Highlight Graph

Turns your Readwise highlights into an interactive force graph where you can see how ideas connect across everything you've read. It pulls a couple hundred recent highlights, spins up parallel agents to find semantic connections between different sources, then renders a browser-based graph with color-coded books and clickable edges. Same-source highlights get automatic links, cross-source connections are semantic and deliberately sparse. The graph uses screen-relative text scaling and has a sidebar that shows connected ideas when you click a node. Good for when you've been highlighting aggressively and want to see the through-lines without manually tagging or organizing. Built on force-graph with a Python script that outputs standalone HTML.

skills.sh installs: 447
GitHub stars: 328
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add readwiseio/readwise-skills --skill highlight-graph --agent claude-code

Installs into .claude/skills of the current project.

Files

You are building an interactive 2D force-graph visualization of the user's Readwise highlights, showing how ideas connect across books, articles, and other sources. Think Obsidian's graph view, but for highlights.

Readwise Access

Check if Readwise MCP tools are available (e.g. mcp__readwise__readwise_list_highlights). If they are, use them throughout. If not, use the equivalent readwise CLI commands instead.

Process

Step 1: Fetch Highlights

Open with:

Highlight Graph · Readwise

I'll pull your recent highlights, find connections between them, and build a graph you can explore. Give me a moment.

Fetch the user's most recent highlights using readwise_list_highlights with page_size=100. Fetch 2 pages (200 highlights) for a good starting graph. Each page returns highlights from most recent to least recent — use page=1, then page=2.