AGENT SKILL

faf-expert

Advanced .faf (Foundational AI-context Format) specialist. IANA-registered format, MCP server config, championship scoring, bi-directional sync.

License 许可
MIT
最近更新
2026-11-10
Stars
★ 1
Forks
0

01 前言 Front Matter

name
faf-expert
risk
safe
tags
[ "faf", "ai-context", "project-management", "mcp", "iana" ]
tools
[ "claude", "cursor", "gemini", "windsurf" ]
author
wolfejam
source
community
category
coding
date_added
2026-04-07
description
Advanced .faf (Foundational AI-context Format) specialist. IANA-registered format, MCP server config, championship scoring, bi-directional sync.
source_repo
Wolfe-Jam/faf-skills
source_type
community

03 SKILL.md 正文

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

# Achieved: 92% Gold tier with FAF Expert
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

# Achieved: 97% Gold tier performance
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%+): Production-ready AI context
  • 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@latest"]
    }
  }
}

🔄 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

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

Real Performance Data:

  • 52k+ downloads across FAF ecosystem
  • 800+ comprehensive tests (CLI + MCP)
  • IANA-registered format (application/vnd.faf+yaml)
  • 153+ validated formats supported
  • Championship-grade performance (<50ms execution)

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: Official Anthropic steward
  • 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.

04 同仓库更多 Skills

YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

vercel-sandbox

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

slack

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

electron

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.

★ 1