2778 个 · 按相关度排序
Serves 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.
中文简介正在准备中。当前显示原文说明。
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
中文简介正在准备中。当前显示原文说明。
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
中文简介正在准备中。当前显示原文说明。
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
中文简介正在准备中。当前显示原文说明。
Optimizes 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.
中文简介正在准备中。当前显示原文说明。
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
中文简介正在准备中。当前显示原文说明。
Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research/analysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models/skills/agents in DeerFlow, manage DeerFlow memory, upload files to DeerFlow threads, or delegate complex research tasks to DeerFlow. Also use when the user mentions deerflow, deer flow, or wants to run a deep research task that DeerFlow can handle.
中文简介正在准备中。当前显示原文说明。
Review or refactor an existing SKILL.md and its bundled resources — a smaller always-loaded core, conditional references, preserved behavior, lean/guided consumer profiles, and an A/B protocol to compare a candidate with the previous version. Use when a skill repeats itself, loads references on every run, triggers too broadly or misses legitimate requests, or needs its efficiency measured across models. Do NOT use for writing a new skill from scratch, refactoring application code, translating a skill verbatim, or performing the target skill's own task.
中文简介正在准备中。当前显示原文说明。
Use when the user wants a backend-only action plan — API endpoints, services, models, migrations, jobs and their tests — 'plano de backend para o endpoint X', 'plan the orders API'. Writes .planning/feat/features/{slug}/plan.md with the PWDEVIA method. Do NOT use for UI work (feat-frontend), full features spanning backend and UI (feat-feature), writing code (feat-exec) or quick 1–3 file fixes (feat-quick).
中文简介正在准备中。当前显示原文说明。
Design clean, scalable, and maintainable REST and GraphQL APIs following industry best practices. Use when designing public or internal APIs, planning endpoint structures, defining request/response contracts, establishing versioning strategies, implementing authentication patterns, designing data models, creating API documentation, ensuring consistent error handling, optimizing for performance, or establishing service contracts between microservices.
中文简介正在准备中。当前显示原文说明。
Design scalable, normalized database schemas with proper relationships, indexes, constraints, and migration strategies for relational and NoSQL databases. Use when designing database schemas, planning table relationships and foreign keys, creating indexes for query optimization, defining constraints and validations, designing data models for scalability, planning database migrations, choosing between SQL and NoSQL, implementing sharding strategies, optimizing query performance, or establishing data integrity rules.
中文简介正在准备中。当前显示原文说明。
Architect scalable backend services using layered architecture, dependency injection, middleware patterns, service classes, and separation of concerns. Use when building API services, implementing business logic layers, creating service classes, setting up middleware chains, implementing dependency injection, designing controller-service-repository patterns, handling cross-cutting concerns, creating domain models, implementing CQRS patterns, or establishing backend architecture standards.
中文简介正在准备中。当前显示原文说明。
Create effective content models for your blocks that are easy for authors to work with. Use this skill anytime you are building new blocks, making changes to existing blocks that modify the initial structure authors work with.
中文简介正在准备中。当前显示原文说明。
Refactor and review SwiftUI view files for consistent structure, dependency injection, and Observation usage. Use when asked to clean up a SwiftUI view’s layout/ordering, handle view models safely (non-optional when possible), or standardize how dependencies and @Observable state are initialized and passed.
中文简介正在准备中。当前显示原文说明。
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate.
中文简介正在准备中。当前显示原文说明。
Think through the consequences of consequences — not just what happens immediately, but what happens next, and next after that, across time. Load when a decision looks obviously good or obviously bad on initial read, when the user is optimising for a short-term outcome that might create a long-term problem, when unintended consequences are a concern, or when deep-thinking diagnoses a second-order frame. Triggers on "what are the downstream effects", "what happens after that", "unintended consequences", "think ahead on this", "long-term vs short-term", or "what comes after that". Based on Howard Marks second-level thinking and Farnam Street mental models. Most powerful for decisions with delayed consequences or systemic effects.
中文简介正在准备中。当前显示原文说明。
Apply Boyd's OODA loop to navigate fast-moving, uncertain, or competitive situations — Observe what is actually happening, Orient through mental models and context, Decide on the clearest path, Act quickly, then loop again. Load when the situation is changing faster than the current plan, when a competitive response is needed, when the user is stuck in analysis paralysis in a dynamic environment, when shipping under uncertainty, or when deep-thinking diagnoses a fast-moving / competitive frame. Triggers on "what should we do right now", "the situation is changing", "how do we respond to this", "competitive response", "we need to move fast", or "we're stuck deciding". Based on John Boyd's OODA loop — Observe, Orient, Decide, Act — adapted for product and business contexts (OODA Canvas 2026).
中文简介正在准备中。当前显示原文说明。
Gracefully retire a skill that is redundant, superseded, or no longer earning its place in the context window. Load when improve-skills finds a skill scoring 0-5/14 AND research confirms the domain is now handled natively by current models, when two skills have overlapping triggers and one subsumes the other, when the user asks to remove a skill, retire a skill, delete a skill, or clean up redundant skills, or when validate-skills flags a skill as a duplicate trigger risk. Handles removal cleanly: updates all callers, removes from AGENTS.md, updates README, and archives rather than deletes so the skill can be recovered if needed.
中文简介正在准备中。当前显示原文说明。
Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research/analysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models/skills/agents in DeerFlow, manage DeerFlow memory, upload files to DeerFlow threads, or delegate complex research tasks to DeerFlow. Also use when the user mentions deerflow, deer flow, or wants to run a deep research task that DeerFlow can handle.
中文简介正在准备中。当前显示原文说明。
Master modern business analysis with AI-powered analytics, real-time dashboards, and data-driven insights. Build comprehensive KPI frameworks, predictive models, and strategic recommendations.
中文简介正在准备中。当前显示原文说明。
This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belief-desire-intention models", "transform RDF to beliefs", "build cognitive agent", or mentions BDI ontology, mental state modeling, rational agency, or neuro-symbolic AI integration.
中文简介正在准备中。当前显示原文说明。
Optimal ViewModel and Wizard creation patterns for Avalonia using Zafiro and ReactiveUI.
中文简介正在准备中。当前显示原文说明。
Azure AI Document Intelligence SDK for .NET. Extract text, tables, and structured data from documents using prebuilt and custom models.
中文简介正在准备中。当前显示原文说明。
Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines.
中文简介正在准备中。当前显示原文说明。