项目简介
包含 23 个精选斜杠命令，赋予 Claude Code CEO、设计师、QA、发布工程师等角色，帮助独立开发者通过结构化 AI 工作流加速交付。
README 预览
# gstack\n\n> "I don't think I've typed like a line of code probably since December, basically, which is an extremely large change." — [Andrej Karpathy](https://fortune.com/2026/03/21/andrej-karpathy-openai-cofounder-ai-agents-coding-state-of-psychosis-openclaw/), No Priors podcast, March 2026\n\nWhen I heard Karpathy say this, I wanted to find out how. How does one person ship like a team of twenty? Peter Steinberger built [OpenClaw](https://github.com/openclaw/openclaw) — 247K GitHub stars — essentially solo with AI agents. The revolution is here. A single builder with the right tooling can move faster than a traditional team.\n\nI'm [Garry Tan](https://x.com/garrytan), President & CEO of [Y Combinator](https://www.ycombinator.com/). I've worked with thousands of startups — Coinbase, Instacart, Rippling — when they were one or two people in a garage. Before YC, I was one of the first eng/PM/designers at Palantir, cofounded Posterous (sold to Twitter), and built Bookface, YC's internal social network.\n\n**gstack is my answer.** I've been building products for twenty years, and right now I'm shipping more products than I ever have. In the last 60 days: 3 production services, 40+ shipped features, part-time, while running YC full-time. On logical code change — not raw LOC, which AI inflates — my 2026 run rate is **~810× my 2013 pace** (11,417 vs 14 logical lines/day). Year-to-date (through April 18), 2026 has already produced **240× the entire 2013 year**. Measured across 40 public + private `garrytan/*` repos including Bookface, after excluding one demo repo. AI wrote most of it. The point isn't who typed it, it's what shipped.\n\n> The LOC critics aren't wrong that raw line counts inflate with AI. They are wrong that normalized-for-inflation, I'm less productive. I'm more productive, by a lot. Full methodology, caveats, and reproduction script: **[On the LOC Controversy](docs/ON_THE_LOC_CONTROVERSY.md)**.\n\n**2026 — 1,237 contributions and counting:**\n\n\n\n**20
常见问题 (5)
故障排除如何防止当 origin/<base> 领先于我的功能分支时，/review 和 /ship 显示虚假删除？
出现此问题的原因是 diff 使用了两点比较 git diff origin/<base>，这会将基分支上尚未合入你分支的提交显示为删除。永久修复方法是使用 git diff $(git merge-base origin/<base> HEAD)，该命令将工作树与合并基点进行比较，排除仅存在于基分支的提交，同时仍包含未提交的更改。此修复已合入 PR #1594。作为临时解决方案，在 /review 之前运行 git merge origin/<base> 可避免误判删除。
故障排除为什么在 gstack AskUserQuestion 中 CJK 字符会出现乱码（例如，管理工具变成 3用箱），以及如何修复？
该bug由模型在AskUserQuestion JSON中使用\\\\uXXXX转义CJK字符导致码点错误引起。修复方法：编辑scripts/resolvers/preamble/generate-ask-user-format.ts，添加rule 12禁止对非ASCII字符进行\\\\uXXXX转义，然后运行bun run gen:skill-docs --host all。或者更新至解决该问题的最新gstack版本。根本原因是模型对plan-review技能中常见的多行长问题字符串的默认转义行为。
故障排除为什么在升级 Codex CLI 后，Codex 审查失败并显示 'error: the argument \\\\'[PROMPT]\\\\' cannot be used with \\\\'--base <BRANCH>\\\\''？
这个问题出现在 Codex CLI ≥ 0.124.0-alpha.2 版本中，该版本不再允许在提供提示时使用 --base 标志。解决方法：编辑 ~/.claude/skills/gstack-codex/SKILL.md（或团队模式路径），移除 Step 2A 中两次 codex review 调用中的 --base <base> 参数。然后在提示中添加一条 git diff 指令，例如：“查看此分支相对于基础分支 <base> 的变更。运行 git diff <base>...HEAD 来查看差异。”或者将 Codex CLI 降级到 0.124.x 之前的版本。上游修复正在此 issue 中跟踪。
故障排除使用 gstack 存在哪些安全风险，以及如何降低这些风险？
安装gstack时，主要风险包括：供应链攻击（仅从官方仓库克隆并验证提交）、权限过高的代理工作流（使用只读技能如qa-only，启用/careful）、本地守护进程令牌泄露（空闲时停止browse守护进程）、Cookie导入风险（使用专用浏览器配置文件）、恶意网站的提示注入（保持GSTACK_SECURITY_OFF=0）、遥测数据泄露（运行'gstack-config set telemetry off'）以及过大的ML下载。缓解措施：运行前审计代码、限制技能范围、约束令牌访问、除非可信否则禁用同步、绝不暴露API密钥。完整详情请参阅仓库的安全文档。
故障排除为什么运行 './setup --help' 会开始安装而不是显示帮助？
这是一个已知的错误，未识别的标志（如--help）会导致安装脚本继续进行安装。该问题在后续更新中已修复。升级到软件的最新版本以获得正确的--help行为。如果无法升级，请避免使用--help，直接参考项目文档。