A unified development plugin for Claude Code with essential skills and specialized agents, all accessible under the ce namespace.
> /plugin marketplace add rileyhilliard/claude-essentials> /plugin install ce@claude-essentials
A unified development plugin for Claude Code with essential skills and specialized agents, all accessible under the ce namespace.
| Command | Description |
|---|---|
| /ce:setup | Bootstrap repo with .claude/ config (rules, permissions, settings) |
Reusable development patterns, accessed with ce: prefix:
Testing & Quality:
| Skill | Description |
|---|---|
| ce:writing-tests | Testing Trophy methodology, behavior-focused tests |
Debugging & Problem Solving:
| Skill | Description |
|---|---|
| ce:systematic-debugging | Four-phase debugging framework |
| ce:fixing-flaky-tests | Diagnose and fix tests that fail concurrently |
Code Quality:
| Skill | Description |
|---|---|
| ce:optimizing-performance | Measurement-driven optimization |
| ce:handling-errors | Error handling best practices |
Planning & Execution:
| Skill | Description |
|---|---|
| ce:planning-products | Product feature definition from a PM perspective |
| ce:executing-plans | Execute plans with mandatory code review |
| ce:architecting-systems | Clean, scalable system architecture for the build phase |
| ce:design | Frontend design skill |
Documentation & Writing:
| Skill | Description |
|---|---|
| ce:writer | Writing style guide with 9 personas (Architect, Engineer, PM, Marketer, Educator, Contributor, Outreach, UX Writer, Poster) |
| ce:structuring-articles | Professional journalistic story structures (WSJ Formula, Inverted Pyramid, Hourglass, etc.) |
| ce:strategy-writer | Executive-quality strategic documents in Economist/HBR style |
Data & Infrastructure:
| Skill | Description |
|---|---|
| ce:managing-databases | PostgreSQL, DuckDB, Parquet, and PGVector architecture |
| ce:managing-pipelines | GitHub Actions CI/CD security, performance, and deployment patterns |
Meta Skills:
| Skill | Description |
|---|---|
| ce:visualizing-with-mermaid | Create professional technical diagrams |
| ce:post-mortem | Review sessions to extract actionable improvements |
Expert AI personas for complex work, accessed with @ce: prefix:
| Agent | Description |
|---|---|
| @ce:code-reviewer | Comprehensive PR/MR reviews enforcing standards |
| @ce:log-reader | Efficient log file analysis using targeted search |
| @ce:devils-advocate | Rigorous critique to find flaws in plans and designs |
| @ce:copywriter | Articles and long-form content using journalistic frameworks |
You need Claude Code installed. If you don't have it yet, head to claude.com/product/claude-code.
/plugin marketplace add https://github.com/rileyhilliard/claude-essentials
/plugin install ce
That's it! You now have access to all skills and agents under the ce namespace.
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
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.
Fresh repositories (no .claude/ directory):
.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):
# Initialize a new project
/ce:setup
# Audit an existing configuration
/ce:setup --audit
# Force regenerate (overwrites existing)
/ce:setup --force
The generated configuration:
references/ subdirectories for domain-specific detailsuv, pytest; Node gets npm, bun, etc.rm -rf, force pushes, hard resetsProgressive 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.
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
Skills vs Agents:
ce:writing-tests) are reusable workflows that guide specific development patterns@ce:code-reviewer) are expert personas for complex, multi-step workUse skills for following proven patterns, and agents when you need specialized expertise.
All components are just markdown files organized in directories. Want to customize? Edit them directly in ~/.claude/plugins/ce/.
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.
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.
~/.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.)
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.
View @rileyhilliard’s profileRun your test suite on dedicated machines instead of your laptop, split across as many hosts as you have. rr syncs your working tree to one or more remote machines over rsync and SSH, runs a command there, and streams the output back.
@rileyhilliardclaude-essentials is a Claude Code plugin with 17 hand-picked skills, indexed on Flowy in the Development category. Install it with the command on its page. It includes architecting-systems, design, executing-plans. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it