Agent-Skills.md

Agent Skills: Readwise Chat (RAG over Highlights)

Chat with Readwise highlights using GPT-5.1 RAG. Use when the user wants to ask questions about their reading library, get summaries across documents, or have a conversation about their highlights. Triggers on "ask readwise", "chat about my highlights", "what do my notes say about", "summarize my reading on".

UncategorizedID: edwinhu/workflows/readwise-chat

Repository

edwinhu/workflows
edwinhu
5

Install this agent skill to your local

pnpm dlx add-skill https://github.com/edwinhu/workflows/tree/HEAD/skills/readwise-chat

Skill Files

Browse the full folder contents for readwise-chat.

Download Skill

Loading file tree…

skills/readwise-chat/SKILL.md

Skill Metadata

Name
readwise-chat
Description
Chat with Readwise highlights using GPT-5.1 RAG. Use when the user wants to ask questions about their reading library, get summaries across documents, or have a conversation about their highlights. Triggers on "ask readwise", "chat about my highlights", "what do my notes say about", "summarize my reading on".

Readwise Chat (RAG over Highlights)

Uses GPT-5.1 to answer questions with RAG over the user's full highlight library via WebSocket streaming.

Prerequisites

Chat requires session cookies (not API token). Check if configured:

grep SESSION_COOKIES ~/.readwise/env

If missing, run:

readwise auth session

This launches Chrome, navigates to readwise.io/chat, and extracts httpOnly session cookies via CDP.

Commands

One-Shot Query

Streams the response to stdout as it arrives:

readwise chat "What are my highlights about fiduciary duty?"
readwise chat "Summarize my notes on proxy advisors"
readwise chat "Compare what I've read about SEC regulation vs FINRA"

With JSON output (includes related highlights):

readwise chat "What do my highlights say about broker-dealer regulation?" --json

Interactive REPL

Multi-turn conversation with context preserved:

readwise chat-interactive
readwise chat-interactive --model 5.1-thinking  # reasoning model

Type exit to quit.

Conversation Management

readwise chat-list                           # List all conversations
readwise chat-get <id>                       # Get conversation with messages
readwise chat-delete <id>                    # Delete conversation
readwise chat-rename <id> "Better Title"     # Rename conversation

Model Options

| Model ID | Name | Use Case | |----------|------|----------| | 5.1 | Fast (default) | Quick answers, simple lookups | | 5.1-thinking | Thinking | Complex synthesis, reasoning |

Chat vs Search

| Feature | readwise chat | readwise search | |---------|-----------------|-------------------| | Returns | Synthesized answer + highlights | Raw highlight matches | | Model | GPT-5.1 RAG | Vector similarity | | Auth | Session cookies | API token | | Speed | ~3-10s (streaming) | ~2s | | Highlights returned | Up to 69 | Top-N vector matches | | Multi-turn | Yes (interactive) | No |

Use chat when: You want a synthesized answer, cross-document analysis, or conversational exploration.

Use search when: You want raw highlight matches, exact quotes, or structured data for further processing.