Open-source skill turns AI into interactive multi-page 'Explorable Explanations' with JS games
danshipper · x · 2026-09-10
Developer nityeshaga released "Explorable Explanation", an open-source Claude skill (in the claude-home-base repo) that pushes models beyond pretty one-page HTML: it generates a set of interconnected pages, one idea per page, interleaved with small JavaScript games and interactive visuals so readers learn by playing.
The author spent 10 days refining it and says it's surprisingly hard even for latest SOTA models — claiming "Fable 5.1" is the only model that excels, while a rival model produced disappointing output from the same prompt. A walkthrough shows the comparison, and the skill is free to reuse.
More from coding & agent
- Cognition's Devin agents factor RSA-260, set new record; RSA-1024 cost pegged at ~$30M — StefanoGogioso · 2026-09-10
- Harmonic's Aristotle: an AI agent that proves software correct with machine-checked proofs — satnam6502 · 2026-09-10
- OpenAI Mobilized 250+ People to Build a "Defense Factory" of AI Agents That Find and Fix Vulnerabilities — OpenAI · 2026-09-10
- LangChain NYC meetup to teach voice agent evaluation across execution, outcomes and experience — LangChain · 2026-09-10
- Astral Details Code Signing for Its Toolchain, Extending to Ruff and ty — charliermarsh · 2026-09-10
- uv Now Ships Code-Signed Binaries for macOS and Windows, Including PyPI Wheels — charliermarsh · 2026-09-10