AGENT SKILLS · 任务装备
值得安装的 Agent Skills
汇总公开仓库中已验证的 Skills。安装前先看清它能做什么、包内包含什么、热度如何，以及来源是否可靠。
- 目录范围
- 已验证
- Skills
- 21,476
- 仓库
- 3293
- 最近同步
- 2026年10月22日
orchestra-researchlong-context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchmiles-rl-training
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchmodel-pruning
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchmoe-training
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchnemo-curator
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchnemo-evaluator-sdk
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchnemo-guardrails
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchoutlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchpinecone
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchpresenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchpytorch-fsdp2
Adds PyTorch FSDP2 (fullyshard) 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.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchqdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchquantizing-models-bitsandbytes
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchsegment-anything-model
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchsentence-transformers
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchsentencepiece
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchsglang
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchsimpo-training
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchskypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchslime-rl-training
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.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchstable-diffusion-image-generation
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchsystems-paper-writing
Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchtorchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日
orchestra-researchunsloth
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
- 安装量
- 2
- GitHub Stars
- 1.3万
- 最近更新
- 6月16日