garrytan/gstack

⭐ 92,193  ·  #5  ·  TypeScript

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

TypeScript Webui

项目分析

🎯 定位	可视化交互层
💡 核心价值	把 Agent 的命令行能力封装成 Web 界面，支持会话管理、历史记录、多模型切换等功能，降低非技术人员的使用门槛
👥 适合谁	不太熟悉终端操作的用户，或者需要团队协作使用 Agent 的场景

为什么值得关注

92,193 Stars 说明这是一个经过大量用户验证的成熟工具。使用 TypeScript 开发。核心特色："I don't think I've typed like a line of code probably since December, basically, which is an extremely large change." — Andrej Karpathy, No Priors podcast, March 2026。

AI 深度分析报告

Summary

A CLI toolset that transforms Claude Code into a virtual software factory.

Core Features

• 23 Expert Roles (Slash Commands): Define roles such as CEO, Designer, Engineering Manager, QA, and Security Officer via Markdown prompts. Each role corresponds to an independent workflow—e.g., /plan-ceo-review handles product strategy review, /qa executes end-to-end testing in a real browser.
• Complete Delivery Pipeline: Covers the full software delivery lifecycle—from product ideation (/office-hours), architecture review (/plan-ceo-review), code review (/review), quality assurance (/qa), to release management (/release).
• Automated Security Audits: Built-in /security-audit command automatically performs OWASP Top 10 and STRIDE threat modeling checks, outputting structured audit reports.
• Zero Cost, Zero Dependencies: All tools are pure Markdown prompts leveraging Claude Code's native capabilities—no additional SaaS subscriptions or infrastructure required.
• MIT Licensed, Forkable & Customizable: Prompts and toolchains are fully open. Developers can freely modify role definitions, adjust workflows, or extend with new slash commands.

Technical Architecture

• Language & Runtime: Primarily TypeScript, relying on Claude Code CLI, Git, and Bun (Node.js required only for Windows).
• Code Structure: Core assets are Markdown files under the prompts/ directory. Each role corresponds to a .md file (e.g., ceo-review.md, qa-engineer.md), loaded via Claude Code's Slash Command mechanism. No complex build systems or frameworks.
• Design Philosophy: Replaces traditional code development with "prompt engineering." Instead of writing business logic, it defines AI agent behavior boundaries, output formats, and interaction flows. Essentially an "operating system for AI agents"—orchestrating multi-agent collaboration through structured prompts.
• Highlight: Encapsulates AI uncertainty within fixed role boundaries. For example, the /release command not only creates a PR but also requires the agent to generate changelogs, validate version numbers, and check rollback plans—significantly reducing the risk of AI hallucinations.

Quick Start Guide

1. Install Dependencies: Ensure Claude Code, Git, and Bun (or Node.js for Windows) are installed.
2. Clone the Repository: Run the following command in the Claude Code terminal:

   git clone --single-branch --depth 1 https://github.com/garrytan/gstack

3. Run Your First Command: Start Claude Code in the project root directory and enter /office-hours to describe your product idea.
4. Typical Workflow: /office-hours → /plan-ceo-review → Write code → /review → /qa → /release.

Strengths, Weaknesses, and Use Cases

Strengths:

• High Efficiency: A single person can execute workflows typically requiring a 5–10 person team, ideal for prototyping and rapid iteration.
• Zero Learning Curve: For developers familiar with Claude Code, it's plug-and-play—no need to learn new frameworks or DSLs.
• Full Transparency: All prompts and workflows are open source, auditable, and modifiable, avoiding the "black box" problem of commercial AI tools.
• Constrained Outputs: Role definitions and output templates significantly reduce the likelihood of AI generating meaningless content.

Weaknesses:

• Tightly Bound to Claude Code: Cannot be migrated to other models like GPT-4 or Gemini, creating single-vendor risk.
• Dependent on AI Quality: Effectiveness is capped by Claude Code's actual capabilities. Complex business logic or rare edge cases may lead to hallucinations or errors.
• Lacks Visual Interface: Pure CLI operation is not friendly to non-technical team members.
• Not Suitable for Large Teams: Designed as a "single-person super team"; multiple people using Claude Code in parallel on the same repository may cause conflicts.

Ideal Use Cases:

• Independent Developers / Technical Founders: Quickly validate product ideas with minimal human resources.
• Small Teams (1–5 people): Need full-process coverage but lack dedicated QA, security, or release engineers.
• AI Tool Explorers: Technologists interested in prompt engineering and AI agent orchestration.

Unsuitable Use Cases:

• Large enterprise projects requiring strict compliance audits and multi-person approval workflows.
• Scenarios demanding extremely high model output reliability (e.g., medical or financial core systems).
• Organizations with mature DevOps and QA infrastructure already in place.

Community & Popularity

• Stars: 92,193 (as of analysis date), growing rapidly, reflecting significant interest in the AI agent tool space.
• Forks / Contributions: Due to the project's nature (a collection of prompts rather than a traditional codebase), the number of forks is expected to be lower than stars. However, "fork and customize" is the intended primary usage model.
• Recent Updates: Last updated on May 9, 2026, indicating active maintenance. Garry Tan continues to iterate, with impressive contribution data shown in the README (1,237 contributions).
• Community Ecosystem: The project encourages users to share custom role prompts via Issues and PRs, potentially forming a "prompt marketplace"-style community resource pool.

技术信息

• 💻 语言: TypeScript
• 📂 Topics:
• 🕐 更新: 2026-05-09
• 🔗 访问 GitHub 仓库

---

数据更新于 2026-05-09 · Stars 数以 GitHub 实际数据为准