Faf Wizard

What it does

When your agent uses it

• Backend & APIs work in your project

Example prompts

• “/faf-wizard”

Requirements

• Python 3
• Node.js
• Docker

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1Detection (10 seconds)
2. 2Generation (30 seconds)
3. 3Scoring & Report (20 seconds)
4. 4Stack Detection
5. 5Context Mining
6. 6Optimization

What it can do on your machine

Read from SKILL.md and the folder at commit 2d14a69. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • npm
  • npx

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • faf.one

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Faf Wizard loads about 1.8k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 622 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~40

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from majiayu000/claude-skill-registry at commit 2d14a69, republished under its MIT licence (© majiayu000). 622 words, ~1,841 tokens.

name

faf-wizard

description

Done-for-you .faf generator. One-click AI context for any project - new, legacy, or famous. Auto-detects stack, scores readiness, works everywhere.

category

productivity

risk

safe

source

community

source_repo

Wolfe-Jam/faf-skills

source_type

community

date_added

2026-04-07

author

wolfejam

tags

faf, automation, project-setup, ai-context, productivity

tools

claude, cursor, gemini, windsurf, any-ai

Before: "This 50k-line PHP codebase from 2015..."
AI: "I don't understand this architecture"

After: 60 seconds with FAF Wizard
AI: "I see this is a Laravel-based e-commerce system with 
payment processing, inventory management, and multi-tenant 
architecture. Here's how I can help..."

Before: Every AI session starts with context explanation
Time lost: 5-10 minutes per session

After: project.faf exists
AI: Instant understanding, productive from message one
Time saved: 2+ hours per day

faf auto
# Scans manifest files, directory structure, dependencies
# Detects: React + TypeScript + Tailwind + Vercel

# Auto-generated project.faf
project:
  name: my-saas-dashboard  
  goal: Customer analytics platform

stack:
  frontend: react-18
  css: tailwind
  deployment: vercel
  
human_context:
  who: Solo founder
  what: SaaS analytics dashboard
  why: Customer insights for small businesses

✅ Generated: project.faf
🏆 AI-Readiness: 87% Bronze - Production ready

Filled: 9/11 active slots
Ignored: 22 slots (not applicable)

To reach Silver (95%):
  + Add API documentation (+5%)  
  + Define deployment details (+3%)

# Migrates existing context
faf migrate --from .cursorrules
faf migrate --from CLAUDE.md  
faf migrate --from README.md

# One format, works everywhere
faf sync --target all

npm install -g faf-cli
cd your-project
faf auto

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

# One command, done forever
npx faf-cli auto

# Check the results
cat project.faf

# Set up team-wide MCP server
faf mcp install --team
faf sync --target all --watch

© majiayu000, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/ai-llm/faf-wizard of majiayu000/claude-skill-registry.

• SKILL.md
• metadata.json

Open the folder on GitHubat commit 2d14a69

Used in 3 other repositories

We found 9 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in majiayu000/claude-skill-registry, which our catalogue first saw on October 7, 2026.

• sickn33/agentic-awesome-skillsskills/faf-wizardplugins/agentic-awesome-skills/skills/faf-wizard+1 more
• lingxling/awesome-skills-cnantigravity-awesome-skills/skills/faf-wizardantigravity-awesome-skills/plugins/agentic-awesome-skills/skills/faf-wizard+1 more
• henryalouf/ruflow.agents/skills/faf-wizardsrc/antigravity-awesome-skills/plugins/antigravity-awesome-skills/skills/faf-wizard+1 more