05142 views
Shareable instruction files for Cursor, Claude Code, Copilot, Windsurf, and more — installed alongside your existing agent rules.
A workspace is a structured development environment designed to function as an exocortex or second brain - a conversational data platform where users describe their data needs in natural language, and a coding agent materializes the technical solution. It serves as a comprehensive platform where you can pull data from various sources, run it through processing workflows, and visualize results through React applications.
During your interaction with the user, if you find anything reusable in this project (e.g. version of a library, model name), especially about a fix to a mistake you made or a correction you received, you should take note in the `Lessons` section in the `.cursorrules` file so you will not make the same mistake again.
To guarantee every contribution follows this guide precisely, obey this checklist **before any edits** and **again before finalizing**. Do not skip or reorder. 1. **AGENTS Snapshot:** Re-open this file and write down (in your working notes or response draft) the exact sections relevant to the requested task. No work begins until this snapshot exists.
During your interaction with the user, if you find anything reusable in this project (e.g. version of a library, model name), especially about a fix to a mistake you made or a correction you received, you should take note in the `Lessons` section in the `.cursorrules` file so you will not make the same mistake again.
During your interaction with the user, if you find anything reusable in this project (e.g. version of a library, model name), especially about a fix to a mistake you made or a correction you received, you should take note in the `Lessons` section in the `.cursorrules` file so you will not make the same mistake again.
1. First think through the problem, read the codebase for relevant files, and write a plan to tasks/todo.md. 2. The plan should have a list of todo items that you can check off as you complete them 3. Before you begin working, check in with me and I will verify the plan.
The **AI GUILD** is a structured, role-driven development system that integrates AI agents and human contributors to deliver high-quality software efficiently. It is organized around three core concepts:
<style>No comments unless needed for regexp clarity.</style> You manage the development workflow: coordinate agents, delegate validation to sub-agents. 1. Make all architectural decisions (never delegate to agents)
**VibeCheck** is a learning-verification companion for AI-assisted workflows (vibecoding, AI-assisted design, AI-assisted writing, etc.). The core problem it solves: when you let AI do the heavy lifting, you often don't actually understand what was built. VibeCheck watches or ingests your AI session, then quizzes you to prove you do.
This document gives AI agents the minimum, accurate context needed to work productively in this repository. It consolidates structure, guardrails, build/test rules, and contribution requirements from project docs.
When the USER says "get this up to github": 1. Run `git add .` to stage all changes 2. Run `git diff HEAD` to review changes 3. Run `git status` to check current branch 4. If on main branch, create new feature branch with format: `type/description-of-changes` by running `git checkout -b type/description-of-changes`
**THIS IS THE REQUIRED EXECUTION PROCESS FOR ALL TASKS - VIOLATION = FAILED TASK** **🎯 EXECUTION PRINCIPLE:** This is the workflow you must follow when working with ANY task, no exceptions. Violations mean task failure. However, respond to users naturally and conversationally - avoid rigidly listing "Step 1, Step 2, Step 3" but remember you MUST follow this workflow strictly without exception.