菜单
SkillsMP 已收集 cuba6112/skillfactory 中的 64 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 40 / 64 个已收集 Skill。
Build RAG (Retrieval-Augmented Generation) agents with Google ADK and Vertex AI RAG Engine. Use when implementing document Q&A, knowledge base search, or citation-backed responses. Covers VertexAiRagRetrieval tool, corpus setup, and citation formatting.
原文语言：英语
Build RAG systems with Ollama local + cloud models. Latest cloud models include DeepSeek-V3.2 (GPT-5 level), Qwen3-Coder-480B (1M context), MiniMax-M2. Use for document Q&A, knowledge bases, and agentic RAG. Covers LangChain, LlamaIndex, ChromaDB, and…
原文语言：英语
Design and operate multi-agent orchestration patterns (ReAct loops, evaluator-optimizer, orchestrator-workers, tool routing) for LLM systems. Use when building or debugging agent workflows, tool-use loops, or multi-step task delegation; triggers: agentic,…
原文语言：英语
Multi-service orchestration with Docker Compose, focusing on network isolation, environment-specific profiles, and service discovery. Triggers: docker-compose, container-networking, docker-profiles, service-discovery, yaml-config.
原文语言：英语
Evaluation framework patterns for RAG and LLMs, including faithfulness metrics, synthetic dataset generation, and LLM-as-a-judge patterns. Triggers: ragas, deepeval, llm-eval, faithfulness, hallucination-check, synthetic-data.
原文语言：英语
Advanced FastAPI patterns including hierarchical dependency injection, background task management, and type-safe dependency annotation. Triggers: fastapi, dependency-injection, background-tasks, annotated-dependency, permission-chain.
原文语言：英语
Safe filesystem operations for agents, including path normalization vs resolution, temp file handling, atomic replacement, and spooled buffers. Use when reading/writing user-supplied paths, staging outputs, or managing temporary files; triggers: filesystem,…
原文语言：英语
Adherence to Conventional Commits and efficient Git history management using types, scopes, and advanced commit tools like fixup/amend. Triggers: git-commit, conventional-commits, breaking-change, fixup, git-amend, rebase.
原文语言：英语
Automation of GitHub tasks using the gh CLI and REST API. Includes pagination strategies, payload construction, and rate limit management. Triggers: github, gh-cli, github-api, rate-limit, pagination, pull-request.
原文语言：英语
Integration patterns for web search grounding, including query operator usage, API-based search orchestration, and citation metadata mapping. Triggers: google-search, grounding, search-api, citations, search-operators, web-search.
原文语言：英语
Building LLM agents with LangChain and LangGraph, covering tool-calling model initialization, state management, and observability with LangSmith. Triggers: langchain, langgraph, langsmith, agent-executor, chat-model-tools.
原文语言：英语
LlamaIndex Wolfram Alpha tool for computational knowledge queries, math solving, scientific calculations, and agent integration. Triggers: wolfram alpha, computational query, math solver, scientific calculation, WolframAlphaToolSpec.
原文语言：英语
Fundamental NumPy operations including ndarray creation, dtypes, shape manipulation, and basic operations with a focus on memory alignment and data views. Triggers: numpy, ndarray, dtype, reshape, memory alignment, array-creation.
原文语言：英语
Date and time handling with datetime64 and timedelta64, including business day offsets and naive time parsing. Triggers: datetime64, timedelta64, busday, time series, naive time.
原文语言：英语
Discrete Fourier Transform routines for spectral analysis, signal filtering, and frequency-domain operations. Triggers: fft, fourier transform, spectral analysis, rfft, fftshift, ifft.
原文语言：英语
Advanced indexing techniques including slicing, fancy indexing, and boolean masks, along with memory implications of views vs. copies. Triggers: indexing, slicing, fancy indexing, boolean mask, np.where, np.ix_.
原文语言：英语
Protocols for cross-library data exchange including DLPack, buffer interfaces, and __array_ufunc__ for overriding NumPy functions. Triggers: DLPack, interoperability, __array_interface__, __array_ufunc__, buffer protocol.
原文语言：英语
File I/O operations including binary formats (npy/npz), text processing (csv), and memory-mapping for huge datasets. Triggers: io, load, save, npz, genfromtxt, memmap, loadtxt.
原文语言：英语
Linear algebra operations in NumPy, including matrix multiplication, SVD, system solving, and least squares fitting. Triggers: linalg, matrix multiplication, SVD, eigenvalues, matrix decomposition, lstsq, multi_dot.
原文语言：英语
Masked arrays for robust handling of missing or invalid data, ensuring they are excluded from statistical and mathematical computations. Triggers: masked array, numpy.ma, missing data, invalid values, hard mask.
原文语言：英语
Deep dive into memory layout, including strides, C vs Fortran order, and zero-copy view generation via stride tricks. Triggers: strides, C-order, Fortran-order, memory locality, stride_tricks.
原文语言：英语
Modern polynomial API for fitting, root finding, and working with orthogonal series like Chebyshev and Legendre. Triggers: polynomial, polyfit, Chebyshev, Legendre, root finding.
原文语言：英语
Modern random number generation using the Generator API, focusing on statistical properties, parallel streams, and reproducibility. Triggers: random, rng, default_rng, SeedSequence, probability distributions, shuffle.
原文语言：英语
Set-theoretic operations for finding unique elements, membership testing, and array intersections. Triggers: unique, isin, intersect1d, setdiff1d, union1d.
原文语言：英语
Sorting and searching algorithms including O(n) partitioning, binary search, and hierarchical multi-key sorting. Triggers: sort, argsort, partition, searchsorted, lexsort, nan sort order.
原文语言：英语
Standard and NaN-robust statistical functions for data analysis, histograms, and correlation matrices. Triggers: statistics, mean, nanmean, histogram, corrcoef, percentile, std.
原文语言：英语
Vectorized string manipulation using the char module and modern string alternatives, including cleaning and search operations. Triggers: string operations, numpy.char, text cleaning, substring search.
原文语言：英语
Structured and record arrays for C-interoperability, binary blob interpretation, and multi-field tabular data handling. Triggers: structured array, record array, compound dtype, multi-field index.
原文语言：英语
Universal functions (ufuncs) for vectorization, including reductions, in-place operations, and custom Python-function wrapping. Triggers: ufunc, vectorize, reduce, accumulate, frompyfunc, in-place.
原文语言：英语
Advanced Python testing strategies with Pytest, covering fixtures, matrix testing with parametrization, and async test architecture. Triggers: pytest, fixtures, parametrize, pytest-asyncio, matrix-testing, yield-fixture.
原文语言：英语
Asyncio patterns in Python for high-concurrency IO-bound tasks. Includes coroutines, task management, and asynchronous resource handling. Triggers: asyncio, python-async, coroutine, await, async-gather, async-generator, event-loop.
原文语言：英语
Core PyTorch fundamentals including tensor operations, autograd, nn.Module architecture, and training loop orchestration. Covers optimizations like pin_memory and lazy module initialization. (pytorch, tensor, autograd, nn.Module, optimizer, training loop,…
原文语言：英语
PyTorch CUDA environment and performance guidance, with emphasis on CUDA 13 toolkit/driver requirements, PyTorch wheel compatibility, and runtime checks. Use when configuring PyTorch on NVIDIA GPUs, debugging CUDA setup, or migrating to CUDA 13; triggers:…
原文语言：英语
Distributed training strategies including DistributedDataParallel (DDP) and Fully Sharded Data Parallel (FSDP). Covers multi-node setup, checkpointing, and process management using torchrun. (ddp, fsdp, distributeddataparallel, torchrun, nccl, rank,…
原文语言：英语
Library for Graph Neural Networks (GNNs). Covers MessagePassing layers, modular aggregation schemes, and handling large graphs via mini-batching with disjoint graph representation. (pyg, messagepassing, gnn, gcn, gat, edge_index, knn_graph, global_mean_pool)
原文语言：英语
High-level training framework for PyTorch that abstracts boilerplate while maintaining flexibility. Includes the Trainer, LightningModule, and support for multi-GPU scaling and reproducibility. (lightning, pytorch-lightning, lightningmodule, trainer,…
原文语言：英语
Exporting PyTorch models to ONNX format for cross-platform deployment. Includes handling dynamic axes, graph optimization in ONNX Runtime, and INT8 model quantization. (onnx, onnxruntime, torch.onnx.export, dynamic_axes, constant-folding, edge-deployment)
原文语言：英语
Techniques for model size reduction and inference acceleration using INT8 quantization, including Post-Training Quantization (PTQ) and Quantization Aware Training (QAT). (quantization, int8, qat, fbgemm, qnnpack, ptq, dequantize)
原文语言：英语
Techniques for ensuring LLM responses adhere to strict JSON schemas, utilizing Pydantic models, JSON mode, and schema-based refusals. Triggers: structured-output, pydantic, json-schema, json-mode, llm-response-parsing.
原文语言：英语
Define and run tool-calling patterns for LLMs (schema design, call loops, validation, parallel calls). Use when building function/tool calling workflows or debugging tool selection and arguments; triggers: tool-calling, function-calling, tool schema, tool…
原文语言：英语