faf-expert – skill Agent & Tự động hóa cho agent AI

FAF Expert - Advanced AI Context Architecture

Master the IANA-registered format that makes AI understand your projects.

Transform any codebase into an AI-intelligent project with persistent context that survives across sessions, tools, and AI platforms. Expert-level control over the foundational layer that powers modern AI development workflows.

When to Use This Skill

Use FAF Expert when you need:

| Scenario | What FAF Expert Provides |

|----------|---------------------------|

| Complex project setup | Expert configuration of .faf files and MCP servers |

| Championship scoring | Achieve 85%+ AI-readiness scores for production projects |

| Multi-AI workflows | Universal context that works across Claude, Cursor, Gemini, Windsurf |

| Legacy codebase revival | Transform archaeology into AI-readable project DNA |

| Team collaboration | Standardized context format for consistent AI assistance |

| Enterprise deployment | Professional MCP server configuration and management |

Real-World Examples

Example 1: Legacy Enterprise Java System

# Illustrative context; no score was measured here
project:
  name: enterprise-payment-api
  goal: Mission-critical payment processing system
  
stack:
  backend: java-spring
  database: oracle
  runtime: java-11
  deployment: kubernetes
  
human_context:
  where: AWS EKS production cluster
  when: Legacy system from 2018, modernizing 2026
  how: Spring Boot 2.7, Oracle 19c, Docker containerization

Example 2: Modern React Dashboard

# Illustrative context; no performance was measured here
project:
  name: analytics-dashboard
  goal: Real-time analytics for SaaS platform
  
stack:
  frontend: react-18
  css_framework: tailwind
  state: zustand
  build: vite
  testing: vitest
  deployment: vercel

Core Capabilities

🏆 Championship Scoring System

• Gold Tier (95%+): Upstream internal completeness label, not production certification
• Silver Tier (85%+): Professional development standard
• Bronze Tier (70%+): Solid foundation for AI assistance

🔧 MCP Server Configuration

Expert setup of claude-faf-mcp with 33 tools:

{
  "mcpServers": {
    "faf": {
      "command": "npx",
      "args": ["-y", "claude-faf-mcp@<reviewed-version>"]
    }
  }
}

🔄 Bi-Directional Sync

Keep context synchronized across platforms:

• .faf ↔ CLAUDE.md
• .faf ↔ .cursorrules
• .faf ↔ GEMINI.md
• .faf ↔ AGENTS.md

📊 Mk4 Architecture Framework

33-slot IANA format for comprehensive project context:

• Project identity and goals
• Technical stack detection
• Human context (who/what/why/where/when/how)
• Architecture patterns
• Deployment configuration

Getting Started

Review an exact CLI/MCP version and dependency/lifecycle/network behavior before installation. Back up and inspect exact changes before init/bi-sync/enhance/MCP configuration; do not overwrite existing agent instructions or send private context to a model without authorization. Named commands/tools are external prerequisites, not bundled.

Quick Installation

# Install FAF CLI
npm install -g faf-cli

# Initialize your project
faf init

# Score AI-readiness
faf score --details

# Set up MCP server
faf mcp install

Expert Commands

# Advanced scoring with breakdown
faf score --championship --verbose

# Multi-platform sync
faf bi-sync --target all

# Validate format compliance
faf validate --strict

# Enhanced AI optimization
faf enhance --model claude --focus completeness

Success Metrics

The upstream project reports adoption/tests/latency figures, but no measurement artifacts are bundled here. Do not repeat those numbers as verified. FAF scores are internal completeness heuristics, not production-readiness, security, compliance or model-quality certification. Example YAML values and achieved scores are illustrative, not executed results. The [IANA media-type registry](https://www.iana.org/assignments/media-types) lists application/vnd.faf+yaml; this registration does not validate performance or completeness claims.

Platform Compatibility

Supported AI Tools

• ✅ Claude Code - Native MCP integration
• ✅ Cursor - .cursorrules sync
• ✅ Gemini CLI - GEMINI.md sync
• ✅ Windsurf - .windsurfrules support
• ✅ Universal - Works with any AI that reads YAML

MCP Servers Available

• claude-faf-mcp - 33 tools, 391 tests
• grok-faf-mcp - xAI/Grok optimized
• rust-faf-mcp - Native performance (4.3MB binary)
• gemini-faf-mcp - Google Gemini integration

Advanced Patterns

Enterprise Configuration

faf_version: "3.0"
project:
  name: enterprise-platform
  tier: production
  
human_context:
  team_size: 50+
  compliance: SOC2, HIPAA
  deployment: multi-region
  
stack:
  architecture: microservices
  orchestration: kubernetes
  monitoring: datadog
  security: vault

Legacy System Revival

# Transform 10-year-old codebase to AI-ready
project:
  archaeology: true
  modernization_target: 2026
  
stack:
  legacy: php-5.6
  migration_path: laravel-11
  database_upgrade: mysql-8

Expert Resources

• Documentation: https://faf.one
• MCP Registry: Verify the current registry listing and maintainer identity; a listing is not endorsement
• CLI Reference: faf --help
• Community: Discord server with 1000+ developers
• Enterprise: Professional support available

When to Use faf-wizard Instead

Use faf-wizard for:

• ✅ Quick project setup
• ✅ One-click generation
• ✅ Beginner-friendly workflow
• ✅ Automated stack detection

Use faf-expert for:

• 🎯 Fine-tuned configuration
• 🎯 Championship scoring optimization
• 🎯 Multi-platform sync management
• 🎯 Enterprise deployment patterns
• 🎯 Advanced MCP server setup

---

*Master the format that makes AI understand your projects. FAF Expert - for when you need championship-grade AI context architecture.*

Limitations

• Use this skill only when the task clearly matches the scope described above.
• Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
• Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.