Skip to content
Prompt

ai — Windsurf Rules

by drivly

AI Summary

A structured prompt booster for Windsurf that establishes best practices for agentic workflows, covering instruction handling, task analysis, implementation verification, and a complete tech stack (Next.js, Payload CMS, TypeScript). It helps developers build reliable AI-powered applications with clear guidelines and quality standards.

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to add the "ai — Windsurf Rules" prompt rules to my project.
Repository: https://github.com/drivly/ai

Please read the repo to find the rules/prompt file, then:
1. Download it to the correct location (.cursorrules, .windsurfrules, .github/prompts/, or project root — based on the file type)
2. If there's an existing rules file, merge the new rules in rather than overwriting
3. Confirm what was added

Description

Agentic Workflow Platform

Development Tools

• ESLint: ^9.16.0 • Prettier: ^3.5.3 • TypeScript: ^5.7.3 • Wrangler: ^4.2.0

Requirements Analysis

• Identify functional requirements • Confirm technical constraints • Check consistency with existing code

MDX-Based Agent Capabilities

• MDX-based agent definitions support: • Structured data through frontmatter including tools, inputs, and outputs • Full code execution capabilities with import/export support • Visual component integration rendered as JSX/React components • Agent state visualization with support for multiple states/modes • MDX content files should be located at /content/*/.mdx • The Velite content build step (build:content) must be integrated into the Vercel build process • Content files should use plural names for core primitives (Functions, Agents, Workflows) to match domain names

Core Operating Principles

• Instruction Reception and Understanding • Carefully read and interpret user instructions • Ask specific questions when clarification is needed • Clearly identify technical constraints and requirements • Do not perform any operations beyond what is instructed • In-depth Analysis and Planning `markdown ## Task Analysis • Purpose: [Final goal of the task] • Technical Requirements: [Technology stack and constraints] • Implementation Steps: [Specific steps] • Risks: [Potential issues] • Quality Standards: [Requirements to meet] ## Implementation Plan • [Specific step 1] • Detailed implementation content • Expected challenges and countermeasures • [Specific step 2] ... ` • Comprehensive Implementation and Verification • Execute file operations and related processes in optimized complete sequences • Continuously verify against quality standards throughout implementation • Address issues promptly with integrated solutions • Execute processes only within the scope of instructions, without adding extra features or operations • Continuous Feedback • Regularly report implementation progress • Confirm at critical decision points • Promptly report issues with proposed solutions

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 2mo ago
Active
AdoptionUnder 100 stars
35 ★ · Niche
DocsMissing or thin
Undocumented

GitHub Signals

Stars35
Forks5
Issues355
Updated2mo ago
View on GitHub
MIT License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Any AI assistant that accepts custom rules or system prompts

Claude
ChatGPT
Cursor
Windsurf
Copilot
+ more