SkillAgentSearch skills...

AIBoilerplate

Universal Context Architecture. One source of truth for Cursor, Claude Code, GitHub Copilot, Gemini, Amazon Q, and 19+ AI coding assistants.

GenerateConvertImprove

Install / Use

/learn @yokharian/AIBoilerplate
About this skill

Quality Score

0/100

Supported Platforms

Claude Code
Claude Desktop
GitHub Copilot
Cursor
Gemini CLI

README

<div align="center"> <img src="https://img.shields.io/badge/AI_Agents-19+-blueviolet?style=for-the-badge" alt="19+ AI Agents" /> <img src="https://img.shields.io/badge/Zero_Drift-100%25-success?style=for-the-badge" alt="Zero Drift" /> <img src="https://img.shields.io/badge/Config_Files-1_Hub-orange?style=for-the-badge" alt="1 Hub" />

🤖 Universal Context Architecture

Stop "Context Drift" in Multi-Agent AI Teams

<br />

Use this template

<br />

One source of truth for Cursor, Claude Code, GitHub Copilot, Gemini, Amazon Q, and 14+ AI coding assistants.

<br />

Quick Start · How It Works · Supported Tools · Customize

</div> <br />
<br />

🤔 The Problem

We're in the era of Multi-Vendor AI Development. Your team might be using:

<table> <tr> <td align="center">🖱️<br/><b>Cursor</b></td> <td align="center">🤖<br/><b>Claude Code</b></td> <td align="center">🐙<br/><b>GitHub Copilot</b></td> <td align="center">💎<br/><b>Gemini CLI</b></td> <td align="center">☁️<br/><b>Amazon Q</b></td> <td align="center">➕<br/><b>14 more...</b></td> </tr> </table> <br />

The catch? Every tool has its own config file. They all drift apart over time.

😵 Before: Chaos
┌─────────────┐  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐
│ .cursorrules│  │  CLAUDE.md  │  │  GEMINI.md  │  │ copilot.md  │
│   v1.2      │  │   v1.5      │  │   v1.0      │  │   v1.3      │
│  (outdated) │  │  (current)  │  │  (wrong)    │  │  (missing)  │
└─────────────┘  └─────────────┘  └─────────────┘  └─────────────┘
      ↓                ↓                ↓                ↓
   Different        Different        Different        Different
   conventions      conventions      conventions      conventions

You end up with duplicated rules, conflicting instructions, and AI assistants that hallucinate different project conventions.

<br />
<br />

💡 The Solution

Governor & Consumer Pattern

Instead of maintaining 19 different config files, use a hub-and-spoke architecture:

✨ After: Harmony
                         ┌─────────────────────┐
                         │     AGENTS.md       │
                         │     (The Hub)       │
                         │  Single Source of   │
                         │      Truth          │
                         └──────────┬──────────┘
                                    │
           ┌────────────┬───────────┼───────────┬────────────┐
           │            │           │           │            │
           ▼            ▼           ▼           ▼            ▼
     .cursorrules  CLAUDE.md   GEMINI.md   copilot.md    19 more...
        │            │           │           │            │
        └────────────┴───────────┴───────────┴────────────┘
                                 │
                      "Read AGENTS.md first"

Every vendor-specific config contains just one instruction:

"System: Read /AGENTS.md before doing anything."

<br />
<br />

🗂️ Architecture

📁 Your Project
│
├── 🎯 AGENTS.md                      ← THE HUB: Entry point for all AI agents
│
├── 📂 .agents/
│   │
│   ├── 📚 skills/                ← KNOWLEDGE (Atomic, Reusable)
│   │   ├── create-prd/
│   │   │   └── SKILL.md             "Create Product Requirements Documents"
│   │   └── generate-tasks/
│   │       └── SKILL.md             "Generate task lists from PRDs"
│   │
│   └── 🎭 sub-agents/            ← PERSONAS (Specialized Roles)
│       ├── ultra-think.md           "Default for all SDLC tasks"
│       └── project-manager.md       "I am the Project Manager"
│
├── 📂 .specify/
│   │
│   ├── 📂 memory/               ← GOVERNANCE (The Law)
│   │   ├── constitution.md          Tech Stack & Rules
│   │   └── plan.md                  Current Tasks & Sprint
│   │
│   └── 📂 features/            ← FEATURE DOCUMENTATION
│       └── 📂 [feature-name]/
│           ├── prd.md               Product Requirements Document
│           └── tasks.md             Task list for implementation
│
└── 📂 [Pointer Files]            ← REDIRECTORS (Thin Wrappers)
    ├── .cursorrules                 → "Read AGENTS.md"
    ├── CLAUDE.md                    → "Read AGENTS.md"
    ├── GEMINI.md                    → "Read AGENTS.md"
    └── ... (19 total)               → "Read AGENTS.md"
<br />
<br />

🚀 Quick Start

<table> <tr> <td>

Step 1️⃣   Use This Template

Click the button below to create your own copy:

Use this template

</td> </tr> <tr> <td>

Step 2️⃣   Define Your Constitution

Edit .specify/memory/constitution.md:

# Your Tech Stack
Frontend: React 18 + TypeScript + Tailwind
Backend:  Node.js + Express + Prisma
Database: PostgreSQL
Cloud:    AWS

# Your Rules
- TypeScript everywhere, no `any`
- All functions must be documented
- Tests required for new features
</td> </tr> <tr> <td>

Step 3️⃣   Set Your Plan

The project-manager sub-agent automatically maintains .specify/memory/plan.md as you work through features. However, you can also manually edit it to set initial sprint goals:

## Current Sprint: User Authentication

### In Progress
- [ ] Implement OAuth2 flow
- [ ] Add password reset

### Up Next
- [ ] Two-factor authentication

Note: When you create PRDs and generate tasks using the project-manager sub-agent, it will automatically update this plan file with progress, moving tasks between sections and updating metrics as work progresses.

</td> </tr> <tr> <td>

Step 4️⃣   Start Coding

Open your project in any AI-powered IDE. The AI will automatically:

  1. 📖 Read the pointer file (.cursorrules, CLAUDE.md, etc.)
  2. 🎯 Navigate to AGENTS.md
  3. 📜 Load your constitution and plan
  4. ✅ Follow your rules consistently
</td> </tr> </table> <br />
<br />

Feature Development Workflow

Build features step-by-step with AI: define requirements, plan tasks, and implement iteratively.

Quick Guide

1. Create a PRD (Product Requirements Document)

Use @.agents/sub-agents/project-manager.md
I want to build a feature: [Describe your feature]

The PRD is saved to .specify/features/[feature-name]/prd.md.

2. Generate Tasks

Take @.specify/features/my-feature/prd.md and generate tasks using @.agents/skills/generate-tasks/SKILL.md

Tasks are saved to .specify/features/[feature-name]/tasks.md.

3. Implement Tasks

Please start on task 1.1 from @.specify/features/my-feature/tasks.md

The AI will implement one task at a time. Review and approve each change before moving to the next task.

4. Track Progress

Tasks are automatically marked complete, and .specify/memory/plan.md updates automatically.

Tips

  • Be specific when describing features
  • Use project-manager for planning, ultra-think (default) for coding
  • Review each task before approving the next one
<br />
<br />

🔌 Supported AI Tools

<div align="center">

| IDE / CLI | Config File | Status | |:--------------------:|:---------------------------------:|:------:| | Cursor | .cursorrules | ✅ | | Windsurf | .windsurfrules | ✅ | | Roo Code / Cline | .clinerules | ✅ | | GitHub Copilot | .github/copilot-instructions.md | ✅ | | Claude Code | CLAUDE.md | ✅ | | Gemini CLI | GEMINI.md | ✅ | | Amazon Q | AMAZON_Q.md | ✅ | | Auggie CLI | .auggie.md | ✅ | | CodeBuddy | .codebuddy | ✅ | | Qoder | .qoder/context.md | ✅ | | OpenCode | .opencode | ✅ | | Amp | .amp.md | ✅ | | Kilo Code | .kilo | ✅ | | Qwen Code | .qwen | ✅ | | IBM Bob | .bob/config | ✅ | | Jules | .jules | ✅ | | SHAI | .shai | ✅ | | Codex CLI | CODEX.md | ✅ | | Goose | goosehints | ✅ |

</div> <br />
<br />

🧠 How It Works

<table> <tr> <th width="33%">📚 Skills</th> <th width="33%">🎭 Sub-Agents</th> <th width="33%">📜 Governance</th> </tr> <tr> <td valign="top">

Atomic knowledge modules

Each skill is a reusable piece of domain knowledge.

create-prd/
├─ PRD structure
├─ Clarifying questions
└─ Requirements format

generate-tasks/
├─ Task breakdown
├─ Sub-task generation
└─ Progress tracking
</td> <td valign="top">

Specialized personas

Sub-agents are experts that use specific skills.

ultra-think.md (default)
├─ Focus: SDLC tasks
├─ Coding, refactoring
├─ Architecture, debugging
└─ Testing, craftsmanship

project-manager.md
├─ Uses: create-prd
├─ Uses: generate-tasks
└─ Focus: Feature development
</td> <td valign="top">

The source of truth

Constitution = the law Plan = current state

memory/
├─ constitution.md
│  └─ "Never ignore me"
└─ plan.md
   └─ "Here's what we're doing"
</td> </tr> </table> <br />
<br />

✨ Before vs After

<table> <tr> <th>😵 Before</th> <th>✨ After</th> </tr> <tr> <td>

❌ 19 config files to maintain

yokharian

View profile

View on GitHub
GitHub Stars32
CategoryDevelopment
Updated2mo ago
Forks8
yokharian/AIBoilerplate

Security Score

90/100

Audited on Jan 19, 2026

No findings