smithery/applied-artificial-intelligence

shared-setup-patterns

Shared configuration patterns for project setup commands. Provides security hooks, Claude framework structure templates, and framework detection patterns used across multiple setup commands.

Installation

$ npx skills add smithery/applied-artificial-intelligence --skill shared-setup-patterns

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from smithery/applied-artificial-intelligence.

npx skills add smithery/applied-artificial-intelligence

Browse all from smithery/applied-artificial-intelligence

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Skill metadata

Parsed from SKILL.md frontmatter.

Declared agents claude-code

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,751 B
  • docs SUMMARY.md 219 B

History

  1. First recorded snapshot · 0 installs

SKILL.md

Shared Setup Patterns

Purpose: Common configuration patterns and templates shared across all project setup commands.

Used by: /setup:python, /setup:javascript, /setup:existing, /setup:explore, /setup:user

Token Impact: Provides ~1,700 tokens of shared templates loaded once, avoiding duplication across 5+ commands (saves ~3,200 tokens through reuse).


Contents

This skill contains ONLY patterns shared by multiple setup commands:

  1. Security Hooks - PreToolUse and PostToolUse hooks for all project types
  2. Claude Framework Structure - .claude/ directory templates and memory files
  3. Framework Detection - Patterns for auto-detecting project languages and frameworks

Language-specific templates (Python, JavaScript, etc.) are kept inline in their respective commands.


1. Security Hooks

Located: templates/security_hooks.json

Comprehensive security and quality hooks configuration:

  • PreToolUse: Blocks dangerous commands (rm -rf, sudo, chmod 777)
  • PostToolUse: Auto-formats code (ruff, prettier, eslint), validates JSON/markdown

Used by: ALL setup commands that create projects


2. Claude Framework Structure

Located: templates/claude_framework/

Templates for .claude/ directory structure:

  • structure.md - Directory layout and purpose
  • memorytemplates/ - projectstate.md, dependencies.md, conventions.md, decisions.md
  • work_structure.md - Work directory organization

Used by: ALL setup commands


3. Framework Detection Patterns

Located: templates/framework_detection.md

Patterns for auto-detecting:

  • Languages: Python, JavaScript/TypeScript, Go, Rust
  • Frameworks: FastAPI, Django, Flask, Next.js, React, Express
  • Tools: pytest, Jest, Mocha, go test, cargo test

Used by: /setup:existing, /setup (if dispatcher exists)


Usage Pattern

Commands reference this skill in frontmatter:

skills: [shared-setup-patterns]

Then access specific templates:

  • Security hooks: Load from templates/security_hooks.json
  • Framework structure: Generate from templates/claude_framework/ templates
  • Detection: Use patterns from templates/framework_detection.md

Design Principle

Only truly shared content lives here. Language-specific templates (Python pyproject.toml, JavaScript package.json) stay inline in their respective commands to avoid skill overhead for single-use templates.

This keeps each command self-contained while sharing common infrastructure patterns.