Claude Essentials

A unified development plugin for Claude Code with essential skills and specialized agents, all accessible under the ce namespace.

What’s Included

Commands

Skills

Reusable development patterns, accessed with ce: prefix:

Testing & Quality:

Debugging & Problem Solving:

Code Quality:

Planning & Execution:

Documentation & Writing:

Data & Infrastructure:

Meta Skills:

Agents

Expert AI personas for complex work, accessed with @ce: prefix:

---

Installation

Prerequisites

You need Claude Code installed. If you don’t have it yet, head to claude.com/product/claude-code.

Setup

1. Add this marketplace to Claude Code:

/plugin marketplace add https://github.com/rileyhilliard/claude-essentials

2. Install the ce plugin:

/plugin install ce

That’s it! You now have access to all skills and agents under the ce namespace.

Verify Installation

Start Claude Code and try these:

# Start Claude Code
claude

# Bootstrap a project
/ce:setup

# Use a skill
ce:writing-tests

# Use a skill
ce:architecting-systems

---

Bootstrapping Your Repository

The /ce:setup command (formerly /ce:init, renamed to avoid the built-in /init) sets up your repository with Claude Code configuration that follows best practices. On repos that already have a developed .claude/, it audits and summarizes instead of regenerating.

What It Does

Fresh repositories (no .claude/ directory):

1. Detects your project stack (Python, TypeScript, Rust, Go, etc.)
2. Generates a complete .claude/ configuration:

.claude/
├── CLAUDE.md           # Project overview, architecture, quick commands
├── settings.json       # Permissions tailored to your stack
└── rules/
    ├── testing.md          # References ce:writing-tests
    ├── error-handling.md   # References ce:handling-errors
    ├── debugging.md        # References ce:systematic-debugging
    └── {stack}/            # Stack-specific rules (python/, frontend/, etc.)

Existing configurations (.claude/ already exists):

1. Audits your current setup against best practices
2. If the config is already developed, summarizes it and stops with at most a few high-value suggestions
3. Otherwise identifies missing skill references, permission gaps, and rule improvements
4. Offers to apply fixes with your confirmation

Quick Start

# Initialize a new project
/ce:setup

# Audit an existing configuration
/ce:setup --audit

# Force regenerate (overwrites existing)
/ce:setup --force

Why This Matters

The generated configuration:

• Progressive disclosure - Rules stay concise (<100 lines), reference ce:* skills for depth, use references/ subdirectories for domain-specific details
• Rules reference ce:* skills - Don’t duplicate content, point to proven patterns
• Permissions are stack-aware - Python projects get uv, pytest; Node gets npm, bun, etc.
• Safety defaults included - Blocks rm -rf, force pushes, hard resets
• Path-scoped rules - Activate only when working in relevant files

Progressive disclosure structure:

rules/
├── testing.md              # ~50 lines, points to ce:writing-tests
└── api/
    ├── conventions.md      # ~100 lines, overview
    └── references/         # Loaded on-demand
        ├── errors.md       # Detailed error patterns
        └── pagination.md   # Pagination strategies

This keeps context small while maintaining depth. Claude loads reference files only when needed.

Based on Claude platform best practices.

---

Usage Examples

Typical Workflows

Bootstrap a new project:

cd my-project
/ce:setup
# Review the generated config, confirm, done

Fix failing tests:

ce:systematic-debugging

Plan and build a feature:

# Define the product spec first:
ce:planning-products
# Then execute:
ce:executing-plans

Clean up legacy code:

ce:refactoring-code

Understanding the System

Skills vs Agents:

• Skills (ce:writing-tests) are reusable workflows that guide specific development patterns
• Agents (@ce:code-reviewer) are expert personas for complex, multi-step work

Use skills for following proven patterns, and agents when you need specialized expertise.

Customization

All components are just markdown files organized in directories. Want to customize? Edit them directly in ~/.claude/plugins/ce/.

Creating Your Own Skill

Add a directory with SKILL.md to ~/.claude/plugins/ce/skills/:

---
name: my-skill
description: What this skill does and when to use it
---

# Skill Instructions

Your skill workflow here.

This will be accessible as ce:my-skill.

Creating Your Own Agent

Add a markdown file to ~/.claude/plugins/ce/agents/:

---
name: my-agent
description: Expert at specific domain
tools: Read, Grep, Glob, Bash
model: sonnet
effort: high
skills: skill-name-one, skill-name-two
color: blue
---

Your agent personality and workflow here.

Field order: name, description, tools, model, effort, skills, color. model is optional and, if omitted, the agent inherits the session model. effort (low|medium|high|xhigh|max) overrides session effort for the agent. skills lists skills the agent should have available.

This will be accessible as @ce:my-agent.

Project Structure

~/.claude/
├── CLAUDE.md              # Communication guidelines (copy here manually)
└── plugins/
    └── ce/
        ├── .claude-plugin/
        │   └── plugin.json       # Plugin metadata
        ├── commands/             # 1 command (/ce:setup)
        ├── skills/               # 17 skills (ce:writing-tests, ce:planning-products, etc.)
        └── agents/               # 4 agents (@ce:code-reviewer, @ce:log-reader, etc.)

Tips

Skills are for learning: Invoke a skill to understand a pattern, then apply it.

ce:writing-tests
# Follow the guidance to write tests

Agents need context: Give agents rich context for better results.

# Vague
ce:architecting-systems help with authentication

# Better
ce:architecting-systems We need OAuth2 + JWT authentication for a React SPA with Node backend. 50k users.

Documentation

• Extending for Projects - How to wrap and extend ce for your specific codebase

Contributing

Found a bug? Have an idea? Contributions welcome.

1. Fork this repo
2. Create a feature branch
3. Test your changes locally
4. Submit a PR with details

Ideas for contributions:

• Additional skills for specific patterns
• Specialized agents for other domains
• Documentation improvements

Resources

• Claude Code
• Claude API Docs
• Model Context Protocol

License

MIT - Use it, share it, make it better.