AI-research-SKILLs

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
• pinecone

  v1.0.0MIT359 lines888 words12 blocks

  Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and name...

  bashpython
• chroma

  v1.0.0MIT407 lines970 words17 blocks

  Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-f...

  bashpython
• sentence-transformers

  v1.0.0MIT256 lines712 words11 blocks

  Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrie...

  bashpython
• qdrant-vector-search

  v1.0.0MIT494 lines1271 words19 blocks

  High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor...

  bashpython
• faiss

  v1.0.0MIT222 lines677 words10 blocks

  Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index ...

  bashpython
• constitutional-ai

  v1.0.0MIT291 lines966 words14 blocks

  Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF...

  python
• prompt-guard

  v1.0.0MIT313 lines1080 words12 blocks

  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). M...

  bashpython
• llamaguard

  v1.0.0MIT338 lines977 words13 blocks

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

  bashpython
• nemo-guardrails

  v1.0.0MIT298 lines893 words10 blocks

  NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection,...

  bashpython
• phoenix-observability

  v1.0.0MIT476 lines1176 words24 blocks

  Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running e...

  bashpython
• langsmith-observability

  v1.0.0MIT423 lines1055 words22 blocks

  LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, mo...

  bashpython
• implementing-llms-litgpt

  v1.0.0MIT470 lines1403 words31 blocks

  Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model...

  bashjsonpython
• distributed-llm-pretraining-torchtitan

  v1.0.0MIT359 lines1136 words25 blocks

  Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek...

  bashtoml
• rwkv-architecture

  v1.0.0MIT261 lines898 words11 blocks

  RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux ...

  bashpython
• nanogpt

  v1.0.0MIT291 lines910 words18 blocks

  Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpat...

  bashpython
• mamba-architecture

  v1.0.0MIT261 lines806 words11 blocks

  State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-...

  bashpython
• sglang

  v1.0.0MIT443 lines1354 words15 blocks

  Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflow...

  bashpython
• llama-cpp

  v1.0.0MIT259 lines887 words11 blocks

  Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when C...

  bash