Skip to content

AI-research-SKILLs

by Orchestra-Research

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.

About

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.

12,704
Stars
99
Skill Files
915
Forks
24
PRs Merged
17
Contributors
12
Issues Open
23
Issues Closed
2026-06-16
Last Activity

Skill Analysis

403
Avg Lines / Skill
1,563
Avg Words / Skill
1653
Code Blocks
529
Total Files
23.45 MB
Repo Size
267
Reference Files
Skill lines81 min / 406 median / 983 max
Code languagesbash, bibtex, http, javascript, json, latex, markdown, python, text, toml, yaml
Frontmatter keysauthor, dependencies, description, license, name, tags, version
Has CLAUDE.mdYes
Has LicenseYes
File typesmd (400), tex (15), sty (15), pdf (11), png (10), tsx (10), bib (9), json (7), js (6), py (5)

Skills (99)

  • autoresearch
    v1.0.0MIT412 lines3571 words7 blocks

    Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear opti...

    json
  • example-skill-name
    v1.0.0MIT107 lines275 words6 blocks

    Brief third-person description of what this skill does and when to use it. Include key terms and triggers for discovery. Maximum 1024 characters.

    bash
  • creative-thinking-for-research
    v1.0.0MIT367 lines3148 words

    Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by lev...

  • brainstorming-research-ideas
    v1.0.0MIT385 lines2891 words

    Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting...

  • awq-quantization
    v1.0.0MIT311 lines1035 words15 blocks

    Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on ...

    bashpython
  • optimizing-attention-flash
    v1.0.0MIT368 lines1287 words25 blocks

    Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long se...

    bashpython
  • gptq
    v1.0.0MIT451 lines1422 words17 blocks

    Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× me...

    bashpython
  • hqq-quantization
    v1.0.0MIT446 lines1218 words18 blocks

    Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets,...

    bashpython
  • ml-training-recipes
    v1.0.0MIT320 lines1528 words7 blocks

    Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Co...

    python
  • quantizing-models-bitsandbytes
    v1.0.0MIT412 lines1169 words23 blocks

    Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or...

    bashpython
  • gguf-quantization
    v1.0.0MIT428 lines1351 words20 blocks

    GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing...

    bashpython
  • blip-2-vision-language
    v1.0.0MIT565 lines1648 words16 blocks

    Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-t...

    bashpython
  • audiocraft-audio-generation
    v1.0.0MIT565 lines1560 words18 blocks

    PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text de...

    bashpython
  • segment-anything-model
    v1.0.0MIT501 lines1485 words23 blocks

    Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as pr...

    bashpython
  • clip
    v1.0.0MIT254 lines779 words8 blocks

    OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M...

    bashpython
  • stable-diffusion-image-generation
    v1.0.0MIT520 lines1380 words25 blocks

    State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, perfor...

    bashpython
  • whisper
    v1.0.0MIT318 lines990 words15 blocks

    OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six mode...

    bashpython
  • llava
    v1.0.0MIT305 lines937 words15 blocks

    Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA l...

    bashpython
  • evaluating-cosmos-policy
    v1.0.0MIT403 lines1603 words17 blocks

    Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, ru...

    bashpythontext
  • fine-tuning-openvla-oft
    v1.0.0MIT442 lines1790 words24 blocks

    Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM con...

    bashpythontext

Recent Commits

-295 contributions across all repos
JunJulAugSepOctNovDecJanFebMarAprMayJun
Less
More
  • 773a5292026-06-16
    release: v1.7.2 — ship Qoder agent auto-detection to npm
    zechenzhangAGI
  • 7590d562026-06-16
    feat(agents): add Qoder to supported agents (#29)
    markfu909
  • b6d48ad2026-06-16
    feat(model-merging): add unsupervised coefficient tuning via generation consistency (#34)
    Yiyang Du
  • c62ccde2026-06-15
    fix(release): v1.7.1 — repair lockfile sync and pin deps to patched versions (#62)
    Zechen Zhang
  • c20149a2026-06-15
    release: v1.7.0 — inventory consistency, drift guard & security hardening (#61)
    Zechen Zhang
  • f8afc972026-06-15
    docs: correct skill/category inventory to 98/23 + add drift guard (#60)
    Zechen Zhang
  • ee806fb2026-06-15
    fix(security): pin npm dependency versions to exact ranges (#53)
    xiaolai
  • 28f2d292026-04-28
    feat: add Agent-Native Research Artifact (ARA) category — 23rd, 3 skills
    zechenzhangAGI
  • 9aff7502026-04-13
    fix: correct welcome screen defaults and sync package-lock.json
    AmberLJC
  • 684be662026-04-13
    Merge pull request #51 from RUFFY-369/feat/hermes-agent-support
    Jiachen LIU