Prototipo · Versión preliminar: todos los servidores del registro oficial, sincronizados cada 30 minutos. Inicia sesión con Google para escribir reseñas.Prototipo · se actualiza cada 30 min
PopNx MCPServidores MCP para quienes usan IA · en palabras sencillas Iniciar sesión

AI-Research-SKILLs Skill

Repositorio ↗

de Orchestra-Research★ 14.665 (todo el repo)98 skills

★ Las estrellas son de todo el repo, no de cada Skill

Elige la Skill que quieres instalar

Qué hace

Este repo es una colección de 98 Skills

  • Conexión Archivos de instrucciones que lee la IA
  • Cuenta o clave No se encontró ninguna clave en el README ni en SKILL.md
  • Categoría Programación
Descripción original del autor
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.
Para autores: añade una insignia a tu README

Si lo creaste tú, pega este código en tu README. La insignia enlaza a esta página.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/orchestra-research-ai-research-skills.svg)](https://mcp.popnx.com/en/skills/orchestra-research-ai-research-skills)

Úsalo junto con

Servidores MCP que conectan la IA a servicios para el mismo trabajo

REA

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

de morlutoMuy usado↓ 388,7 mil/sem★ 468,8 milActualizado hace 8 días

MCP · Conecta un servicioSe ejecuta en tu computadora

Fallow

Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.

de fallow-rsMuy usado↓ 2,4 M/sem★ 5,4 milActualizado ayer

MCP · Conecta un servicioSe ejecuta en tu computadora

Desktop Commander

MCP server for terminal commands, file operations, and process management

de wonderwhy-erMuy usado↓ 740,3 mil/sem★ 10,4 milActualizado anteayer

MCP · Conecta un servicioSe ejecuta en tu computadora

Skills parecidas

Mismo tipo de trabajo, ordenadas como la lista de Skills

Comparado con otros parecidos
Este
AI-Research-SKILLs
reaandrej-karpathy-skillsgraphifyMoneyPrinterTurbo
AutorOrchestra-Researchmorlutomultica-aiGraphify-Labsharry0703
Skills981111
Estrellas de GitHub14.665468.733234.332150.287144.566
Último cambio de código11 oct 202619 nov 202620 abr 202618 nov 202618 nov 2026
LicenciaMITMIT–Apache-2.0MIT

98 skills (conjuntos de instrucciones) de Orchestra-Research que la IA lee y sigue · no es un MCP server

Elige la Skill que quieres instalar

Instala solo las que uses. Abre una Skill para ver cómo instalarla

Este conjunto tiene 98 Skills, demasiadas para instalarlas todas: la descripción de cada Skill instalada se carga en todos los chats y la IA se equivoca más fácilmente de Skill. Elige de la lista de abajo solo las que uses

Mostrando 30 de 98 Ver todas en GitHub

  • 0-autoresearch-skill

    Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execut…

  • axolotl

    Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

  • constitutional-ai

    Anthropic'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.

  • grpo-rl-training

    Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

  • huggingface-tokenizers

    Fast 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-per…

  • litgpt

    Implements 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…

  • llama-factory

    Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

  • llamaguard

    Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

  • mamba

    State-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.

  • miles

    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.

  • nanogpt

    Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

  • nemo-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, cl…

  • nemo-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.

  • nnsight

    Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

  • openrlhf

    High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

  • peft

    Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transfor…

  • prompt-guard

    Meta'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.

  • pyvene

    Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

  • ray-data

    Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pip…

  • rwkv

    RNN+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.

  • saelens

    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.

  • sentencepiece

    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 l…

  • simpo

    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.

  • slime

    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.

  • torchforge

    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.

  • torchtitan

    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.

  • transformer-lens

    Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

  • trl-fine-tuning

    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.

  • unsloth

    Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

  • verl

    Provides 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.

En qué se diferencia un Skill de MCP

MCP = las manos

Conecta la IA a un servicio o dato externo, como leer Notion o crear una factura. Necesita un programa o servidor en marcha.

Skill = el manual

Un archivo de texto que enseña a la IA cómo hacer una tarea. No se conecta a nada.

A veces se parecen: algunas Skills ejecutan scripts que llaman herramientas y algunos MCP solo envían conocimiento. Empieza por la tarea que quieres hacer.

Funciona con

Claude CodeCursorGemini CLIOpenCode

Según el README del autor y las carpetas del repo

Instalar

Primero elige una Skill

Este repo tiene 98 Skills. Elige una de la lista de arriba: su página muestra todas las formas de instalarla, como pedírselo a la IA o usar un ZIP

Que la IA la instale
Subir a claude.ai

Ir a la lista de Skills ↑

El comando del autor instala el conjunto completo de 98
/plugin marketplace add orchestra-research/AI-research-SKILLs
/plugin install fine-tuning@ai-research-skills

Copiado del README del autor; descarga y ejecuta su código

Conversación

Pregunta, comparte un consejo o avisa de que no funciona. Ordenado por lo que la gente marcó como útil.

Aún no hay publicaciones. Sé la primera persona en preguntar o compartir.

Lo publicado aquí lo escriben usuarios, no el equipo de PopNx.

Inicia sesión para publicar

Desde GitHub

Estrellas en GitHub
14.665
Las estrellas son de todo el repo, no de cada Skill
Autor
Orchestra-Research
Licencia
MIT
Último cambio de código
11 oct 2026
Archivos SKILL.md del repo (con traducciones y plantillas)
30
Temas
ai, ai-research, claude, claude-code, claude-skills, codex, gemini, gpt-5, grpo, huggingface, machine-leanring, megatron