rulebook-ai

🥈Silver

Elevate vibe coding to vibe engineering: Get consistent Github Copilot custom instructions, Cursor, Roo Code, Cline, Windsurf, Claude Code, Gemini Cli, Codex CLI, kilo code, warp custom rules via a universal, managed template. Features vibe coding memory bank & best practices for large codebases.

592790Updated 2w ago

Intermediate30min to implementautomation

Saves ~90 min per use

Quick InstallView Source

git clone https://github.com/botingw/rulebook-ai.git

Works with:

Claude

Overview

About This Skill

memory/docs/user_guide/tutorial.md

How to Use

[{"step":"Identify your project's tech stack and team conventions. Gather existing documentation (e.g., README, style guides) and past decisions (e.g., architecture diagrams, meeting notes).","action":"Use the prompt template to generate a draft template. Replace [LANGUAGE/TECH_STACK] with your stack (e.g., 'TypeScript/React'), [TEAM_RULES] with your conventions, [BEST_PRACTICES] with your standards, and [MEMORY_BANK] with project-specific notes."},{"step":"Customize the template for your AI tool. Adjust the JSON structure to match your tool's import format (e.g., Copilot uses a text file, Cursor uses a JSON config).","action":"For Copilot: Save the JSON as a .txt file and import it via Settings > Copilot > Custom Instructions. For Cursor: Paste the JSON into Settings > AI > Custom Rules."},{"step":"Test the template in a controlled environment. Generate code snippets for a small feature (e.g., a new API endpoint) and verify the output aligns with your rules.","action":"Use your AI tool to generate code for a simple task (e.g., 'Add a new endpoint for fetching user orders'). Compare the output against your team's standards. Iterate on the template if needed."},{"step":"Share the template with your team and enforce its use. Document how to update the template as the project evolves.","action":"Create a shared Notion/GitHub page explaining how to update the template. Schedule monthly reviews to add new memory bank entries (e.g., 'Added new Redis cache for product listings')."},{"step":"Monitor AI tool performance and gather feedback. Adjust the template based on recurring issues or gaps in the rules.","action":"Use your AI tool's feedback features (e.g., Copilot's 'thumbs up/down') to track compliance. Add a 'feedback' section to the template to log common issues (e.g., 'AI often forgets to add error handling for Stripe calls')."}]

Use Cases

Quickly onboard AI assistants with tailored rules for specific programming tasks.

Maintain consistent coding standards across different AI platforms without manual adjustments.

Easily switch between different project configurations using named profiles.

Collaborate with team members by sharing environment packs that encapsulate best practices.

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/botingw/rulebook-ai

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Generate a universal GitHub Copilot/Cursor/CLI custom instructions template for [LANGUAGE/TECH_STACK] projects. Include [TEAM_RULES] (e.g., naming conventions, error handling), [BEST_PRACTICES] (e.g., security, performance), and [MEMORY_BANK] (e.g., project architecture, past decisions). Format as a JSON config for direct import into [TOOL_NAME]. Example: 'Generate a Copilot custom instructions template for a Python/Django e-commerce backend. Include team rules for API versioning, best practices for database indexing, and memory bank notes about our payment gateway integration.'

Example Output

```json
{
  "name": "Python/Django E-Commerce Backend",
  "version": "1.2",
  "instructions": {
    "team_rules": {
      "naming": "Use snake_case for variables/functions, PascalCase for classes. Prefix private methods with '_'.",
      "api_versioning": "Always include v{major}.{minor} in URL paths (e.g., /api/v1/products/).",
      "error_handling": "Wrap third-party API calls in try-except blocks and log errors with context."
    },
    "best_practices": {
      "security": [
        "Never hardcode secrets. Use environment variables or Django's settings.py.",
        "Sanitize user inputs to prevent SQL injection and XSS."
      ],
      "performance": [
        "Use Django's select_related() for foreign key queries to reduce DB hits.",
        "Cache frequent queries with Redis (e.g., product listings)."
      ],
      "testing": "Write unit tests for all new features using pytest. Aim for 80%+ coverage."
    },
    "memory_bank": {
      "architecture": "Monolithic Django app with separate apps for users, products, and orders.",
      "past_decisions": {
        "payment_gateway": "Integrated Stripe for payments. Store only payment intent IDs, not full card details.",
        "auth_system": "Used Django-allauth for auth. Customized login flow to include OTP verification."
      },
      "known_issues": [
        "Cart persistence is client-side only. Consider server-side storage for logged-in users.",
        "Image uploads are slow. Plan to migrate to S3-compatible storage."
      ]
    }
  }
}
```

**Usage Notes:**
- Import this JSON into your AI tool's custom instructions settings.
- Update `memory_bank` weekly as the project evolves.
- Share this template with your team to ensure consistency across tools (Copilot, Cursor, etc.).