surprise-me

Analyze Readwise highlights, Reader saves, and tags to surface a grounded insight.

Updated Jun 17, 2025
One-click install
npx skills add https://github.com/nikbrunner/dots --skill surprise-me-nikbrunner
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: surprise-me
Source: https://github.com/nikbrunner/dots/tree/main/common/.agents/skills/surprise-me
Command: npx skills add https://github.com/nikbrunner/dots --skill surprise-me-nikbrunner

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This capability helps users uncover surprising patterns in their personal reading data by synthesizing highlights, saved items, and metadata from Readwise and Reader to reveal meaningful self-knowledge.

Core Features & Use Cases

  • Cross-source analysis of highlights, saves, and tags to surface hidden interests and evolving reading patterns.
  • Delivers a single grounded surprise about the reader, with concrete evidence drawn from multiple documents.
  • Use case: reflect on long-term reading tendencies and identify unexpected connections between topics.

Quick Start

Ask it to analyze your Readwise highlights and Reader saves to surface a surprising insight.

Frequently Asked Questions about surprise-me

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find surprising patterns in my Readwise highlights?

Cross-source analysis of Readwise highlights and Reader saves identifies hidden interests and evolving reading patterns, delivering a single grounded insight validated across documents and time windows.

What is cross-source analysis of reading data?

Cross-source reading data analysis is the process of synthesizing Readwise highlights, Reader saves, and tags to reveal meaningful self-knowledge and unexpected connections between topics.

Do I need a Readwise MCP connection to analyze reading behavior?

Yes, analyzing reading behavior requires access to Readwise MCP tools or CLI equivalents, and the process includes safeguards to handle incomplete data or tool unavailability.

Can I use this to reflect on long-term reading tendencies?

Yes, you can reflect on long-term reading tendencies by validating findings across documents and time windows to ensure a grounded result about your evolving reading patterns.

What happens if my Readwise data is incomplete during analysis?

If Readwise data is incomplete during analysis, built-in safeguards activate to ensure the surfaced insight is grounded and validated across available documents and time windows.

How does this reading insight tool validate its findings?

This reading insight tool validates findings by analyzing data from all sources in parallel, cross-referencing documents and time windows to ensure the final insight is fully grounded in evidence.