Skip to content

Instantly share code, notes, and snippets.

-- =========================================================
-- BARE MINIMUM NORTHWIND FOR TEACHING SQL
-- =========================================================
-- 1. SCHEMA DEFINITION
-- ---------------------------------------------------------
DROP TABLE IF EXISTS OrderDetails;
DROP TABLE IF EXISTS Orders;
DROP TABLE IF EXISTS Products;

> build · minimaxai/minimax-m2.7

<think>The user wants to add a BMP180 device/sensor to espforge. This matches the trigger phrase for the espforge-devices skill. I should load that skill first to get the detailed instructions.
</think>
→ Skill "espforge-devices"
→ Read ../../.config/opencode/skills/espforge-devices/SENSOR_CATEGORY.md
→ Read ../../.config/opencode/skills/espforge-devices/CLONEREPO.md
→ Read ../../.config/opencode/skills/espforge-devices/FIND_CRATES.md
→ Read ../../.config/opencode/skills/espforge-devices/REPO_EXAMPLES.md

LLM Wiki

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.

The core idea

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.