Skip to main content
πŸŽ“ Claude Code Masterclass Learn AI-assisted development on Udemy β€” plus the companion book on Leanpub & Amazon. Start Learning
Garry Tan gstack - Claude Code AI factory with 23 specialists
AI

Garry Tan's gstack: 23 Claude Code Specialists That Ship

Y Combinator CEO Garry Tan open-sourced gstack β€” 23 Claude Code slash commands that turn one developer into a virtual engineering team. CEO, designer, QA.

LB
Luca Berton
Β· 3 min read

Y Combinator CEO Garry Tan just open-sourced gstack β€” a collection of 23 Claude Code slash commands that turn a single developer into a virtual engineering team. CEO product review, design critique, code review, QA with real browser testing, security audits, and automated releases β€” all from Markdown skill files.

The Premise: One Builder, Team-Scale Output

Tan’s pitch is backed by his own numbers: 3 production services and 40+ shipped features in 60 days, part-time, while running YC full-time. He cites Andrej Karpathy’s admission of not typing code since December 2025 and Peter Steinberger building OpenClaw (247K GitHub stars) essentially solo with AI agents.

The claim is not that AI writes perfect code. The claim is that with the right role specialization β€” giving the LLM different personas for different tasks β€” one person can cover the functions that traditionally require a team of designers, reviewers, QA engineers, and release managers.

The 23 Specialists

gstack organizes Claude Code into specialized roles via slash commands:

Product and Strategy:

  • /office-hours β€” describe what you are building, get structured feedback
  • /plan-ceo-review β€” product-level review of any feature idea
  • /plan-eng-review β€” architecture and engineering review
  • /plan-design-review β€” design critique before implementation

Design:

  • /design-consultation β€” interactive design session
  • /design-shotgun β€” rapid design exploration across multiple directions
  • /design-html β€” generate production-ready HTML/CSS

Engineering:

  • /review β€” rigorous code review on any branch
  • /ship β€” prepare changes for merge
  • /land-and-deploy β€” automated release workflow
  • /canary β€” canary deployment validation
  • /benchmark β€” performance testing

QA and Security:

  • /qa β€” opens a real browser against your staging URL
  • /browse β€” web browsing skill for research and testing
  • /connect β€” integration testing

Each command is a Markdown file in ~/.claude/skills/gstack/. No dependencies beyond Claude Code, Git, and Bun.

Why Role Specialization Works

The key insight is not giving Claude more tools β€” it is giving Claude different mindsets for different tasks. When you run /review, Claude acts as a senior engineer looking for production bugs. When you run /plan-design-review, it acts as a designer looking for AI slop and UX inconsistencies.

This mirrors how Karpathy’s CLAUDE.md works β€” behavioral constraints in Markdown that shape LLM output. gstack takes it further by creating an entire roster of specialized behaviors instead of a single set of principles.

The architecture is simple:

  1. Skill files are Markdown documents with role descriptions and behavioral rules
  2. Slash commands activate specific skill files
  3. Claude Code reads the active skill and adjusts its behavior accordingly
  4. No custom tooling, no API wrappers, no infrastructure

What This Means for Solo Builders

The 810x productivity claim (normalized logical lines of code per day) is provocative and debatable. But the underlying pattern is real: AI coding agents with structured roles let individuals cover more surface area than ever before.

For founders, this means:

  • Pre-funding: Ship an MVP without a team. Use /plan-ceo-review to pressure-test the product, /review for code quality, /qa for testing.
  • Early stage: One technical founder can maintain the velocity of a small team while focusing on customers and fundraising.
  • Growth stage: Use gstack as a template for how your team structures AI-assisted workflows.

How to Install

# Clone into Claude Code skills directory
git clone --single-branch --depth 1 \
  https://github.com/garrytan/gstack.git \
  ~/.claude/skills/gstack

# Run setup
cd ~/.claude/skills/gstack && ./setup

Then add gstack to your project’s CLAUDE.md to make the slash commands available.

My Take

The individual tools are useful, but the real value is the pattern: decomposing the software development lifecycle into specialized AI roles, each with explicit behavioral constraints. Whether you use gstack directly or build your own skill library, the approach of role-based LLM specialization is becoming the standard for AI-assisted development.

The MIT license means you can fork it, strip what you do not need, and add your own roles. I would start with /review and /qa β€” those cover the highest-value gap for most solo developers.

Master Claude Code

Want to build your own gstack-style workflow? These resources will get you there:

Free 30-min AI & Cloud consultation

Book Now