akillness/ai-research-skills

1

llama-cpp Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M…

akillness/ai-research-skills

2

2

long-context Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when…

akillness/ai-research-skills

2

3

audiocraft-audio-generation PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you ne…

akillness/ai-research-skills

1

4

autogpt-agents Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, …

akillness/ai-research-skills

1

5

autoresearch Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid expe…

akillness/ai-research-skills

1

6

awq-quantization Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when de…

akillness/ai-research-skills

1

7

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

akillness/ai-research-skills

1

8

blip-2-vision-language Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, v…

akillness/ai-research-skills

1

9

brainstorming-research-ideas Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when explo…

akillness/ai-research-skills

1

10

chroma Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text searc…

akillness/ai-research-skills

1

11

clip OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross…

akillness/ai-research-skills

1

12

constitutional-ai Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with s…

akillness/ai-research-skills

1

13

creative-thinking-for-research Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely…

akillness/ai-research-skills

1

14

crewai-multi-agent Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents wo…

akillness/ai-research-skills

1

15

deepspeed Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/F…

akillness/ai-research-skills

1

16

distributed-llm-pretraining-torchtitan Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use whe…

akillness/ai-research-skills

1

17

dspy Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and…

akillness/ai-research-skills

1

18

evaluating-code-models Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when …

akillness/ai-research-skills

1

19

evaluating-cosmos-policy Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for …

akillness/ai-research-skills

1

20

evaluating-llms-harness Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking …

akillness/ai-research-skills

1

21

experiment-tracking-swanlab Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hos…

akillness/ai-research-skills

1

22

faiss Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU…

akillness/ai-research-skills

1

23

fine-tuning-openvla-oft Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action hea…

akillness/ai-research-skills

1

24

fine-tuning-serving-openpi Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robo…

akillness/ai-research-skills

1

25

fine-tuning-with-trl Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/…

akillness/ai-research-skills

1

26

gguf-quantization GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardwar…

akillness/ai-research-skills

1

27

gptq Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on c…

akillness/ai-research-skills

1

28

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

akillness/ai-research-skills

1

29

guidance Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and…

akillness/ai-research-skills

1

30

hqq-quantization Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision with…

akillness/ai-research-skills

1

31

huggingface-accelerate Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpee…

akillness/ai-research-skills

1

32

huggingface-tokenizers Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Suppor…

akillness/ai-research-skills

1

33

implementing-llms-litgpt Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mi…

akillness/ai-research-skills

1

34

instructor Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse co…

akillness/ai-research-skills

1

35

knowledge-distillation Compress large language models using knowledge distillation from teacher to student models. Use when deploying smalle…

akillness/ai-research-skills

1

36

lambda-labs-gpu-cloud Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances w…

akillness/ai-research-skills

1

37

langchain Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, An…

akillness/ai-research-skills

1

38

langsmith-observability LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating m…

akillness/ai-research-skills

1

39

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

akillness/ai-research-skills

1

40

llamaguard Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual …

akillness/ai-research-skills

1

41

llamaindex Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing,…

akillness/ai-research-skills

1

42

llava Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP v…

akillness/ai-research-skills

1

43

mamba-architecture State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV ca…

akillness/ai-research-skills

1

44

miles-rl-training Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training l…

akillness/ai-research-skills

1

45

ml-paper-writing Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use …

akillness/ai-research-skills

1

46

mlflow Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments w…

akillness/ai-research-skills

1

47

modal-serverless-gpu Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure…

akillness/ai-research-skills

1

48

model-merging Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating special…

akillness/ai-research-skills

1

49

model-pruning Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing mode…

akillness/ai-research-skills

1

50

moe-training Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limit…

akillness/ai-research-skills

1