From a dense paper to an idea you can use.
My roleCreator
01 / The context
Readers want to understand the ideas behind AI papers without losing the detail inside equations, architecture diagrams, and terminology.
A Claude Code skill that turns AI research papers into interactive HTML lessons with analogies, workflows, annotated code, plain-English math, and quizzes.
02 / Inside the project
Choose a step, inspect the details, and explore the thinking behind the experience.
Authored teaching example · illustrates the skill’s output patterns
Imagine asking a question in a reading group. You listen more closely to the people whose notes are relevant. Attention similarly combines information with different weights. This analogy explains weighting, not every detail of a Transformer.
From the project
Original project assets. Open an image to inspect it at full resolution.
03 / Decisions & evidence
The skill guides a coding assistant to analyze a paper and produce a self-contained HTML lesson. Teaching patterns include analogies, annotated code, equation explanations, and scenario-based quizzes. Inspired by Zara Zhang’s codebase-to-course skill, as credited in the original LinkedIn post; this project specializes in research papers.
The README includes example output for Attention Is All You Need. The interactive lesson on this page was written for the portfolio to illustrate the skill’s teaching patterns; it was not generated by running the skill.
Reviewed against the linked public sources and supplied assets. Demonstrations on this page use fixed example content unless labeled as an original recording or screenshot.