Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words Sign in

AI-Research-SKILLs Skill

Repository ↗

by Orchestra-Research★ 14,691 (whole repo)98 skills

★ Stars are for the whole repo, not each skill

Pick the skill to install

What it does

This repo is a collection of 98 skills

  • Connects Instruction files the AI reads
  • Account or key No key found in README or SKILL.md
  • Category Coding
Maker’s original description
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.
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![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)

Use together with

MCP servers that connect the AI to services for the same work

REA

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

by morlutoWidely used↓ 388.7K/wk★ 470.2KUpdated 8 days ago

MCP · Connects a serviceRuns on your computer

Fallow

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

by fallow-rsWidely used↓ 2.4M/wk★ 5.4KUpdated yesterday

MCP · Connects a serviceRuns on your computer

Desktop Commander

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

by wonderwhy-erWidely used↓ 740.3K/wk★ 10.4KUpdated 2 days ago

MCP · Connects a serviceRuns on your computer

Similar Skills

Same kind of work, ordered like the Skills list

Compared with similar ones
This one
AI-Research-SKILLs
reaandrej-karpathy-skillsgraphifyMoneyPrinterTurbo
MakerOrchestra-Researchmorlutomultica-aiGraphify-Labsharry0703
Skills981111
GitHub stars14,691470,165234,528150,695144,727
Last code changeOct 11, 2026Nov 20, 2026Apr 20, 2026Nov 20, 2026Nov 19, 2026
LicenseMITMIT–Apache-2.0MIT

98 skills (instruction sets) by Orchestra-Research that an AI reads and follows · not an MCP server

Pick the skill to install

Install only the ones you use. Open a skill to see how to install it

This set has 98 skills, too many to install at once: every installed skill’s description loads into every chat, so the AI picks the wrong one more easily. Pick only the ones you use from the list below

Showing 30 of 98 See all on 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.

How a Skill differs from MCP

MCP = the hands

Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.

Skill = the manual

A text file that teaches the AI how to do a task. It connects to nothing.

Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.

Works with

Claude CodeCursorGemini CLIOpenCode

From the maker’s README and the folders in the repo

Install

Pick a skill first

This repo has 98 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP

Let the AI install it
Upload to claude.ai

Go to the skill list ↑

The maker’s command installs the whole set of 98
/plugin marketplace add orchestra-research/AI-research-SKILLs
/plugin install fine-tuning@ai-research-skills

Copied from the maker’s README; it downloads and runs the maker’s code

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

From GitHub

GitHub stars
14,691
Stars are for the whole repo, not each skill
Maker
Orchestra-Research
License
MIT
Last code change
Oct 11, 2026
SKILL.md files in the repo (including translated copies and templates)
30
Topics
ai, ai-research, claude, claude-code, claude-skills, codex, gemini, gpt-5, grpo, huggingface, machine-leanring, megatron