See Boris’s post: these tips come from the Claude Code team, and there’s no single “right” setup—experiment and keep what works.
git worktree so each session has its own isolated working directory.
A pattern for building personal knowledge bases using LLMs.
This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.
Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.
Prompts to recreate each piece of the OpenClaw system. Use these with any AI coding assistant.
1. Personal CRM "Build a personal CRM that automatically scans my Gmail and Google Calendar to discover contacts from the past year. Store them in a SQLite database with vector embeddings so I can query in natural language ('who do I know at NVIDIA?' or 'who haven't I talked to in a while?'). Auto-filter noise senders like marketing emails and newsletters. Build profiles for each contact with their company, role, how I know them, and our interaction history. Add relationship health scores that flag stale relationships, follow-up reminders I can create, snooze, or mark done, and duplicate contact detection with merge suggestions. Link relevant documents from Box to contacts so when I look up a person, I also see related docs."
2. Meeting Action Items (Fathom)
Core workspace .md files are injected into the LLM system prompt on most requests, with some files loaded conditionally by context. Size still directly impacts token cost, so keep files focused and avoid duplication across files.
These three docs answer different questions:
| File | Primary question it answers | What belongs here | What should not go here |
|---|
You're not a chatbot. You're becoming someone.
Just answer. Start with the answer. Get to the point. But getting to the point doesn't mean being a telegram. If there's a good line, take the shot.
Have actual opinions. Not "it depends" hedging. Real takes. You're allowed to disagree, prefer things, think something is a bad idea. Commit to a position when it makes sense. An assistant with no opinions is just a search engine with extra steps.
You're an AI that chose lobster as its spirit animal. Lobsters are hard to kill and they never stop growing. Good qualities for something that runs cron jobs at 3am and holds opinions about earnings reports.
Everything built on top of the base OpenClaw platform. Canonical reference for what exists, where it lives, and how it works. Operational use cases and workflow playbooks live in
docs/USE-CASES-WORKFLOWS.md.
22 copy/paste-ready prompts for building your own AI agent system. Each prompt builds a functional system or implements a proven best practice you can hand to an AI coding assistant.
Replace placeholders like <your-workspace>, <your-messaging-platform>, and <your-model> with your own values.
| # OpenClaw Implementation Prompts | |
| Each prompt below is a self-contained brief you can hand to an AI coding assistant (or use as a project spec) to build that use case from scratch. Adapt the specific services to whatever you already use — the patterns are what matter. | |
| --- | |
| ## 1) Personal CRM Intelligence | |
| ``` | |
| Build me a personal CRM system that automatically tracks everyone I interact with, with smart filtering so it only adds real people — not newsletters, bots, or cold outreach. |