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.
47.307 skill-uri din 2.272 de depozite · actualizat acum 18 ore
47.305 skill-uri
- huggingface-tokenizersOrchestra-Research/AI-Research-SKILLsFast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.ȘtiințăFără avertismente★ 14 K↓ —
- pytorch-fsdp2Orchestra-Research/AI-Research-SKILLsAdds PyTorch FSDP2 (fully_shard) 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.ProductivitateFără avertismente★ 14 K↓ —
- training-llms-megatronOrchestra-Research/AI-Research-SKILLsTrains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.ProductivitateFără avertismente★ 14 K↓ —
- constitutional-aiOrchestra-Research/AI-Research-SKILLsAnthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.AlteleFără avertismente★ 14 K↓ —
- ml-paper-writingOrchestra-Research/AI-Research-SKILLsWrite publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. For systems venues (OSDI, NSDI, ASPLOS, SOSP), use systems-paper-writing instead.ȘtiințăFără avertismente★ 14 K↓ —
- model-pruningOrchestra-Research/AI-Research-SKILLsReduce 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.AlteleFără avertismente★ 14 K↓ —
- eas-app-storesActualizatexpo/skillsBuild and submit iOS and Android apps with EAS to TestFlight, the App Store, or Google Play. Supports Expo and other React Native projects, plus existing native apps. Use for eas.json setup, release pipelines, signing, app versions and build numbers, store submissions, and listing metadata. For Expo websites and API routes, use eas-hosting; for adding React Native screens to a native app, use expo-brownfield.OficialInginerieFără avertismente★ 3,4 K↓ —
- moe-trainingOrchestra-Research/AI-Research-SKILLsTrain 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.PlanificareFără avertismente★ 14 K↓ —
- resubmit-pipelinewanshuiyin/Auto-claude-code-research-in-sleepWorkflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never overwrite prior submissions). Use when user says "resubmit pipeline", "重投流程", "port paper to <new venue>", "resubmit to <venue>", "tighten paper for resubmission", or has a rejected/withdrawn paper to move to a different top venue under tight time budget.ȘtiințăFără avertismente★ 18,2 K↓ —
- kill-argumentwanshuiyin/Auto-claude-code-research-in-sleepTwo-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says "kill argument", "adversarial review", "hostile review", "rebuttal preparation", "reviewer-2 simulation", or before submitting a theory paper that has already passed standard review rounds.ȘtiințăFără avertismente★ 18,2 K↓ —
- azure-eventhub-dotnetmicrosoft/skillsAzure Event Hubs SDK for .NET. Use for high-throughput event streaming: sending events (EventHubProducerClient, EventHubBufferedProducerClient), receiving events (EventProcessorClient with checkpointing), partition management, and real-time data ingestion. Triggers: "Event Hubs", "event streaming", "EventHubProducerClient", "EventProcessorClient", "send events", "receive events", "checkpointing", "partition".OficialDevOpsFără avertismente★ 3,2 K↓ —
- wiki-cliAgriciDaniel/claude-obsidianDetect and use the official Obsidian command-line interface for read-only vault access; use for wiki-cli, Obsidian CLI, Obsidian read, Obsidian search, vault transport, which transport, transport detection, backlinks, tags, or Obsidian command line. Mutations always go through the claude-obsidian transaction core.InginerieFără avertismente★ 15,9 K↓ —
- instructorOrchestra-Research/AI-Research-SKILLsExtract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output libraryAlteleFără avertismente★ 14 K↓ —
- novelty-checkwanshuiyin/Auto-claude-code-research-in-sleepVerify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.ȘtiințăFără avertismente★ 18,2 K↓ —
- prompt-guardOrchestra-Research/AI-Research-SKILLsMeta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.SecuritateFără avertismente★ 14 K↓ —
- fine-tuning-with-trlOrchestra-Research/AI-Research-SKILLsFine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.AlteleFără avertismente★ 14 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★ 14 K↓ —
- optimizing-attention-flashOrchestra-Research/AI-Research-SKILLsOptimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.ProductivitateFără avertismente★ 14 K↓ —
- nemo-curatorOrchestra-Research/AI-Research-SKILLsGPU-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.MediaFără avertismente★ 14 K↓ —
- stable-diffusion-image-generationOrchestra-Research/AI-Research-SKILLsState-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.MediaFără avertismente★ 14 K↓ —
- azure-ai-transcription-pymicrosoft/skillsAzure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization. Triggers: "transcription", "speech to text", "Azure AI Transcription", "TranscriptionClient".OficialDevOpsFără avertismente★ 3,2 K↓ —
- outlinesOrchestra-Research/AI-Research-SKILLsGuarantee 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 libraryInginerieFără avertismente★ 14 K↓ —
- guidanceOrchestra-Research/AI-Research-SKILLsControl LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation frameworkȘtiințăFără avertismente★ 14 K↓ —
- llama-cppOrchestra-Research/AI-Research-SKILLsRuns LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.DevOpsFără avertismente★ 14 K↓ —
fine-tuning-with-trl
Orchestra-Research/AI-Research-SKILLs
AlteleActualizat 11 oct. 2026
De la autor
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
Instalare
npx skills add Orchestra-Research/AI-Research-SKILLs --skill fine-tuning-with-trl -a claude-code
Se instalează în .claude/skills/fine-tuning-with-trl/ · 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 (5)
- SKILL.md
- references/dpo-variants.md
- references/online-rl.md
- references/reward-modeling.md
- references/sft-training.md