallelism, Booster plugins, ShardFormer, Colossal-Inference, and first-party application workflow routing.

中文简介正在准备中。当前显示原文说明。

Routes CenterNet object-detection training, evaluation, configuration, and setup workflows.

中文简介正在准备中。当前显示原文说明。

Use BoxMOT for multi-object tracking, benchmark replay, ReID model lifecycle workflows, and native C++ tracker backends.

中文简介正在准备中。当前显示原文说明。

Use bm25s for sparse lexical retrieval: tokenize text, build and query BM25 indexes, persist or memory-map them, run the high-level or bm25 CLI workflows, and diagnose optional acceleration and integrations.

中文简介正在准备中。当前显示原文说明。

Use Biotite for computational molecular biology workflows: sequence analysis, structure analysis, biological database access, file-format conversion, application wrappers, and optional molecular interfaces.

中文简介正在准备中。当前显示原文说明。

Use BERT-pytorch for corpus preparation, vocabulary building, and tiny BERT pretraining workflows.

中文简介正在准备中。当前显示原文说明。

Route BayesianOptimization package tasks for black-box Bayesian optimization, HPO, acquisition functions, constraints, typed domains, domain reduction, and checkout maintenance.

中文简介正在准备中。当前显示原文说明。

Use AutoKeras for Keras-based AutoML task APIs, custom AutoModel graphs, tuner search, and model export workflows.

中文简介正在准备中。当前显示原文说明。