Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track...

Use when making decisions under uncertainty with quantifiable outcomes, comparing risky options (investments, product bets, strategic choices), prioritizing projects by expected return, assessing...

Smart article illustration skill. Analyzes article content and generates illustrations at positions requiring visual aids with multiple style options. Use when user asks to "add illustrations to...

Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, integrate with scanpy/PyTorch, for population-scale single-cell analysis.

Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, integrate with scanpy/PyTorch, for population-scale single-cell analysis.

Code review expert for security, quality, and performance analysis. Use when reviewing code, PRs, conducting security audits, or identifying performance issues.

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...

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF,...

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or...

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or...

Document database schemas, ERD diagrams, table relationships, indexes, and constraints. Use when documenting database schema, creating ERD diagrams, or writing table documentation.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF,...

Comprehensive guide for building high-performance Solana programs using Pinocchio - the zero-dependency, zero-copy framework. Covers account validation, CPI patterns, optimization techniques, and...

Guide for using SLIME (LLM post-training framework for RL Scaling). Use when working with SLIME for reinforcement learning training of language models, including setup, configuration, training...

Design serverless function deployments for AWS Lambda, Azure Functions, and Google Cloud Functions with event sources, IAM, and cold start optimization.

Use when adding unit tests for a dbt model or practicing test-driven development (TDD) in dbt

>

Tailwind CSS utility-first styling for JARVIS UI components

Design data pipelines with quality checks, orchestration, and governance using modern data stack patterns for robust ELT/ETL workflows.

Specialized Preact development skill for standards-based web applications with native-first architecture and minimal dependency footprint. Use when building Preact projects, particularly those...