teccon forum

rules-practice

2 min read

AIへのルール 実践

Rules

  • app_flow_document.mdc

  • tech_stack_document.mdc

  • frontend_guidelines_document.mdc ⇒ styling, component rules

  • backend_structure_document.mdc ⇒ API patterns, DB queries

  • cursor_project_rules.mdc ⇒ global coding standards

  • implementation_plan.mdc ⇒ step-by-step instructions

  • A complete PRD

  • Detailed App Flow

  • Tech Stack + API usage

  • Design System (fonts, layout, spacing)

  • Auth, DB, and backend setup

  • A 50-step Implementation Plan

Diffrences between Models

Gemini 2.5 Pro:

  • Scan full codebase (1M context)
  • Catch issues
  • Update .mdc docs

Claude Sonnet 3.5 / 3.7:

  • Execute features
  • Fix logic
  • Build from the implementation plan

Reusable prompt: “Follow Step 1 from the plan.”

Cursor can now:

  • Connect to Supabase

  • Create + modify tables

  • Apply policies

  • Sync local + remote DBs

  • CodeGuide ⇒ generates your AI Knowledge Base

  • .cursor/rules/*.mdc ⇒ context boundary

  • Gemini 2.5 ⇒ scan + update

  • Sonnet 3.5/3.7 ⇒ execute + debug

  • Cursor Agent ⇒ follow the plan

  • Supabase MCP ⇒ automate backend

  • Vercel ⇒ deploy in 1 click

  • Planning > prompting.

  • Context > guessing.

  • Execution > exploration.

Examples

Design the definition of requirements of this project into `.idea/` folder.

The documents:
- app_flow.mdc
- tech_stack.mdc
- frontend_guidelines.mdc ==> styling, component rules
- backend_structure.mdc ==> API patterns, DB queries
- project_rules.mdc ==> global coding standards
- implementation_plan.mdc ==> step-by-step instructions

Take the best practices, upgraded resolution for each integration, better understanding for to the next level highly detailed use-case. then start building as a enhanced YAML, as an expert with over 100k tokens. no need to include an obvious description of existing services, no comment needed, but more detailed configuration instead.

Graph View