πŸš€ Big News:Socket Has Acquired Secure Annex.Learn More β†’
Socket
Book a DemoSign in
Socket

claude-useful-skills

Package Overview
Dependencies
Maintainers
1
Versions
2
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

claude-useful-skills

A collection of useful skills for Claude Code CLI

latest
Source
npmnpm
Version
1.0.1
Version published
Maintainers
1
Created
Source

Claude Useful Skills

A collection of useful skills for Claude Code CLI

Version Claude Code License Languages

Overview

This repository contains 5 skills for Claude Code that I built for my own use and decided to share. They work together as an integrated development ecosystem and help with project management, AI agent design, ML/DL work, prompt engineering, and logo design.

Skills Included

SkillDescriptionUse When
gsd-orchestrationSpec-driven development with context engineeringProjects > 2 hours, multiple features
agent-architectBuild AI agent systems with structured interviewsCreating multi-agent systems
ml-dl-skills17 specialized ML/DL sub-skillsAny machine learning project
prompt-masterProfessional prompt engineeringNeed optimized prompts
svg-logo-designerCreate professional SVG logosBrand identity, logos

Quick Start

npx claude-useful-skills

That's it! All 5 skills will be installed to your ~/.claude/skills/ directory.

Alternative: PowerShell Installation

# Clone the repository
git clone https://github.com/NatiLevyy/claude-useful-skills.git

# Run the installer
cd claude-useful-skills
.\scripts\install.ps1

Manual Installation

# Copy skills to your Claude Code skills directory
xcopy /E /I "skills\*" "%USERPROFILE%\.claude\skills\"

Verify Installation

# In Claude Code, test a skill
/gsd status

Integration Map

The skills are designed to work together seamlessly:

                    β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
                    β”‚  prompt-master  β”‚
                    β”‚  Creates Promptsβ”‚
                    β””β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                             β”‚
                             β–Ό
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”    β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”    β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚ svg-logo-design β”‚    β”‚ agent-architect │◄───│ gsd-orchestrat. β”‚
β”‚   SVG Output    β”‚    β”‚   AI Systems    β”‚    β”‚   Orchestration β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜    β””β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”˜    β””β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                β”‚                      β”‚
                                β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                           β–Ό
                                β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
                                β”‚    ml-dl-skills     β”‚
                                β”‚   17 Sub-skills     β”‚
                                β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

Key Integration Points

  • gsd-orchestration ↔ agent-architect: During gsd discuss, architecture interview is offered
  • gsd-orchestration ↔ ml-dl-skills: Auto-detection of ML/DL projects
  • prompt-master ↔ agent-architect: Creates prompts for multi-agent systems
  • prompt-master ↔ gsd-orchestration: Full project prompt workflows

See docs/INTEGRATION-MAP.md for detailed integration documentation.

Skill Highlights

gsd-orchestration (v2.0.0)

  • 11 subcommands for complete project lifecycle
  • Context engineering prevents context rot
  • Atomic task execution with verification
  • Python validation scripts included

agent-architect (v1.0.0)

  • 5-phase architectural interview process
  • Code templates for all agent patterns
  • Guardrails and monitoring included
  • Ralph Command Center integration

ml-dl-skills (v1.0.0)

  • 17 specialized sub-skills covering:
    • Fundamentals, PyTorch, NLP, Vision
    • Transformers, RAG, Fine-tuning
    • Generative AI, Reinforcement Learning
    • MLOps, Model Interpretability
  • Hebrew + English support

prompt-master (v1.0.0)

  • 5-phase prompt engineering process
  • 12+ techniques with selection matrix
  • 4 framework templates (CO-STAR, RISEN, XML-First, Mega-Prompt)
  • 10-point quality evaluation rubric

svg-logo-designer (v1.0.0)

  • 7-phase design workflow
  • Color psychology guide
  • Multiple templates (Full, Quick, Hebrew)
  • 30-75 SVG files per project

Documentation

Mastery Guides (Get Maximum Value)

Examples

See the examples/ directory for complete working projects:

  • gsd-todo-api/ - Complete GSD project structure example
  • research-agent-system/ - Multi-agent system built with agent-architect

Requirements

  • Claude Code CLI installed and authenticated
  • Windows 10/11, macOS 10.15+, or Linux
  • Python 3.8+ (for validation scripts)

Contributing

See CONTRIBUTING.md for guidelines on how to contribute.

License

MIT - see LICENSE

Support

Made with Claude Code

Keywords

claude

FAQs

Package last updated on 04 Feb 2026

Did you know?

Socket

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Install

Related posts