aradotso avatar

Illustrated Explainer Spec

This is a complete spec for building a watercolor-style visual Wikipedia where every click drills deeper into whatever you point at. Type "photosynthesis," get a 16:9 painted explainer, click the chloroplast, get a new page zooming into that structure, infinitely. It's built on content-addressed caching so identical clicks never regenerate, and the architecture uses a thin client with server-side image model calls (Gemini in the reference implementation). The clever bit is compositing a red marker onto parent images before feeding them back to the model with strict style-consistency prompts. This is the kind of explorable explanation that feels obvious in retrospect but required someone to actually spec out the hashing, prompt engineering, and Sharp compositing plumbing.

skills.sh installs
165
GitHub stars
26
last updated
Jun 3, 2026

Install

$ npx -y skills add aradotso/trending-skills --skill illustrated-explainer-spec --agent claude-code

Installs into .claude/skills of the current project.

Files

Illustrated Explainer Spec Implementation Guide

Skill by ara.so — Daily 2026 Skills collection.

What This Project Is

A spec (not a library) for building a locally-run single-page web app where:

  1. User types a topic → AI generates a 16:9 watercolor-style illustrated explainer page
  2. User clicks anywhere on the image → AI generates a "drill-into" next page for that spot
  3. This repeats infinitely, preserving painting style across all pages
  4. Content-addressed caching means identical queries/clicks never re-generate

The spec is stack-agnostic — you choose the framework, image model API, and language. This skill shows you how to implement it end-to-end.


Architecture Overview

Browser (thin client)
  └── POST /api/page  ──►  Server
                              ├── hash → check disk cache
                              ├── composite red marker onto parent image
                              ├── call image model (text + optional image)
                              └── write PNG → return page object

Page Object Shape

Sponsors

Details

Repository
github.com/aradotso/trending-skills
Category
Documentation
First seen
Jun 3, 2026

More from aradotso/trending-skills

All 251
1sickn33 avataravoid-ai-writingsickn33/antigravity-awesome-skillsavoid ai writing165skills.sh installs
2boshu2 avatarlearnboshu2/agentopsOptionally analyze collections of durable157skills.sh installs
3rohitg00 avatarwiki-queryrohitg00/pro-workflowQuery pro-workflow wikis via SQLite FTS5 BM25 retrieval. Returns top-K passages with citations. Use when answering a question that any of the user's wikis alrea157skills.sh installs
4rohitg00 avatarwiki-builderrohitg00/pro-workflowStart, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base. Each wiki is a folder of markdown pages with provenance, 156skills.sh installs
5tomasonjo avatarneo4j-cypher-guidetomasonjo/blogsneo4j cypher guide155skills.sh installs
6rohitg00 avatarwiki-research-looprohitg00/pro-workflowAuto-grow a pro-workflow wiki by running a budget-capped BFS research loop over pluggable source fetchers (web, arXiv, GitHub). Each iteration pops a seed from 154skills.sh installs