AGENT SKILLS · ÉQUIPEMENT DE MISSION
Des Agent Skills utiles classés selon leur usage réel
Comparez les Skills vérifiés par fonction, contenu, installations et fiabilité de la source avant de les ajouter.
- PÉRIMÈTRE
- VÉRIFIÉ
- Skills
- 21 476
- dépôts
- 3293
- dernière synchronisation
- 22 oct. 2026
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
orchestra-researchunsloth
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
- installations
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin