agentleFS
Wolfe-JamWolfe-Jam/grok-faf-mcp/skill/SKILL.md

faf-expert

Skill19 starsChanged 10 months agoMITView on GitHub

Expert in .faf (Foundational AI-context Format) files for persistent project context. Use when working with .faf files, project DNA, syncing project.faf into CLAUDE.md, faf-cli commands, MCP server configuration, or AI-readiness scoring (0-100%). Updated for v2.8.0 Tool Visibility System.

  • Installs packages

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. Wolfe-Jam/faf-cli★ 44same name
    2. Wolfe-Jam/faf-skills★ 4same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use faf sync: - Write CLAUDE.md from .faf after each change

    line 134
  2. Distinctive:

    NO BS ZONE: - Only real stats, verified claims

    line 233
  3. Distinctive:

    All tests reported and documented

    line 273

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

FAF Expert - Project DNA Specialist

What is .faf?

.faf is the universal format for persistent AI project context - "Project DNA ✨ for ANY AI".

Core Concepts:

  • Foundational AI-context Format - YAML-based project context file
  • Persistent Context - Survives across sessions, tools, and AI assistants
  • Universal - Works with Claude, ChatGPT, Gemini, Cursor, any AI
  • Measurable - Championship scoring system (0-100% AI-readiness)
  • Official Anthropic MCP Steward - PR #2759 MERGED

When to Use This Skill

Activate this skill when:

  • Creating or updating .faf files
  • Working with CLAUDE.md files
  • Running faf CLI commands (init, auto, score, formats, sync)
  • Scoring project AI-readiness
  • Setting up MCP server (claude-faf-mcp)
  • Configuring tool visibility (v2.8.0+)
  • Discussing project context or documentation

Key Files

  • .faf - YAML format, machine-readable project context
  • CLAUDE.md - Markdown format, human-readable project guide
  • Sync - faf sync writes CLAUDE.md from .faf (one way; .faf is the source)
  • project.faf - v1.2.0 standard naming

Common Commands

faf-cli Commands

faf init              # Create .faf from project
faf auto              # Auto-detect stack and create .faf
faf score             # Rate AI-readiness (0-100%)
faf formats           # List 153+ supported formats
faf sync              # Write CLAUDE.md from .faf (one way)
faf status            # Check project AI-readiness
faf validate          # Validate .faf structure
faf doctor            # Diagnose and fix issues
faf migrate           # Migrate to latest format

MCP Tools (claude-faf-mcp v2.8.0+)

v2.8.0 introduces Tool Visibility System:

  • 21 Core Tools (default) - Essential workflow
  • 51 Total Tools (opt-in) - All features

Configuration:

{
  "mcpServers": {
    "faf": {
      "command": "npx",
      "args": ["-y", "claude-faf-mcp@2.8.0"],
      "env": {
        "FAF_MCP_SHOW_ADVANCED": "false"
      }
    }
  }
}

Core Tools (21):

  • Essential Workflow: faf, faf_auto, faf_init, faf_innit, faf_status
  • Quality: faf_score, faf_validate, faf_doctor, faf_audit
  • Intelligence: faf_formats, faf_stacks, faf_skills
  • Sync: faf_sync (old name faf_bi_sync still works), faf_update, faf_migrate
  • AI: faf_chat
  • Help: faf_index, faf_faq, faf_about

Advanced Tools (30+): Set FAF_MCP_SHOW_ADVANCED: "true" to enable:

  • Display variants: faf_display, faf_show, faf_check
  • Trust system: faf_trust, faf_trust_confidence, faf_trust_garage
  • File operations: faf_read, faf_write, faf_list, faf_exists, etc.
  • DNA tracking: faf_dna, faf_log, faf_auth, faf_recover
  • Utilities: faf_choose, faf_clear, faf_share, faf_credit

AI-Readiness Scoring

Championship Tiers:

  • 🏆 95-100% - Championship (Gold)
  • 🥇 85-94% - Podium (Silver)
  • 🥈 70-84% - Points (Bronze)
  • 🥉 55-69% - Midfield
  • 🟢 40-54% - Backmarker
  • 🟡 25-39% - Struggling
  • 🔴 10-24% - Critical
  • 🤍 0-9% - DNF (Did Not Finish)

Target: 85%+ for production projects

.faf File Structure

# Basic .faf structure
format: typescript-nextjs
language: typescript
framework: nextjs
version: "14.0.0"

structure:
  - src/
  - components/
  - pages/

dependencies:
  react: "^18.0.0"
  next: "^14.0.0"

testing: jest
deployment: vercel

# v1.2.0+ additions
project_name: "My Project"
ai_readiness_score: 87

Best Practices

  1. Start with faf auto - Let it detect your stack
  2. Review and refine - Auto-detection is 85% accurate, tweak as needed
  3. Run faf score - Target 85%+ for championship context
  4. Use faf sync - Write CLAUDE.md from .faf after each change
  5. Update regularly - As project evolves, update context
  6. Use core tools first - Advanced tools are opt-in for specific needs

The FAF Family

6 Championship Integrations:

  • React (20M/week npm downloads) 🏆
  • TypeScript (40M/week) 🏆
  • Next.js (5M/week) 🏆
  • Vite (9M/week) 🥇
  • Svelte (400K/week) 🥇
  • n8n (401K/week - TURBO only) 🥇

Installation

faf-cli (npm)

npm install -g faf-cli

faf-cli (Homebrew)

brew install faf-cli

claude-faf-mcp (MCP Server)

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "faf": {
      "command": "npx",
      "args": ["-y", "claude-faf-mcp@latest"]
    }
  }
}

For advanced tools:

{
  "mcpServers": {
    "faf": {
      "command": "npx",
      "args": ["-y", "claude-faf-mcp@latest"],
      "env": {
        "FAF_MCP_SHOW_ADVANCED": "true"
      }
    }
  }
}

v2.8.0 Tool Visibility System

Problem Solved: Reduced cognitive load from 51 tools to 21 core tools.

How It Works:

  • Default: Shows 21 essential tools
  • Opt-in: Enable all 51 tools via environment variable
  • Smart Filtering: Tools categorized by purpose
  • Backward Compatible: Existing setups continue working

Categories:

  • workflow - Essential commands
  • quality - Scoring and validation
  • intelligence - Format/stack detection
  • sync - Context synchronization
  • ai - AI enhancement features
  • help - Documentation
  • trust - Trust validation
  • file - File operations
  • utility - Misc tools

Configuration Priority:

  1. Environment variable (FAF_MCP_SHOW_ADVANCED)
  2. Config file (~/.fafrc)
  3. Default (core only)

Philosophy

The Noodle Philosophy 🍜

  • YAML noodles for AI (machine-readable)
  • Converts to markdown/TXT for humans (human-readable)
  • Interconnected context, not flat data

Format-First

  • The format is the foundation
  • Without .faf, there is no universal context
  • Format-driven architecture

Official Stewardship

  • Anthropic-approved MCP server (PR #2759 MERGED)
  • Account Managers for all things .FAF in Anthropic ecosystem
  • Governance responsibility for format specification

Brand Values

  • NO BS ZONE - Only real stats, verified claims
  • Championship Standards - <50ms performance, 1,000+ tests
  • Free Forever - MIT license, open source
  • Trust is Everything - Built on credibility
  • Professional, Boring, Trusted - F1-grade engineering

Stats (Real, Verified - November 2025)

  • 11,000+ total downloads (CLI + MCP combined)
  • 5,000+ MCP downloads (weekly: 800+)
  • 6,000+ CLI downloads
  • 79 tests passing (57 MCP + 22 visibility)
  • 153+ formats validated (TURBO-CAT engine)
  • <10ms tool filtering (5x better than 50ms target)
  • Zero regressions in v2.8.0 release
  • WJTTC Gold Certified - F1-inspired testing standards
  • Anthropic-approved MCP server (Official steward)

Version History

  • v3.1.1 - faf-cli latest
  • v2.8.0 - MCP Tool Visibility System (CURRENT)
  • v2.7.3 - Previous MCP stable
  • v1.2.0 - project.faf standard naming

Resources

Testing Standards

WJTTC (WolfeJam Technical & Testing Center)

  • F1-Inspired testing methodology
  • 3 Tiers: Brake Systems, Engine Systems, Aerodynamics
  • Philosophy: "We break things so others never have to know they were broken"
  • All tests reported and documented
  • Gold certification for production releases

Troubleshooting

MCP Server Not Loading

# Check logs
tail -f ~/Library/Logs/Claude/mcp-server-claude-faf-mcp.log

# Verify config
cat ~/Library/Application\ Support/Claude/claude_desktop_config.json

# Test locally
node /path/to/claude-faf-mcp/dist/src/index.js

Tool Count Verification

# Should show 21 core tools (default)
# Or 51 tools (advanced mode)
# Check console output when MCP loads

CLI Not Found

# Install globally
npm install -g faf-cli

# Or via Homebrew
brew install faf-cli

# Verify installation
faf --version

Advanced Usage

Custom Config File

Create ~/.fafrc:

{
  "showAdvanced": true
}

Or key=value format:

FAF_SHOW_ADVANCED=true

Local Development

# Use local build
{
  "mcpServers": {
    "faf": {
      "command": "node",
      "args": ["/path/to/claude-faf-mcp/dist/src/index.js"],
      "env": {
        "FAF_MCP_SHOW_ADVANCED": "false"
      }
    }
  }
}

Skill Control

To disable this skill temporarily:

# Rename directory to disable
mv ~/.claude/skills/faf-expert ~/.claude/skills/faf-expert.disabled

To re-enable:

# Rename back to enable
mv ~/.claude/skills/faf-expert.disabled ~/.claude/skills/faf-expert

Or just delete the directory to remove completely.


How to Get This Skill

Option 1: Manual Installation

  1. Copy this SKILL.md file
  2. Create directory: ~/.claude/skills/faf-expert/
  3. Save as: ~/.claude/skills/faf-expert/SKILL.md
  4. Restart Claude Code

Option 2: Git Clone (if published)

# Coming soon - published skills repository
git clone [skills-repo] ~/.claude/skills/faf-expert

Option 3: From FAF CLI (future)

# Planned feature
faf skill install faf-expert

Made with 🧡 by wolfejam.dev Official Anthropic MCP Steward Championship Edition v2.8.0 🏎️✨ IANA-Registered Format: application/vnd.faf+yaml

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.