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.
Skill Analysis
Skills (99)
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear opti...
jsonBrief third-person description of what this skill does and when to use it. Include key terms and triggers for discovery. Maximum 1024 characters.
bashApplies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by lev...
Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting...
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on ...
bashpythonOptimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long se...
bashpythonPost-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...
bashpythonHalf-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets,...
bashpythonBattle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Co...
pythonQuantizes 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...
bashpythonGGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing...
bashpythonVision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-t...
bashpythonPyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text de...
bashpythonFoundation 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...
bashpythonOpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M...
bashpythonState-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, perfor...
bashpythonOpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six mode...
bashpythonLarge Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA l...
bashpythonEvaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, ru...
bashpythontextFine-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
- 773a5292026-06-16release: v1.7.2 — ship Qoder agent auto-detection to npmzechenzhangAGI
- 7590d562026-06-16feat(agents): add Qoder to supported agents (#29)markfu909
- b6d48ad2026-06-16feat(model-merging): add unsupervised coefficient tuning via generation consistency (#34)Yiyang Du
- c62ccde2026-06-15fix(release): v1.7.1 — repair lockfile sync and pin deps to patched versions (#62)Zechen Zhang
- c20149a2026-06-15release: v1.7.0 — inventory consistency, drift guard & security hardening (#61)Zechen Zhang
- f8afc972026-06-15docs: correct skill/category inventory to 98/23 + add drift guard (#60)Zechen Zhang
- ee806fb2026-06-15fix(security): pin npm dependency versions to exact ranges (#53)xiaolai
- 28f2d292026-04-28feat: add Agent-Native Research Artifact (ARA) category — 23rd, 3 skillszechenzhangAGI
- 9aff7502026-04-13fix: correct welcome screen defaults and sync package-lock.jsonAmberLJC
- 684be662026-04-13Merge pull request #51 from RUFFY-369/feat/hermes-agent-supportJiachen LIU