Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
36.618 skill-uri din 1.661 de depozite · actualizat acum 4 minute
36.618 skill-uri
- evaluating-cosmos-policyOrchestra-Research/AI-Research-SKILLsEvaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.MediaFără avertismente★ 13,9 K↓ —
- implementing-llms-litgptOrchestra-Research/AI-Research-SKILLsImplements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.PlanificareFără avertismente★ 13,9 K↓ —
- code-mate-github-copilotCherryHQ/cherry-studioRun GitHub Copilot CLI non-interactively for coding tasks. Use when the user asks to delegate work to Copilot.InginerieFără avertismente★ 52,9 K↓ —
- fine-tuning-openvla-oftOrchestra-Research/AI-Research-SKILLsFine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.DevOpsFără avertismente★ 13,9 K↓ —
- mamba-architectureOrchestra-Research/AI-Research-SKILLsState-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.PlanificareFără avertismente★ 13,9 K↓ —
- serving-llms-vllmOrchestra-Research/AI-Research-SKILLsServes 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.DevOpsFără avertismente★ 13,9 K↓ —
- code-mate-qoderCherryHQ/cherry-studioRun the Qoder CLI non-interactively with structured output. Use when the user asks to delegate a coding task to Qoder.InginerieFără avertismente★ 52,9 K↓ —
- rwkv-architectureOrchestra-Research/AI-Research-SKILLsRNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.PlanificareFără avertismente★ 13,9 K↓ —
- weights-and-biasesOrchestra-Research/AI-Research-SKILLsTrack ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platformAlteleFără avertismente★ 13,9 K↓ —Apare și în 1 alt depozit
- paper-writewanshuiyin/Auto-claude-code-research-in-sleepDraft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.ȘtiințăFără avertismente★ 18 K↓ —
- simpo-trainingOrchestra-Research/AI-Research-SKILLsSimple 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.AlteleFără avertismente★ 13,9 K↓ —
- miles-rl-trainingOrchestra-Research/AI-Research-SKILLsProvides 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.PlanificareFără avertismente★ 13,9 K↓ —
- slime-rl-trainingOrchestra-Research/AI-Research-SKILLsProvides 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.AlteleFără avertismente★ 13,9 K↓ —
- phoenix-observabilityOrchestra-Research/AI-Research-SKILLsOpen-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.DevOpsFără avertismente★ 13,9 K↓ —
- axolotlOrchestra-Research/AI-Research-SKILLsExpert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal supportAlteleFără avertismente★ 13,9 K↓ —
- modal-serverless-gpuOrchestra-Research/AI-Research-SKILLsServerless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.DevOpsFără avertismente★ 13,9 K↓ —
- distributed-llm-pretraining-torchtitanOrchestra-Research/AI-Research-SKILLsProvides 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.AlteleFără avertismente★ 13,9 K↓ —
- kqlmicrosoft/skillsKQL language expertise for writing correct, efficient Kusto Query Language queries. Covers syntax gotchas, join patterns, dynamic types, datetime pitfalls, regex patterns, serialization, memory management, result-size discipline, and advanced functions (geo, vector, graph). USE THIS SKILL whenever writing, debugging, or reviewing KQL queries — even simple ones — because the gotchas section prevents the most common errors that waste tool calls and cause expensive retry cascades. Trigger on: KQL, Kusto, ADX, Azure Data Explorer, Fabric Real-Time Intelligence, EventHouse, Log Analytics, log analysis, data exploration, time series, anomaly detection, summarize, where clause, join, extend, project, let statement, parse operator, extract function, any mention of pipe-forward query syntax.OficialDevOpsFără avertismente★ 3,1 K↓ —
- llamaindexOrchestra-Research/AI-Research-SKILLsData framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.PlanificareFără avertismente★ 13,9 K↓ —
- blip-2-vision-languageOrchestra-Research/AI-Research-SKILLsVision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.MediaFără avertismente★ 13,9 K↓ —
- fine-tuning-serving-openpiOrchestra-Research/AI-Research-SKILLsFine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.InginerieFără avertismente★ 13,9 K↓ —
- gptqOrchestra-Research/AI-Research-SKILLsPost-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.DevOpsFără avertismente★ 13,9 K↓ —
- verl-rl-trainingOrchestra-Research/AI-Research-SKILLsProvides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.DevOpsFără avertismente★ 13,9 K↓ —
- langchainOrchestra-Research/AI-Research-SKILLsFramework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.DevOpsFără avertismente★ 13,9 K↓ —
miles-rl-training
Orchestra-Research/AI-Research-SKILLs
PlanificareActualizat 11 oct. 2026
De la autor
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.
Instalare
npx skills add Orchestra-Research/AI-Research-SKILLs --skill miles-rl-training -a claude-code
Se instalează în .claude/skills/miles-rl-training/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Descarcă .zip
Identic octet cu octet cu commit-ul scanat, cu licența depozitului și un fișier SOURCE.txt.
La ce are acces
Doar instrucțiuniFolosește rețeauaLicență: MIT
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 93
Securitate100
Proveniență90
Întreținere100
Licență100
Adopție65
Fișiere (3)
- SKILL.md
- references/api-reference.md
- references/troubleshooting.md