Home / orchestra-research / ai-research-skills · GitHub

CLAUDE.mdA

CLAUDE.md from orchestra-research/ai-research-skills is a CLAUDE.md file: the standing instructions Claude Code reads in that repo.

Install it, pinned
mdr add orchestra-research/ai-research-skills/CLAUDE.md@git:20260615.f8afc97

Pins git:20260615.f8afc97 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
CLAUDE.md file
Repository
orchestra-research/ai-research-skills
Path
CLAUDE.md
Versions recorded
5
Latest version
git:20260615.f8afc97, committed Jun 15, 2026
First version recorded
Feb 8, 2026
Size
14,471 bytes
Repository stars
13,718
License
MIT

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

## Project Overview

**AI Research Skills Library** - A comprehensive open-source library of 98 AI research skills enabling AI agents to autonomously conduct AI research — from idea to paper. Each skill provides expert-level guidance (200-500 lines) with real code examples, troubleshooting guides, and production-ready workflows.

**Mission**: Enable AI agents to autonomously conduct AI research from hypothesis to experimental verification, covering the full lifecycle: literature survey, ideation, dataset preparation, training pipelines, model deployment, evaluation, and paper writing.

## Repository Architecture

### Directory Structure (98 Skills Across 23 Categories)

Skills are organized into numbered categories representing the AI research lifecycle:

- `0-autoresearch-skill/` - **Autonomous research orchestration** (1 skill: Autoresearch — central layer that manages the full lifecycle and routes to all other skills)
- `01-model-architecture/` - Model architectures (5 skills: TorchTitan, LitGPT, Mamba, RWKV, NanoGPT)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add orchestra-research/ai-research-skills/CLAUDE.md@sha256:be8a06e14bf324f5

The line at the top of this page pins the label git:20260615.f8afc97, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_u2lnk562b3desipp.svg)](https://markdownregistry.com/a/art_u2lnk562b3desipp)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Feb 8, 2026 and Jun 15, 2026, about one every 32 days.

versioncommittedcommitsizeaudit
git:20260615.f8afc97 latest2026-06-15 f8afc97 14,471 BA view · diff
git:20260428.28f2d292026-04-28 28f2d29 14,296 BA view · diff
git:20260325.6710bc72026-03-25 6710bc7 14,068 BA view · diff
git:20260316.9d398932026-03-16 9d39893 14,068 BA view · diff
git:20260208.398ba622026-02-08 398ba62 13,615 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (14471 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

orchestra-research/ai-research-skills · 13,718 stars · license MIT · pushed 2026-10-11 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_u2lnk562b3desipp
GET https://markdownregistry.com/api/v1/resolve?ref=orchestra-research/ai-research-skills/CLAUDE.md
GET https://markdownregistry.com/api/v1/blob/be8a06e14bf324f524cf11ede6255ccb825bcf09844e9ae7cfff2ae008303241

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: what a CLAUDE.md file is · keeping AGENTS.md and CLAUDE.md in sync · which agent file does what.

More from orchestra-research/ai-research-skills

autoresearch SKILL.md skill
orchestra-research/ai-research-skills · 0-autoresearch-skill/SKILL.md · Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid…
v1.0.0 · audit A · 13,718 stars
implementing-llms-litgpt SKILL.md skill
orchestra-research/ai-research-skills · 01-model-architecture/litgpt/SKILL.md · Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen…
v1.0.0 · audit A · 13,718 stars
mamba-architecture SKILL.md skill
orchestra-research/ai-research-skills · 01-model-architecture/mamba/SKILL.md · State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV…
v1.0.0 · audit A · 13,718 stars
nanogpt SKILL.md skill
orchestra-research/ai-research-skills · 01-model-architecture/nanogpt/SKILL.md · Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning…
v1.0.0 · audit A · 13,718 stars
rwkv-architecture SKILL.md skill
orchestra-research/ai-research-skills · 01-model-architecture/rwkv/SKILL.md · RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel)…
v1.0.0 · audit A · 13,718 stars
distributed-llm-pretraining-torchtitan SKILL.md skill
orchestra-research/ai-research-skills · 01-model-architecture/torchtitan/SKILL.md · Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when…
v1.0.0 · audit A · 13,718 stars
huggingface-tokenizers SKILL.md skill
orchestra-research/ai-research-skills · 02-tokenization/huggingface-tokenizers/SKILL.md · Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports…
v1.0.0 · audit A · 13,718 stars
sentencepiece SKILL.md skill
orchestra-research/ai-research-skills · 02-tokenization/sentencepiece/SKILL.md · Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k…
v1.0.0 · audit A · 13,718 stars
axolotl SKILL.md skill
orchestra-research/ai-research-skills · 03-fine-tuning/axolotl/SKILL.md · Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO…
v1.0.0 · audit A · 13,718 stars
llama-factory SKILL.md skill
orchestra-research/ai-research-skills · 03-fine-tuning/llama-factory/SKILL.md · Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal…
v1.0.0 · audit A · 13,718 stars
peft-fine-tuning SKILL.md skill
orchestra-research/ai-research-skills · 03-fine-tuning/peft/SKILL.md · Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B)…
v1.0.0 · audit A · 13,718 stars
unsloth SKILL.md skill
orchestra-research/ai-research-skills · 03-fine-tuning/unsloth/SKILL.md · Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
v1.0.0 · audit A · 13,718 stars

Every file in orchestra-research/ai-research-skills

Other files named CLAUDE.md

CLAUDE.md CLAUDE.md file
affaan-m/ecc · CLAUDE.md
git:20260528.04c68e4 · audit A · 284,510 stars
CLAUDE.md CLAUDE.md file
firecrawl/firecrawl · CLAUDE.md
git:20261008.5a75dca · audit A · 193,096 stars
CLAUDE.md CLAUDE.md file
garrytan/gstack · CLAUDE.md
git:20261011.5d64745 · audit A · 136,966 stars
CLAUDE.md CLAUDE.md file
juliusbrussee/caveman · CLAUDE.md
git:20261010.505ac30 · audit B · 113,780 stars
CLAUDE.md CLAUDE.md file
addyosmani/agent-skills · CLAUDE.md
git:20260720.8fd2081 · audit A · 109,013 stars
CLAUDE.md CLAUDE.md file
nexu-io/open-design · CLAUDE.md
git:20260430.9b57c22 · audit B · 102,533 stars
CLAUDE.md CLAUDE.md file
thedotmack/claude-mem · CLAUDE.md
git:20261013.84bbb53 · audit A · 102,153 stars
CLAUDE.md CLAUDE.md file
egonex-ai/understand-anything · CLAUDE.md
git:20260710.6677c67 · audit B · 87,696 stars

Browse by kind, by grade A, or by owner.