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
Tanβs 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 Karpathyβs 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-hoursβ describe what you are building, get structured feedback/plan-ceo-reviewβ product-level review of any feature idea/plan-eng-reviewβ architecture and engineering review/plan-design-reviewβ design critique before implementation
Design:
/design-consultationβ interactive design session/design-shotgunβ rapid design exploration across multiple directions/design-htmlβ generate production-ready HTML/CSS
Engineering:
/reviewβ rigorous code review on any branch/shipβ prepare changes for merge/land-and-deployβ automated release workflow/canaryβ canary deployment validation/benchmarkβ performance testing
QA and Security:
/qaβ opens a real browser against your staging URL/browseβ web browsing skill for research and testing/connectβ 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 Karpathyβs 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:
- Skill files are Markdown documents with role descriptions and behavioral rules
- Slash commands activate specific skill files
- Claude Code reads the active skill and adjusts its behavior accordingly
- 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-reviewto pressure-test the product,/reviewfor code quality,/qafor 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 && ./setupThen add gstack to your projectβs 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.
Related Reading
- Karpathyβs CLAUDE.md: 4 Rules That Fix LLM Coding
- GitHub Copilot Agent Mode
- AI Coding Agents and Platform Engineering
- Context Architecture for AI Agents
Master Claude Code
Want to build your own gstack-style workflow? These resources will get you there:
- π Claude Code Masterclass (Free on Udemy) β 13 lectures covering CLAUDE.md, hooks, MCP servers, and autonomous coding patterns
- π Claude Code Companion Book (Leanpub) β Deep dive into enterprise patterns, team workflows, and production Claude Code setups
- π 5 Claude Code Mods That Make It Production-Ready β Ralph Loop, Ultracode, Context7, and more