reader-deep-dive – OpenClaw Skill

---

name: reader-deep-dive description: Daily briefing that connects your recent reading to your long-term archive. metadata: {"clawdbot":{"emoji":"🤿","requires":{"env":["READWISE_TOKEN"]}}}

Reader Deep Dive 🤿

Your reading list shouldn't be a write-only memory. This skill checks what you've saved recently, finds connected ideas from your deep archive (last 3 days, 3 months, or years ago), and sends you a high-signal briefing with context on why you should revisit them.

It turns "I saved that somewhere" into "Here is the timeline of your thinking on this topic."

How it works

1. Scans Recent Saves: Checks your Readwise Reader "new" folder for the last 24 hours.
2. Identifies Themes: Uses your system's default LLM to figure out your current obsession.
3. Temporal Context: Searches your library history and finds relevant items from different timeframes.
4. Delivers Briefing: Sends a WhatsApp message with a "Deep Dive" summary connecting your current saves to your past library.

Setup

1. Get your Access Token from readwise.io/access_token.
2. Set it in your environment:

   export READWISE_TOKEN="your_token_here"
   

Usage

Manual Trigger:

bash scripts/brief.sh

Schedule (Cron): Run it every afternoon at 2 PM:

clawdbot cron add --id reader_brief --schedule "0 14 * * *" --command "bash scripts/brief.sh"

Customization

You can tweak the prompt in prompts/briefing.txt if you want a different tone or format. By default, it uses a clean, WhatsApp-friendly style.

Reader Deep Dive 🤿

Your reading list shouldn't be a write-only memory.

Most of us save articles, read them (maybe), and then forget them. We have a library of thousands of ideas, but we treat every new day like we're starting from zero.

This agent changes that. It scans what you're reading right now and connects it to the deepest cuts from your past. It doesn't just list links; it builds a timeline of your thinking on a specific topic.

What It Does

Every afternoon (or on-demand), it runs a comprehensive research pass:

1. Detects Your Current Focus: It analyzes your last 24 hours of saves to identify the core theme—whether it's "AI Agents," "Vibe Coding," or "Metabolic Health."
2. Mines Your Archive: It searches your entire history for that topic, pulling from thousands of documents saved over years.
3. Synthesizes Intelligence: It selects at least 5 deep-dive connections and organizes them chronologically (Oldest to Newest) to show you the history of your thinking.
4. Enriches Metadata: Every reference includes the Author Name and Media Type (tweet, video, article, etc.) for high-signal context.

The Output

You get a high-signal WhatsApp message formatted for mobile readability:

TOPIC: AI AGENTS 🎯

CURRENT FOCUS

• Why OpenClaw feels alive (tweet) by claire vo (Saved: Today) Argues that "aliveness" comes from reactive loops rather than raw intelligence.

DEEP DIVE CONNECTIONS

• One Year Ago: AutoGPT: The Dream of Autonomy (video) by Prompt Engineering (Saved: 2024-05-20) The original vision for self-improving agents. Revisiting this highlights the progress from "prompt engineering" to the "agentic engineering" patterns in your current saves. https://read.readwise.io/read/xyz

• Last Month: The Rise of the Wrapper (article) by Nat Friedman (Saved: 2025-11-12) An analysis of LLM thin-clients. This provides the architectural context for the more complex stateful frameworks you are exploring today. https://read.readwise.io/read/abc

[... at least 3 more items ...]

Setup

1. Get a Token: Grab your Readwise Access Token from readwise.io/access_token.
2. Set Environment:

   export READWISE_TOKEN="your_token_here"
   

3. Run:

   bash scripts/brief.sh
   

Requirements

• curl, jq
• clawdbot (for LLM inference and WhatsApp delivery)
• gemini CLI (for stateless completion)