deep▌

Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.

Systematic literature research: disambiguate, search with collision-aware queries, grade evidence, produce structured reports.

$22

I help you conduct comprehensive, multi-faceted research on any topic. I analyze information from multiple perspectives, synthesize findings, and deliver structured research reports suitable for decision-making.

Expert guidance for deep learning, transformers, diffusion models, and LLM development with PyTorch. \n \n Covers PyTorch model architectures, transformers, diffusion models, and LLM fine-tuning with libraries including Transformers, Diffusers, and Gradio \n Emphasizes GPU optimization, mixed precision training, distributed training, and gradient accumulation for efficient workflows \n Includes best practices for data loading, train/validation splits, early stopping, learning rate scheduling, an

This skill provides a systematic methodology for conducting thorough web research. Load this skill BEFORE starting any content generation task to ensure you gather sufficient information from multiple angles, depths, and sources.

Answers: "Who is this wallet and what have they been doing?"

Comprehensive GitHub repository analysis through multi-round research combining API data, web search, and structured reporting. \n \n Executes four research rounds: GitHub API extraction, discovery searches, deep investigation with web fetching, and timeline analysis from commits and issues \n Produces structured markdown reports with executive summaries, chronological timelines, metrics tables, and Mermaid diagrams for architecture and comparisons \n Implements source prioritization (official d

Master deep work with a three-part framework: 1 hour daily of Building, balanced with Maintenance and Recovery. \n \n Establish sustainable productivity through a 90-day transformation sequence: diagnose focus state, define vision and anti-vision, build a 10-year-to-daily goal hierarchy, and apply project-based learning to close skill gaps \n Identify lever-moving tasks that actually progress goals using the challenge-equals-skill principle, avoiding both anxiety (challenge too high) and boredom

Exhaustive research with configurable depth, latency, and cost trade-offs for complex topics. \n \n Three processor tiers (pro-fast, ultra-fast, ultra) ranging from 30 seconds to 25 minutes, with cost scaling from 1x to 3x baseline \n Asynchronous execution with polling: kick off research instantly, monitor progress via URL, retrieve results when ready without blocking \n Outputs formatted markdown report and JSON metadata; executive summary printed to stdout for quick overview \n Designed for e