FAF Expert - Advanced AI Context Architecture

Overview

This public intake copy packages

plugins/antigravity-awesome-skills-claude/skills/faf-expert

https://github.com/sickn33/antigravity-awesome-skills

Use it when the operator needs the upstream workflow, support files, and repository context to stay intact while the public validator and private enhancer continue their normal downstream flow.

This intake keeps the copied upstream files intact and uses

metadata.json

ORIGIN.md

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.

Imported source sections that did not map cleanly to the public headings are still preserved below or in the support files. Notable imported sections: Core Capabilities, Getting Started, Success Metrics, Platform Compatibility, Advanced Patterns, Limitations.

When to Use This Skill

Use this section as the trigger filter. It should make the activation boundary explicit before the operator loads files, runs commands, or opens a pull request.

• 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

Operating Table

metadata.json

ORIGIN.md

SKILL.md

SKILL.md

## Related Skills

Workflow

This workflow is intentionally editorial and operational at the same time. It keeps the imported source useful to the operator while still satisfying the public intake standards that feed the downstream enhancer flow.

1. Confirm the user goal, the scope of the imported workflow, and whether this skill is still the right router for the task.
2. Read the overview and provenance files before loading any copied upstream support files.
3. Load only the references, examples, prompts, or scripts that materially change the outcome for the current request.
4. Execute the upstream workflow while keeping provenance and source boundaries explicit in the working notes.
5. Validate the result against the upstream expectations and the evidence you can point to in the copied files.
6. Escalate or hand off to a related skill when the work moves out of this imported workflow's center of gravity.
7. Before merge or closure, record what was used, what changed, and what the reviewer still needs to verify.

Imported Workflow Notes

Imported: 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

Examples

Example 1: Ask for the upstream workflow directly

Use @faf-expert to handle <task>. Start from the copied upstream workflow, load only the files that change the outcome, and keep provenance visible in the answer.

Explanation: This is the safest starting point when the operator needs the imported workflow, but not the entire repository.

Example 2: Ask for a provenance-grounded review

Review @faf-expert against metadata.json and ORIGIN.md, then explain which copied upstream files you would load first and why.

Explanation: Use this before review or troubleshooting when you need a precise, auditable explanation of origin and file selection.

Example 3: Narrow the copied support files before execution

Use @faf-expert for <task>. Load only the copied references, examples, or scripts that change the outcome, and name the files explicitly before proceeding.

Explanation: This keeps the skill aligned with progressive disclosure instead of loading the whole copied package by default.

Example 4: Build a reviewer packet

Review @faf-expert using the copied upstream files plus provenance, then summarize any gaps before merge.

Explanation: This is useful when the PR is waiting for human review and you want a repeatable audit packet.

Imported Usage Notes

Imported: 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

Best Practices

Treat the generated public skill as a reviewable packaging layer around the upstream repository. The goal is to keep provenance explicit and load only the copied source material that materially improves execution.

• Keep the imported skill grounded in the upstream repository; do not invent steps that the source material cannot support.
• Prefer the smallest useful set of support files so the workflow stays auditable and fast to review.
• Keep provenance, source commit, and imported file paths visible in notes and PR descriptions.
• Point directly at the copied upstream files that justify the workflow instead of relying on generic review boilerplate.
• Treat generated examples as scaffolding; adapt them to the concrete task before execution.
• Route to a stronger native skill when architecture, debugging, design, or security concerns become dominant.

Troubleshooting

Problem: The operator skipped the imported context and answered too generically

Symptoms: The result ignores the upstream workflow in

plugins/antigravity-awesome-skills-claude/skills/faf-expert

metadata.json

ORIGIN.md

Problem: The imported workflow feels incomplete during review

Symptoms: Reviewers can see the generated

SKILL.md

Problem: The task drifted into a different specialization

Symptoms: The imported skill starts in the right place, but the work turns into debugging, architecture, design, security, or release orchestration that a native skill handles better. Solution: Use the related skills section to hand off deliberately. Keep the imported provenance visible so the next skill inherits the right context instead of starting blind.

Related Skills

• @devops-deploy

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

• @devops-troubleshooter

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

• @differential-review

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

• @discord-automation

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

Additional Resources

Use this support matrix and the linked files below as the operator packet for this imported skill. They should reflect real copied source material, not generic scaffolding.

references

references/n/a

examples

examples/n/a

scripts

scripts/n/a

agents

agents/n/a

assets

assets/n/a

Imported Reference Notes

Imported: 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

Imported: 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

Imported: 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)

Imported: 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

Imported: 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

Imported: 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.