70 个 · 按相关度排序
Build AI applications using the Azure AI Projects Python SDK (azure-ai-projects). Use when working with Foundry project clients, creating versioned agents with PromptAgentDefinition, running evaluations, managing connections/deployments/datasets/indexes, or using OpenAI-compatible clients. This is the high-level Foundry SDK - for low-level agent operations, use azure-ai-agents-python skill.
中文简介正在准备中。当前显示原文说明。
Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter. Triggers: "PersistentAgentsClient", "persistent agents", "agent threads", "agent runs", "streaming agents", "function calling agents .NET".
中文简介正在准备中。当前显示原文说明。
A low-level plotting library for comprehensive customization. Use when fine-grained control over every plot element is needed, creating new types of charts, or integrating into specific scientific workflows. Can export to PNG/PDF/SVG for publication. For quick statistical charts, use seaborn; for interactive charts, use plotly; for journal-style, publication-ready multi-panel charts, use scientific-visualization.
中文简介正在准备中。当前显示原文说明。
Translate NI-DAQmx C function signatures into correct calldaqlib MATLAB calls. Use when the user mentions calldaqlib, any DAQmx* C function name (DAQmxCfgSampClkTiming, DAQmxExportSignal, DAQmxSetStartTrigRetriggerable, DAQmxGetSampClkRate, etc.), or needs NI-DAQmx functionality not exposed by the daq object. Covers: projection rules (taskHandle implicit, output pointers become return values, buffer-size args, enum-as-string), multi-task semantics, start() clobber, device-level empty-daq workaround, dictionary returns, string getter placeholder, array getter placeholder. Trigger contexts: low-level DAQ, escape hatch, retriggerable acquisition, shared timebase, export signal, connect terminals, external sample clock, trigger configuration, NI driver, C function translation.
中文简介正在准备中。当前显示原文说明。
Physics-based animation library combining React Spring (spring dynamics, gesture integration, 60fps animations) and Popmotion (low-level composable animation utilities, reactive streams). Use when building fluid, natural-feeling UI animations, gesture-driven interfaces, physics simulations, or spring-loaded interactions. Triggers on tasks involving React Spring hooks, spring physics, inertia scrolling, physics-based motion, animation composition, or natural UI movements. Alternative physics approach to motion-framer for more physically accurate animations.
中文简介正在准备中。当前显示原文说明。
Implements low-level utilities for single-cell trajectory analysis, primarily intended for re-use inside higher-level packages. Include a function to create a cluster-level minimum spanning tree and data structures to hold pseudotime infere
中文简介正在准备中。当前显示原文说明。
MetaboCoreUtils defines metabolomics-related core functionality provided as low-level functions to allow a data structure-independent usage across various R packages. This includes functions to calculate between ion (adduct) and compound ma
中文简介正在准备中。当前显示原文说明。
MsCoreUtils defines low-level functions for mass spectrometry data and is independent of any high-level data structures. These functions include mass spectra processing functions (noise estimation, smoothing, binning, baseline estimation),
中文简介正在准备中。当前显示原文说明。
Produce a flow-level summary of the current Claude Code session — executive summary, chronological timeline, and outcomes — written into the active feature directory next to spec.md / plan.md.
中文简介正在准备中。当前显示原文说明。
Decision protocol for building, debugging, and operating LangGraph-based agent systems. Activates when a coder agent is asked to design a stateful LLM workflow, add human-in-the-loop, choose a multi-agent pattern (supervisor / swarm / hierarchical), pick a checkpoint backend, or migrate a fragile chain into a durable graph. LangGraph is positioned by its maintainers as a "low-level orchestration framework for building, managing, and deploying long-running, stateful agents" — this skill encodes the *when* and *why*, not the API.
中文简介正在准备中。当前显示原文说明。
Statistical visualization on matplotlib + pandas. Distributions (histplot, kdeplot, violin, box), relational (scatter, line), categorical, regression, correlation heatmaps. Auto aggregation/CIs. Use plotly for interactive; matplotlib for low-level.
中文简介正在准备中。当前显示原文说明。
Low-level Python plotting for scientific figures: publication-quality line, scatter, bar, heatmap, contour, 3D; multi-panel layouts; fine control of every element. PNG/PDF/SVG export. Use seaborn for quick stats, plotly for interactive.
中文简介正在准备中。当前显示原文说明。
CesiumJS primitives and geometry - Primitive, GeometryInstance, Appearance, BufferPrimitive collections, GeoJsonPrimitive, Billboard/Label/PointPrimitive collections, built-in geometry shapes, ground primitives, classification. Use when rendering performance-critical static or vector geometry, loading GeoJSON without entities, creating custom shapes, batching draw calls, or using low-level collections.
中文简介正在准备中。当前显示原文说明。
Expert in Ethereum Virtual Machine internals - gas optimization, assembly/Yul, opcode-level optimization, and low-level EVM patternsUse when "evm, gas optimization, yul, inline assembly, opcodes, solidity optimization, evm bytecode, storage layout, evm, ethereum, solidity, yul, assembly, gas-optimization, opcodes, smart-contracts" mentioned.
中文简介正在准备中。当前显示原文说明。
Use when writing or running Unreal Engine tests - which test type fits (simple/complex automation tests, Automation Specs, functional tests, CQTest, Low-Level Tests, Gauntlet), naming and filters, latent tests, and the headless UnrealEditor-Cmd run with report export, exit handling and screenshot captures.
中文简介正在准备中。当前显示原文说明。
The low-level on-chain probes for identifying what an owner address is — cast code → EOA / EIP-7702-delegated EOA / contract, VERSION() → Gnosis Safe, read-only get-owner-ica.ts derive → ICA derivation, getAccountInfo → Sealevel account existence — with how to interpret each result. The primitive layer beneath validate-owners / resolve-artifacts / update-owners, which each apply their own per-chain or per-artifact policy on top.
中文简介正在准备中。当前显示原文说明。
Systems programming from memory management through networking. Covers memory models (stack vs heap, manual allocation, garbage collection, ownership/borrowing), concurrency (threads, mutexes, channels, async/await, actor model, data races vs race conditions), operating system concepts (processes, virtual memory, page tables, system calls, file descriptors, signals), compilation (lexing, parsing, code generation, linking, static vs dynamic libraries), networking fundamentals (TCP/IP, sockets, HTTP, DNS, TLS), and the hardware-software boundary (caches, cache lines, false sharing, memory-mapped I/O). Use when working with low-level code, diagnosing system-level bugs, understanding performance characteristics, or bridging between high-level languages and machine behavior.
中文简介正在准备中。当前显示原文说明。
Systematic code maturity assessment using Trail of Bits' 9-category framework. Analyzes codebase for arithmetic safety, auditing practices, access controls, complexity, decentralization, documentation, MEV risks, low-level code, and testing. Produces professional scorecard with evidence-based ratings and actionable recommendations. (project, gitignored)
中文简介正在准备中。当前显示原文说明。
Expert C++ developer specializing in modern C++20/23, systems programming, and high-performance computing. Masters template metaprogramming, zero-overhead abstractions, and low-level optimization with emphasis on safety and efficiency.
中文简介正在准备中。当前显示原文说明。
Generalised autonomous optimisation loop — soft RLVR for any artifact a user can measure. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and learning from each attempt. Triggers include: "optimise this", "keep improving until it's good", "run experiments on", "autoresearch", "iterate on this overnight", "try different approaches and pick the best", or any request implying repeated evaluate-and-improve cycles. Also use when the user wants to improve a system prompt, a data pipeline, a writing style, or any artifact where quality can be decomposed into measurable tracks. For inference optimisation tasks (model latency, throughput, quantization, GPU deployment), a* delegates the low-level tuning to AITune while maintaining quality tracking and learning.
中文简介正在准备中。当前显示原文说明。
Produce a flow-level summary of the current Claude Code session — executive summary, chronological timeline, and outcomes — written into the active feature directory next to spec.md / plan.md.
中文简介正在准备中。当前显示原文说明。
Azure AI Agents Persistent SDK for Java. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools.
中文简介正在准备中。当前显示原文说明。
Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools.
中文简介正在准备中。当前显示原文说明。
Produce a flow-level summary of the current Claude Code session — executive summary, chronological timeline, and outcomes — written into the active feature directory next to spec.md / plan.md.
中文简介正在准备中。当前显示原文说明。