MyClaude Studio Engine

The creation pipeline for Claude Code products.
_{Research what to build. Create it with structure. Validate quality. Publish to a marketplace.
One engine. Any expertise. No coding required.}

Install · Example · Build · Guides · Marketplace · FAQ

Thousands of Claude Code users build custom skills, agents, and tools every day.
But there is no standard for quality — no way to know if what you built is robust, no guided process to follow, and no easy way to share your work with others.

The Studio Engine is the missing creation pipeline.
It walks you from idea to published product: researching your domain, generating structure, guiding you through content, scoring quality against 20 structural patterns, and publishing to a marketplace where anyone can install your work with one command.

You don't need to write code. You need expertise worth packaging.

_{The myClaude Marketplace — where your products live.}

Install in 30 Seconds

myclaude studio

Don't have the CLI yet? npm i -g @myclaude-cli/cli — then run the command above.

Or clone directly: git clone https://github.com/myclaude-sh/myclaude-creator-engine && cd myclaude-creator-engine && claude

That's it. Open the folder in Claude Code and run /onboard — the engine adapts to you.

See It in Action

A Kubernetes security consultant used the engine to turn 15 years of expertise into an installable advisor — in one sitting:

/scout kubernetes-security

The engine tested what Claude already knows about K8s security, found 11 gaps
it can't cover alone, scanned the marketplace for existing tools, and
recommended building a cognitive mind.

/create minds

Generated a product structure with guided annotations — 7 sections,
each with context about what belongs there and why.

/fill

The engine asked targeted questions: "What's the first thing you check
in a cluster audit?" "Walk me through an attack path from exposed etcd."
The consultant answered. The engine wrote the structure.

/validate

Scored 100% — Elite quality. 20/20 structural patterns passing.
Attack-path reasoning, CIS benchmarks, hardening checklists — all verified.

/publish

Live on myclaude.sh. Anyone in the world can now run:
myclaude install k8s-security-advisor
and Claude Code gains deep K8s security expertise it doesn't have natively.

The consultant provided the expertise. The engine handled everything else.

✦ That's the thesis: Claude is powerful out of the box. But your Claude — augmented with real expertise — is something else entirely.

What You Can Build

Every product is self-contained — no engine dependency after install. Portable, yours, forever.

See more scenarios: Use Cases — lawyers, marketers, consultants, solo businesses, researchers.

Not sure what to build? Run /scout marketing-strategy (or any domain). The engine tests what Claude already knows, finds the gaps, and recommends exactly what to build. You start with intelligence, not guesswork.

How It Works

  research       create       refine       verify       ship
  /scout    →   /create  →   /fill   →  /validate →  /publish
                   │                        │
                   │    AI-guided filling    │  20 structural
                   │    with your expertise  │  quality patterns
                   └────────────────────────┘

v3.0.0 expanded validation from 7 stages to 10 — adding intent coherence (does the product match what the creator set out to build?), voice coherence (is the tone consistent?), and value intelligence (market positioning and pricing signals).

The engine asks the right questions. You provide the expertise. Each step feeds the next — scout research flows into /create, which generates structure for /fill, which produces content scored by /validate. Nothing is disconnected.

What Makes This Different

Other tools in the Claude Code ecosystem give you pre-built configurations — collections of skills, agents, and rules to install. They are warehouses of ready-made parts.

The Studio Engine is a factory. It helps you create your own.

No other tool in the ecosystem validates quality before publishing. Your products are verified, not just functional.

Quality You Can Measure

Every product is scored: (DNA x 0.50) + (Structural x 0.30) + (Integrity x 0.20)

20 structural patterns across 10 validation stages check for: activation protocols, error handling, anti-pattern guards, progressive disclosure, quality gates, graceful degradation, cache-friendly design, and more.

Run /validate at any time. The engine shows exactly what passes, what needs work, and how to fix it — with specific instructions, not vague suggestions.

The Ecosystem

         YOU                          ANYONE
          │                             │
     ┌────┴────┐                   ┌────┴────┐
     │  BUILD  │                   │ INSTALL  │
     │ Engine  │  ──── publish ──→ │   CLI    │
     │ /create │                   │ myclaude │
     │ /fill   │                   │ install  │
     │/validate│                   │          │
     └─────────┘                   └──────────┘
          │                             │
          └──── myclaude.sh ────────────┘
                marketplace

Products created by the engine use the Agent Skills format — YAML frontmatter with name, description, and constraints, followed by markdown instructions. This is the same SKILL.md format used natively by Claude Code and recognized by other AI coding tools that support structured skill definitions.

13 Product Types

Each type has specific structural DNA — patterns that ensure it works correctly, handles edge cases, and activates reliably.

Built on the Marketplace

Products created with the Studio Engine and published to myclaude.sh:

Browse all 39 products at myclaude.sh, or run /explore inside the engine.

Documentation

Requirements

• Claude Code — CLI, desktop app, or IDE extension
• MyClaude CLI — for publishing and marketplace access (npm i -g @myclaude-cli/cli)

Contributing

The engine improves through use. If something feels off — friction, confusion, a missing feature — that is valuable signal.

Contributions are welcome. See CONTRIBUTING.md for guidelines.

Ways to contribute:

• Friction reports from real usage — the most valuable contribution
• New product types with DNA spec, template, and exemplar
• New structural patterns with validation logic
• Documentation improvements and translations
• Bug fixes and quality improvements

License

MIT. See LICENSE.

Why This Exists

Every Claude Code user has a setup. Skills you've refined. Workflows you repeat. Knowledge you've encoded into prompts and rules over weeks of real work. That setup makes you powerful.

But it's trapped. In your machine, in your project, in your head. You can't score it. You can't share it. You can't install it somewhere else with one command. And the person next to you — the consultant, the researcher, the developer on another continent — is solving the same problem from scratch because your solution is invisible to them.

The Studio Engine exists to change that equation. To make every Claude Code setup shareable, every piece of expertise installable, every tool scorable before it ships. Not as a platform that owns your work — as a pipeline that packages it and gets out of the way.

The vision is simple: a world where Claude Code gets better every time someone publishes a product. Where a lawyer's contract review methodology becomes a tool any lawyer can install. Where a solo founder's operational playbook becomes a bundle that saves the next founder 10 hours a week. Where quality isn't a guess — it's a number.

Every feature came from a real need. The scoring exists because shipping without knowing if it's solid isn't shipping — it's hoping. The guided pipeline exists because a blank file is where good ideas go to die. The non-developer support exists because the deepest expertise doesn't come from people who write code — it comes from people who solve real problems every day and never had a way to package that.

This is built by a Claude Code user, with Claude Code, for Claude Code users. The entire engine was created using the same pipeline it teaches you to use. Dogfooding isn't a buzzword here — it's the architecture.

The marketplace is the multiplier. Every product published makes the ecosystem smarter. Every install makes someone's Claude Code more capable. Every creator who packages their expertise raises the floor for everyone. That's the game we're playing.

The name says it. myClaude — not the Claude, not a Claude. Yours. The moment you install a product that carries someone's real expertise, Claude stops being a generic AI and becomes something personal. Shaped by what you need. Augmented by what others know. That's the thesis: Claude is powerful out of the box, but your Claude — configured, specialized, extended with tools built by people who understand your domain — that's something else entirely.

Acknowledgments

This is an independent, community-driven project. It is not affiliated with or endorsed by Anthropic. The engine creates products that work with Claude Code — Anthropic's official coding tool — but is not made by Anthropic.

Built with respect for the ecosystem and the developers, researchers, consultants, and creators who push Claude Code further every day.

_{Every Claude Code user deserves to operate at the apex of what the tool can do.
Some build tools, some install tools, most do both. The marketplace is the bridge.}

myclaude.sh