Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4Γ memory reduction with <2% perplexity...
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language...
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to...
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive...
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5Γ cost reduction vs dense models), implementing sparse...
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models...
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor -...
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic...
Quality control, citation validation, fact-checking before human review
Prevent feature creep when building software, apps, and AI-powered products. Use this skill when planning features, reviewing scope, building MVPs, managing backlogs, or when a user says "just one...
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished...
Create with AI video tools on Runway - generate videos, edit with AI, and use creative ML models
Archives, contemporary accounts, timeline reconstruction
How to use a Win32 build of BusyBox to run many of the standard UNIX command line tools on Windows.
Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.
Personal backgrounds, interviews, motivations, humanizing details
DOJ/FBI/SEC press releases, agency statements, government sources
SEC filings, earnings calls, analyst reports, market data
Investigative articles, interviews, news coverage
Court documents, indictments, plea agreements, sentencing records