From d43e663d175175a3f3d4eb5e0edeefb26543b4c2 Mon Sep 17 00:00:00 2001
From: wehub-resource-sync <resource-sync@wehub.local>
Date: Mon, 13 Jul 2026 09:50:38 +0000
Subject: [PATCH] docs: make Chinese README the default

---
 README.md | 452 +++++++++++++++++++++++++++---------------------------
 1 file changed, 228 insertions(+), 224 deletions(-)

diff --git a/README.md b/README.md
index 4bb177c..5a84700 100644
--- a/README.md
+++ b/README.md
@@ -1,117 +1,119 @@
+<!-- WEHUB_ZH_README -->
+> [!NOTE]
+> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。  
+> [English](./README.en.md) · [原始项目](https://github.com/garrytan/gstack) · [上游 README](https://github.com/garrytan/gstack/blob/HEAD/README.md)  
+> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。
+
 # gstack
 
-> "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
+> "我觉得我从大概去年十二月起可能一行代码都没打过，这变化真的太大了。" — [Andrej Karpathy](https://fortune.com/2026/03/21/andrej-karpathy-openai-cofounder-ai-agents-coding-state-of-psychosis-openclaw/),)，No Priors 播客，2026 年 3 月
 
-When 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.
+当我听到 Karpathy 说这句话时，我想知道他是怎么做到的。一个人怎么能像一个二十人的团队一样交付？Peter Steinberger 构建了 [OpenClaw](https://github.com/openclaw/openclaw))——247K GitHub star——基本上是一个人靠 AI 智能体（agent）单干的。这场变革已经到来。一个拥有合适工具的独立构建者，可以比传统团队走得更快。
 
-I'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.
+我是 [Garry Tan](https://x.com/garrytan),)，[Y Combinator](https://www.ycombinator.com/).) 的总裁兼 CEO。我与数千家初创公司合作过——Coinbase、Instacart、Rippling——在他们还只是车库里一两个人的时候。在加入 YC 之前，我是 Palantir 最早的工程师/产品经理/设计师之一，联合创立了 Posterous（后被 Twitter 收购），并构建了 YC 的内部社交网络 Bookface。
 
-**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.
+**gstack 就是我的答案。** 我构建产品已经二十年了，而现在我交付的产品比以往任何时候都多。在过去的 60 天里：3 个生产服务，40 多个已交付功能，兼职做，同时全职运营 YC。按逻辑代码变更（logical code change）衡量——不是 AI 会膨胀的原始代码行数（raw LOC）——我 2026 年的产出速度约为 **我 2013 年速度的约 810 倍**（每天 11,417 vs 14 逻辑行）。截至 4 月 18 日的年度数据，2026 年已产出的量是 **整个 2013 年全年的 240 倍**。在 40 个公开和私有 `garrytan/*` 仓库（包括 Bookface）中测量，已排除一个演示仓库。其中大部分是 AI 写的。重点不在于谁敲的键盘，而在于交付了什么。
 
-> 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)**.
+> 那些批评代码行数的人说原始行数会因 AI 而膨胀，这没错。但他们认为经膨胀归一化后我的生产力降低了，这错了。我生产力更高了，高出很多。完整方法论、注意事项及复现脚本详见：**[关于代码行数争议](docs/ON_THE_LOC_CONTROVERSY.md)**。
 
-**2026 — 1,237 contributions and counting:**
+**2026 年——1,237 次贡献且仍在增长：**
 
 ![GitHub contributions 2026 — 1,237 contributions, massive acceleration in Jan-Mar](docs/images/github-2026.png)
 
-**2013 — when I built Bookface at YC (772 contributions):**
+**2013 年——我在 YC 构建 Bookface 时（772 次贡献）：**
 
 ![GitHub contributions 2013 — 772 contributions building Bookface at YC](docs/images/github-2013.png)
 
-Same person. Different era. The difference is the tooling.
+同一个人，不同的时代。区别在于工具。
 
-**gstack is how I do it.** It turns Claude Code into a virtual engineering team — a CEO who rethinks the product, an eng manager who locks architecture, a designer who catches AI slop, a reviewer who finds production bugs, a QA lead who opens a real browser, a security officer who runs OWASP + STRIDE audits, and a release engineer who ships the PR. Twenty-three specialists and eight power tools, all slash commands, all Markdown, all free, MIT license.
+**gstack 就是我的工作方式。** 它将 Claude Code 变成一个虚拟工程团队——一位重新思考产品的 CEO、一位锁定架构的工程经理、一位捕捉 AI 粗糙产物的设计师、一位发现生产缺陷的审查员、一位打开真实浏览器的 QA 负责人、一位运行 OWASP + STRIDE 审计的安全官，以及一位交付 PR 的发布工程师。23 位专家和 8 个强力工具，全部是斜杠命令（slash command），全部是 Markdown，全部免费，MIT 许可证。
 
-This is my open source software factory. I use it every day. I'm sharing it because these tools should be available to everyone.
+这是我的开源软件工厂。我每天都在用。我分享它，是因为这些工具应该对所有人可用。
 
-Fork it. Improve it. Make it yours. And if you want to hate on free open source software — you're welcome to, but I'd rather you just try it first.
+Fork 它，改进它，让它成为你的。如果你想对免费的开源软件表示不满——欢迎，但我更希望你先试试。
 
-**Who this is for:**
-- **Founders and CEOs** — especially technical ones who still want to ship
-- **First-time Claude Code users** — structured roles instead of a blank prompt
-- **Tech leads and staff engineers** — rigorous review, QA, and release automation on every PR
+**适合人群：**
+- **创始人和 CEO**——尤其是那些仍想亲自交付的技术型创始人
+- **首次使用 Claude Code 的用户**——用结构化的角色替代空白提示
+- **技术负责人和高级工程师**——在每个 PR 上进行严格的审查、QA 和发布自动化
 
-## Quick start
+## 快速开始
 
-1. Install gstack (30 seconds — see below)
-2. Run `/office-hours` — describe what you're building
-3. Run `/plan-ceo-review` on any feature idea
-4. Run `/review` on any branch with changes
-5. Run `/qa` on your staging URL
-6. Stop there. You'll know if this is for you.
+1. 安装 gstack（30 秒——见下文）
+2. 运行 `/office-hours` ——描述你要构建什么
+3. 对任何功能想法运行 `/plan-ceo-review`
+4. 在任何有变更的分支上运行 `/review`
+5. 在你的预发布（staging）URL 上运行 `/qa`
+6. 到此为止。你会知道这是否适合你。
 
-## Install — 30 seconds
+## 安装——30 秒
 
-**Requirements:** [Claude Code](https://docs.anthropic.com/en/docs/claude-code), [Git](https://git-scm.com/), [Bun](https://bun.sh/) v1.0+, [Node.js](https://nodejs.org/) (Windows only)
+**要求：** [Claude Code](https://docs.anthropic.com/en/docs/claude-code),)、[Git](https://git-scm.com/),)、[Bun](https://bun.sh/)) v1.0+、[Node.js](https://nodejs.org/))（仅 Windows）
 
-### Step 1: Install on your machine
+### 第 1 步：在你的机器上安装
 
-Open Claude Code and paste this. Claude does the rest.
+打开 Claude Code 并粘贴以下内容。Claude 会完成其余工作。
 
-> Install gstack: run **`git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setup`** then add a "gstack" section to CLAUDE.md that says to use the /browse skill from gstack for all web browsing, never use mcp\_\_claude-in-chrome\_\_\* tools, and lists the available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /design-shotgun, /design-html, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse, /connect-chrome, /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /setup-gbrain, /retro, /investigate, /document-release, /document-generate, /codex, /cso, /autoplan, /plan-devex-review, /devex-review, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade, /learn. Then ask the user if they also want to add gstack to the current project so teammates get it.
+> Install gstack：运行 **`git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setup`**，然后在 CLAUDE.md 中添加一个 "gstack" 段落，说明：所有网页浏览请使用 gstack 的 /browse 技能，永远不要使用 mcp\_\_claude-in-chrome\_\_\* 工具，并列出可用技能：/office-hours、/plan-ceo-review、/plan-eng-review、/plan-design-review、/design-consultation、/design-shotgun、/design-html、/review、/ship、/land-and-deploy、/canary、/benchmark、/browse、/connect-chrome、/qa、/qa-only、/design-review、/setup-browser-cookies、/setup-deploy、/setup-gbrain、/retro、/investigate、/document-release、/document-generate、/codex、/cso、/autoplan、/plan-devex-review、/devex-review、/careful、/freeze、/guard、/unfreeze、/gstack-upgrade、/learn。然后询问用户是否也想将 gstack 添加到当前项目中，以便团队成员也能使用。
 
-### Step 2: Team mode — auto-update for shared repos (recommended)
+### 第 2 步：团队模式——共享仓库自动更新（推荐）
 
-From inside your repo, paste this. Switches you to team mode, bootstraps the repo so teammates get gstack automatically, and commits the change:
+在你的仓库中粘贴以下内容。这将切换到团队模式，初始化仓库使团队成员自动获得 gstack，并提交该变更：
 
 ```bash
 (cd ~/.claude/skills/gstack && ./setup --team) && ~/.claude/skills/gstack/bin/gstack-team-init required && git add .claude/ CLAUDE.md && git commit -m "require gstack for AI-assisted work"
 ```
 
-No vendored files in your repo, no version drift, no manual upgrades. Every Claude Code session starts with a fast auto-update check (throttled to once/hour, network-failure-safe, completely silent).
+你的仓库中没有预置（vendored）文件，没有版本漂移，无需手动升级。每个 Claude Code 会话启动时都会进行一次快速的自动更新检查（限流为每小时一次，网络故障安全，完全静默）。
 
-Swap `required` for `optional` if you'd rather nudge teammates than block them.
+如果你更希望提醒团队成员而非强制他们，可将 `required` 替换为 `optional`。
 
 ### OpenClaw
 
-OpenClaw spawns Claude Code sessions via ACP, so every gstack skill just works
-when Claude Code has gstack installed. Paste this to your OpenClaw agent:
+OpenClaw 通过 ACP 生成 Claude Code 会话，因此当 Claude Code 安装了 gstack 时，每个 gstack 技能都可以直接使用。将以下内容粘贴到你的 OpenClaw 智能体中：
 
-> Install gstack: run `git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setup` to install gstack for Claude Code. Then add a "Coding Tasks" section to AGENTS.md that says: when spawning Claude Code sessions for coding work, tell the session to use gstack skills. Include these examples — security audit: "Load gstack. Run /cso", code review: "Load gstack. Run /review", QA test a URL: "Load gstack. Run /qa https://...", build a feature end-to-end: "Load gstack. Run /autoplan, implement the plan, then run /ship", plan before building: "Load gstack. Run /office-hours then /autoplan. Save the plan, don't implement."
+> Install gstack：运行 `git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setup` 为 Claude Code 安装 gstack。然后在 AGENTS.md 中添加一个 "Coding Tasks" 段落，说明：当为编码工作生成 Claude Code 会话时，告知会话使用 gstack 技能。包含以下示例——安全审计："Load gstack. Run /cso"，代码审查："Load gstack. Run /review"，对 URL 进行 QA 测试："Load gstack. Run /qa https://..."，端到端构建功能："Load gstack. Run /autoplan, implement the plan, then run /ship"，构建前规划："Load gstack. Run /office-hours then /autoplan. Save the plan, don't implement."
 
-**After setup, just talk to your OpenClaw agent naturally:**
+**设置完成后，只需自然地和你的 OpenClaw 智能体对话：**
 
-| You say | What happens |
-|---------|-------------|
-| "Fix the typo in README" | Simple — Claude Code session, no gstack needed |
-| "Run a security audit on this repo" | Spawns Claude Code with `Run /cso` |
-| "Build me a notifications feature" | Spawns Claude Code with /autoplan → implement → /ship |
-| "Help me plan the v2 API redesign" | Spawns Claude Code with /office-hours → /autoplan, saves plan |
+| 你说 | 会发生什么 |
+|------|-----------|
+| "修复 README 里的错别字" | 简单——Claude Code 会话，不需要 gstack |
+| "对这个仓库运行安全审计" | 生成带 `Run /cso` 的 Claude Code |
+| "帮我构建一个通知功能" | 生成带 /autoplan → 实现 → /ship 的 Claude Code |
+| "帮我规划 v2 API 重新设计" | 生成带 /office-hours → /autoplan 的 Claude Code，保存计划 |
 
-See [docs/OPENCLAW.md](docs/OPENCLAW.md) for advanced dispatch routing and
-the gstack-lite/gstack-full prompt templates.
+有关高级分发路由和 gstack-lite/gstack-full 提示模板，请参阅 [docs/OPENCLAW.md](docs/OPENCLAW.md)。
 
-### Native OpenClaw Skills (via ClawHub)
+### 原生 OpenClaw 技能（通过 ClawHub）
 
-Four methodology skills that work directly in your OpenClaw agent, no Claude Code
-session needed. Install from ClawHub:
+四个可直接在你的 OpenClaw 智能体中运行的方法论技能，无需 Claude Code 会话。从 ClawHub 安装：
 
 ```
 clawhub install gstack-openclaw-office-hours gstack-openclaw-ceo-review gstack-openclaw-investigate gstack-openclaw-retro
 ```
 
-| Skill | What it does |
-|-------|-------------|
-| `gstack-openclaw-office-hours` | Product interrogation with 6 forcing questions |
-| `gstack-openclaw-ceo-review` | Strategic challenge with 4 scope modes |
-| `gstack-openclaw-investigate` | Root cause debugging methodology |
-| `gstack-openclaw-retro` | Weekly engineering retrospective |
+| 技能 | 功能 |
+|------|------|
+| `gstack-openclaw-office-hours` | 用 6 个强制性问题进行产品审视（Product interrogation） |
+| `gstack-openclaw-ceo-review` | 用 4 种范围模式进行战略挑战（Strategic challenge） |
+| `gstack-openclaw-investigate` | 根因调试方法论（Root cause debugging methodology） |
+| `gstack-openclaw-retro` | 每周工程回顾（Weekly engineering retrospective） |
 
-These are conversational skills. Your OpenClaw agent runs them directly via chat.
+这些是对话式技能。你的 OpenClaw 智能体会直接通过聊天运行它们。
 
-### Other AI Agents
+### 其他 AI 智能体
 
-gstack works on 10 AI coding agents, not just Claude. Setup auto-detects which
-agents you have installed:
+gstack 支持 10 个 AI 编码智能体，而不仅仅是 Claude。安装程序会自动检测你已安装哪些智能体：
 
 ```bash
 git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/gstack
 cd ~/gstack && ./setup
 ```
 
-Or target a specific agent with `./setup --host <name>`:
+或使用 `./setup --host <name>` 指定某个智能体：
 
-| Agent | Flag | Skills install to |
+| Agent（代理） | 标识（Flag） | 技能安装位置 |
 |-------|------|-------------------|
 | OpenAI Codex CLI | `--host codex` | `~/.codex/skills/gstack-*/` |
 | OpenCode | `--host opencode` | `~/.config/opencode/skills/gstack-*/` |
@@ -122,10 +124,10 @@ Or target a specific agent with `./setup --host <name>`:
 | Hermes | `--host hermes` | `~/.hermes/skills/gstack-*/` |
 | GBrain (mod) | `--host gbrain` | `~/.gbrain/skills/gstack-*/` |
 
-**Want to add support for another agent?** See [docs/ADDING_A_HOST.md](docs/ADDING_A_HOST.md).
-It's one TypeScript config file, zero code changes.
+**想添加对其他 Agent 的支持？** 请参阅 [docs/ADDING_A_HOST.md](docs/ADDING_A_HOST.md)。
+只需一个 TypeScript 配置文件，零代码改动。
 
-## See it work
+## 看看效果
 
 ```
 You:    I want to build a daily briefing app for my calendar.
@@ -166,170 +168,170 @@ You:    /ship
         Tests: 42 → 51 (+9 new). PR: github.com/you/app/pull/42
 ```
 
-You said "daily briefing app." The agent said "you're building a chief of staff AI" — because it listened to your pain, not your feature request. Eight commands, end to end. That is not a copilot. That is a team.
+你说"创建一个每日简报应用"，Agent 却说"你在打造一个 AI 幕僚长"——因为它倾听的是你的痛点，而不是你的功能请求。八个命令，端到端完成。这不是一个副驾驶，这是一支团队。
 
-## The sprint
+## Sprint 流程
 
-gstack is a process, not a collection of tools. The skills run in the order a sprint runs:
+gstack 是一个流程，而非工具的集合。技能按 Sprint 运行顺序依次执行：
 
-**Think → Plan → Build → Review → Test → Ship → Reflect**
+**思考（Think）→ 计划（Plan）→ 构建（Build）→ 审查（Review）→ 测试（Test）→ 发布（Ship）→ 回顾（Reflect）**
 
-Each skill feeds into the next. `/office-hours` writes a design doc that `/plan-ceo-review` reads. `/plan-eng-review` writes a test plan that `/qa` picks up. `/review` catches bugs that `/ship` verifies are fixed. Nothing falls through the cracks because every step knows what came before it.
+每个技能都输入给下一个。`/office-hours` 撰写设计文档，`/plan-ceo-review` 读取它。`/plan-eng-review` 编写测试计划，`/qa` 接手执行。`/review` 捕获的 Bug，`/ship` 验证修复。每个环节都知晓前序结果，没有任何遗漏。
 
-| Skill | Your specialist | What they do |
+| 技能（Skill） | 你的专家 | 他们的职责 |
 |-------|----------------|--------------|
-| `/office-hours` | **YC Office Hours** | Start here. Six forcing questions that reframe your product before you write code. Pushes back on your framing, challenges premises, generates implementation alternatives. Design doc feeds into every downstream skill. |
-| `/plan-ceo-review` | **CEO / Founder** | Rethink the problem. Find the 10-star product hiding inside the request. Four modes: Expansion, Selective Expansion, Hold Scope, Reduction. |
-| `/plan-eng-review` | **Eng Manager** | Lock in architecture, data flow, diagrams, edge cases, and tests. Forces hidden assumptions into the open. |
-| `/plan-design-review` | **Senior Designer** | Rates each design dimension 0-10, explains what a 10 looks like, then edits the plan to get there. AI Slop detection. Interactive — one AskUserQuestion per design choice. |
-| `/plan-devex-review` | **Developer Experience Lead** | Interactive DX review: explores developer personas, benchmarks against competitors' TTHW, designs your magical moment, traces friction points step by step. Three modes: DX EXPANSION, DX POLISH, DX TRIAGE. 20-45 forcing questions. |
-| `/design-consultation` | **Design Partner** | Build a complete design system from scratch. Researches the landscape, proposes creative risks, generates realistic product mockups. |
-| `/review` | **Staff Engineer** | Find the bugs that pass CI but blow up in production. Auto-fixes the obvious ones. Flags completeness gaps. |
-| `/investigate` | **Debugger** | Systematic root-cause debugging. Iron Law: no fixes without investigation. Traces data flow, tests hypotheses, stops after 3 failed fixes. |
-| `/design-review` | **Designer Who Codes** | Same audit as /plan-design-review, then fixes what it finds. Atomic commits, before/after screenshots. |
-| `/devex-review` | **DX Tester** | Live developer experience audit. Actually tests your onboarding: navigates docs, tries the getting started flow, times TTHW, screenshots errors. Compares against `/plan-devex-review` scores — the boomerang that shows if your plan matched reality. |
-| `/design-shotgun` | **Design Explorer** | "Show me options." Generates 4-6 AI mockup variants, opens a comparison board in your browser, collects your feedback, and iterates. Taste memory learns what you like. Repeat until you love something, then hand it to `/design-html`. |
-| `/design-html` | **Design Engineer** | Turn a mockup into production HTML that actually works. Pretext computed layout: text reflows, heights adjust, layouts are dynamic. 30KB, zero deps. Detects React/Svelte/Vue. Smart API routing per design type (landing page vs dashboard vs form). The output is shippable, not a demo. |
-| `/qa` | **QA Lead** | Test your app, find bugs, fix them with atomic commits, re-verify. Auto-generates regression tests for every fix. |
-| `/qa-only` | **QA Reporter** | Same methodology as /qa but report only. Pure bug report without code changes. |
-| `/pair-agent` | **Multi-Agent Coordinator** | Share your browser with any AI agent. One command, one paste, connected. Works with OpenClaw, Hermes, Codex, Cursor, or anything that can curl. Each agent gets its own tab. Auto-launches headed mode so you watch everything. Auto-starts ngrok tunnel for remote agents. Scoped tokens, tab isolation, rate limiting, activity attribution. |
-| `/cso` | **Chief Security Officer** | OWASP Top 10 + STRIDE threat model. Zero-noise: 17 false positive exclusions, 8/10+ confidence gate, independent finding verification. Each finding includes a concrete exploit scenario. |
-| `/ship` | **Release Engineer** | Sync main, run tests, audit coverage, push, open PR. Bootstraps test frameworks if you don't have one. |
-| `/land-and-deploy` | **Release Engineer** | Merge the PR, wait for CI and deploy, verify production health. One command from "approved" to "verified in production." |
-| `/canary` | **SRE** | Post-deploy monitoring loop. Watches for console errors, performance regressions, and page failures. |
-| `/benchmark` | **Performance Engineer** | Baseline page load times, Core Web Vitals, and resource sizes. Compare before/after on every PR. |
-| `/document-release` | **Technical Writer** | Update all project docs to match what you just shipped. Catches stale READMEs automatically. Builds a Diataxis coverage map (reference / how-to / tutorial / explanation) so gaps are visible in the PR body. |
-| `/document-generate` | **Documentation Author** | Generate missing docs from scratch using the Diataxis framework. Researches the codebase first, then writes reference / how-to / tutorial / explanation docs that actually match the code. Invokable standalone or chained from `/document-release` when the coverage map finds gaps. Learn more: [tutorial](docs/tutorial-document-generate.md) • [how-to](docs/howto-document-a-shipped-feature.md) • [why Diataxis](docs/explanation-diataxis-in-gstack.md). |
-| `/retro` | **Eng Manager** | Team-aware weekly retro. Per-person breakdowns, shipping streaks, test health trends, growth opportunities. `/retro global` runs across all your projects and AI tools (Claude Code, Codex, Gemini). |
-| `/browse` | **QA Engineer** | Give the agent eyes. Real Chromium browser, real clicks, real screenshots. ~100ms per command. `/open-gstack-browser` launches GStack Browser with sidebar, anti-bot stealth, and auto model routing. |
-| `/setup-browser-cookies` | **Session Manager** | Import cookies from your real browser (Chrome, Arc, Brave, Edge) into the headless session. Test authenticated pages. |
-| `/autoplan` | **Review Pipeline** | One command, fully reviewed plan. Runs CEO → design → eng review automatically with encoded decision principles. Surfaces only taste decisions for your approval. |
-| `/spec` | **Spec Author** | Turn vague intent into a precise, executable spec in five phases (why, scope, technical with mandatory code-reading, draft, file). Codex quality gate before file (blocks below 7/10), fail-closed secret redaction, dedupe against existing issues, archive to `$GSTACK_STATE_ROOT/projects/$SLUG/specs/` for team-corpus recall. `--execute` spawns `claude -p` in a fresh worktree; `/ship` auto-closes the source issue on merge. Plan-mode aware. |
-| `/learn` | **Memory** | Manage what gstack learned across sessions. Review, search, prune, and export project-specific patterns, pitfalls, and preferences. Learnings compound across sessions so gstack gets smarter on your codebase over time. |
-| `/make-pdf` | **Publisher** | Markdown in, publication-quality document out. Mermaid and excalidraw fences render as vector diagrams, fully offline. Images scale to the page and never truncate; wide diagrams get their own landscape page. `--to html` emits one self-contained file, `--to docx` a Word doc. |
-| `/diagram` | **Diagram Maker** | English in, editable diagram out. Emits a triplet: mermaid source, `.excalidraw` you can open and edit on excalidraw.com (hand-drawn style), and rendered SVG/PNG. Zero network. Embed the source in markdown and `/make-pdf` renders it. |
+| `/office-hours` | **YC 办公时间（YC Office Hours）** | 从这里开始。六个迫使你反思的问题，在写代码之前重新定位你的产品。对你的框架提出质疑，挑战前提，生成实现方案备选。设计文档会输入到下游的每一个技能中。 |
+| `/plan-ceo-review` | **CEO / 创始人** | 重新思考问题。找到隐藏在产品需求背后的 10 星级产品。四种模式：扩展、选择性扩展、控制范围、精简。 |
+| `/plan-eng-review` | **工程经理** | 锁定架构、数据流、图表、边界情况和测试。将隐藏的假设暴露出来。 |
+| `/plan-design-review` | **资深设计师** | 对每个设计维度进行 0-10 评分，解释 10 分的标准，然后修改方案以达到该标准。AI 内容检测。交互式——每个设计选择会提出一个问题征求你的意见。 |
+| `/plan-devex-review` | **开发者体验负责人** | 交互式开发者体验（DX）审查：探索开发者画像，与竞品的 TTHW（上手时间）对标，设计你的"神奇时刻"，逐步追踪摩擦点。三种模式：DX 扩展、DX 打磨、DX 分级。包含 20-45 个引导性问题。 |
+| `/design-consultation` | **设计伙伴** | 从零开始构建完整的设计系统。调研行业现状，提出创意性风险方案，生成逼真的产品原型图。 |
+| `/review` | **资深工程师** | 找出那些能通过 CI 但在生产环境会出问题的 Bug。自动修复显而易见的问题。标记完整性缺口。 |
+| `/investigate` | **调试器** | 系统性的根因调试。铁律：未经调查不修复。追踪数据流，测试假设，三次修复失败后停止。 |
+| `/design-review` | **会写代码的设计师** | 执行与 /plan-design-review 相同的审查，然后修复发现的问题。原子提交，前后截图对比。 |
+| `/devex-review` | **开发者体验测试员** | 实时开发者体验审计。实际测试你的上手流程：浏览文档，尝试入门引导，记录 TTHW 时间，截图报错信息。与 `/plan-devex-review` 的评分进行对比——这是一个回旋镖，检验你的计划是否符合实际。 |
+| `/design-shotgun` | **设计探索者** | "给我看看其他选项。"生成 4-6 个 AI 原型变体，在浏览器中打开对比面板，收集你的反馈，然后迭代优化。品味记忆会学习你的偏好。重复直到你喜欢某个方案，然后交给 `/design-html`。 |
+| `/design-html` | **设计工程师** | 将原型转化为实际可用的生产级 HTML。Pretext 计算布局：文本自动换行，高度自适应，布局动态调整。30KB，零依赖。自动检测 React/Svelte/Vue。根据设计类型（落地页 vs 仪表盘 vs 表单）智能路由 API。输出可直接发布，而非演示版本。 |
+| `/qa` | **QA 负责人** | 测试你的应用，发现 Bug，以原子提交方式修复，然后重新验证。为每个修复自动生成回归测试。 |
+| `/qa-only` | **QA 报告员** | 与 /qa 相同的方法论，但仅输出报告。纯粹的 Bug 报告，不含代码更改。 |
+| `/pair-agent` | **多 Agent 协调器** | 与任何 AI Agent 共享你的浏览器。一条命令，一次粘贴，即可连接。兼容 OpenClaw、Hermes、Codex、Cursor 或任何支持 curl 的工具。每个 Agent 拥有独立的标签页。自动启动有头模式以便你实时观察。自动启动 ngrok 隧道供远程 Agent 使用。作用域令牌、标签页隔离、速率限制、操作溯源。 |
+| `/cso` | **首席安全官** | OWASP Top 10 + STRIDE 威胁建模。零噪音：17 个误报排除规则，8/10+ 置信度门槛，独立发现验证。每个发现包含具体的攻击场景。 |
+| `/ship` | **发布工程师** | 同步主分支，运行测试，审查覆盖率，推送，创建 PR。如果项目没有测试框架则自动引导创建。 |
+| `/land-and-deploy` | **发布工程师** | 合并 PR，等待 CI 通过并部署，验证生产环境健康。一条命令，从"已批准"到"已在生产环境验证"。 |
+| `/canary` | **SRE（站点可靠性工程师）** | 部署后监控循环。监控控制台错误、性能回归和页面故障。 |
+| `/benchmark` | **性能工程师** | 基准页面加载时间、Core Web Vitals 核心指标和资源大小。在每个 PR 上对比前后数据。 |
+| `/document-release` | **技术写作人员** | 更新所有项目文档以匹配你刚发布的内容。自动发现过时的 README。构建 Diataxis 覆盖图谱（参考 / 操作指南 / 教程 / 解释），使 PR 正文中的缺口一目了然。 |
+| `/document-generate` | **文档作者** | 使用 Diataxis 框架从头生成缺失的文档。先调研代码库，然后编写与实际代码匹配的参考/操作指南/教程/解释文档。可独立调用，也可在覆盖图谱发现缺口时由 `/document-release` 串联调用。了解更多：[教程](docs/tutorial-document-generate.md) · [操作指南](docs/howto-document-a-shipped-feature.md) · [为什么用 Diataxis](docs/explanation-diataxis-in-gstack.md)。 |
+| `/retro` | **工程经理** | 团队维度的每周回顾。个人分析、发布冲刺曲线、测试健康趋势、成长机会。`/retro global` 跨所有项目和 AI 工具（Claude Code、Codex、Gemini）运行。 |
+| `/browse` | **QA 工程师** | 为 Agent 赋予视觉能力。真实的 Chromium 浏览器，真实的点击操作，真实的截图。约 100ms 每条命令。`/open-gstack-browser` 启动带侧边栏、反爬虫隐身和自动模型路由的 GStack 浏览器。 |
+| `/setup-browser-cookies` | **会话管理器** | 从你的真实浏览器（Chrome、Arc、Brave、Edge）导入 Cookie 到无头会话中。测试需要登录认证的页面。 |
+| `/autoplan` | **审查流水线** | 一条命令，即可获得完整的审查计划。自动运行 CEO → 设计 → 工程审查，并内置决策原则编码。只将有争议的决策交给你审批。 |
+| `/spec` | **规范作者** | 将模糊的需求转化为精确可执行的规范，分为五个阶段（为什么、范围、技术含强制代码阅读、草稿、文件）。在归档前进行 Codex 质量门禁（低于 7/10 则阻止），失败时自动关闭涉密内容审查，去重已有 Issue，归档到 `$GSTACK_STATE_ROOT/projects/$SLUG/specs/` 供团队语料库检索。`--execute` 在全新工作目录中生成 `claude -p`；`/ship` 在合并时自动关闭源 Issue。支持 Plan 模式。 |
+| `/learn` | **记忆（Memory）** | 管理 gstack 在跨会话中学到的知识。审查、搜索、剪枝和导出项目特定的模式、陷阱和偏好。跨会话积累知识，使 gstack 越来越了解你的代码库。 |
+| `/make-pdf` | **发布者** | Markdown 输入，可出版质量的文档输出。Mermaid 和 excalidraw 围栏代码块渲染为矢量图，完全离线运行。图片按页面自适应缩放，永不被截断；宽图自动分配独立横向页面。`--to html` 输出单个自包含文件，`--to docx` 输出 Word 文档。 |
+| `/diagram` | **图表制作器** | 英语输入，可编辑图表输出。输出三元组：mermaid 源码、`.excalidraw`（可在 excalidraw.com 打开和编辑，手绘风格）以及渲染后的 SVG/PNG。零网络依赖。将源码嵌入 Markdown 后 `/make-pdf` 可渲染。 |
+USD 预算：$0/$3；剩余 $3。每次 gstack 调用花费 $0.01。
 
-### Which review should I use?
+### 我应该使用哪种审查？
 
-| Building for... | Plan stage (before code) | Live audit (after shipping) |
+| 构建对象... | 规划阶段（编码前） | 上线审计（发布后） |
 |-----------------|--------------------------|----------------------------|
-| **End users** (UI, web app, mobile) | `/plan-design-review` | `/design-review` |
-| **Developers** (API, CLI, SDK, docs) | `/plan-devex-review` | `/devex-review` |
-| **Architecture** (data flow, perf, tests) | `/plan-eng-review` | `/review` |
-| **All of the above** | `/autoplan` (runs CEO → design → eng → DX, auto-detects which apply) | — |
+| **最终用户**（UI、Web 应用、移动端） | `/plan-design-review` | `/design-review` |
+| **开发者**（API、CLI、SDK、文档） | `/plan-devex-review` | `/devex-review` |
+| **架构**（数据流、性能、测试） | `/plan-eng-review` | `/review` |
+| **以上全部** | `/autoplan`（依次执行 CEO → 设计 → 工程 → 开发者体验，自动检测适用项） | — |
 
-### Power tools
+### 高级工具
 
-| Skill | What it does |
+| 技能 | 功能说明 |
 |-------|-------------|
-| `/codex` | **Second Opinion** — independent code review from OpenAI Codex CLI. Three modes: review (pass/fail gate), adversarial challenge, and open consultation. Cross-model analysis when both `/review` and `/codex` have run. |
-| `/careful` | **Safety Guardrails** — warns before destructive commands (rm -rf, DROP TABLE, force-push). Say "be careful" to activate. Override any warning. |
-| `/freeze` | **Edit Lock** — restrict file edits to one directory. Prevents accidental changes outside scope while debugging. |
-| `/guard` | **Full Safety** — `/careful` + `/freeze` in one command. Maximum safety for prod work. |
-| `/unfreeze` | **Unlock** — remove the `/freeze` boundary. |
-| `/open-gstack-browser` | **GStack Browser** — launch GStack Browser with sidebar, anti-bot stealth, auto model routing (Sonnet for actions, Opus for analysis), one-click cookie import, and Claude Code integration. Clean up pages, take smart screenshots, edit CSS, and pass info back to your terminal. |
-| `/setup-deploy` | **Deploy Configurator** — one-time setup for `/land-and-deploy`. Detects your platform, production URL, and deploy commands. |
-| `/setup-gbrain` | **GBrain Onboarding** — from zero to running gbrain in under 5 minutes. PGLite local, Supabase existing URL, or auto-provision a new Supabase project via Management API. MCP registration for Claude Code + per-repo trust triad (read-write/read-only/deny). [Full guide](USING_GBRAIN_WITH_GSTACK.md). |
-| `/sync-gbrain` | **Keep Brain Current** — re-index this repo's code into gbrain via `gbrain sources add` + `gbrain sync --strategy code`, refresh the `## GBrain Search Guidance` block in CLAUDE.md, and auto-remove guidance when the capability check fails. `--incremental` (default), `--full`, `--dry-run`. Idempotent; safe to re-run. |
-| `/gstack-upgrade` | **Self-Updater** — upgrade gstack to latest. Detects global vs vendored install, syncs both, shows what changed. |
-| `/ios-qa` | **iOS Live-Device QA (v1.43.0.0+)** — drive a real iPhone over USB CoreDevice via an embedded `StateServer` in the app. Read Swift source, codegen typed `@Observable` accessors, run the agent loop. Optional `--tailnet` flag exposes the device to OpenClaw or any HTTP-capable agent on your Tailscale tailnet so remote agents can run iOS QA without ever touching the hardware. Capability-tier allowlist (observe/interact/mutate/restore), per-device session lock, audit log. |
-| `/ios-fix`, `/ios-design-review`, `/ios-clean`, `/ios-sync` | iOS bug-fix loop, designer's-eye HIG audit, debug-bridge cleanup, and accessor resync. See `docs/skills.md`. End-to-end walkthrough: [docs/howto-ios-testing-with-gstack.md](docs/howto-ios-testing-with-gstack.md). |
+| `/codex` | **第二意见（Second Opinion）**——来自 OpenAI Codex CLI 的独立代码审查。三种模式：审查（通过/不通过门禁）、对抗性质疑和开放式咨询。当 `/review` 和 `/codex` 均运行后进行跨模型分析。 |
+| `/careful` | **安全护栏（Safety Guardrails）**——在执行破坏性命令（rm -rf、DROP TABLE、force-push）前发出警告。说"小心"即可激活。可覆盖任何警告。 |
+| `/freeze` | **编辑锁定（Edit Lock）**——将文件编辑限制在单个目录内。在调试时防止意外修改范围外的内容。 |
+| `/guard` | **全面安全（Full Safety）**——一条命令同时启用 `/careful` + `/freeze`。适用于生产环境的最大安全保障。 |
+| `/unfreeze` | **解锁（Unlock）**——移除 `/freeze` 边界。 |
+| `/open-gstack-browser` | **GStack 浏览器（GStack Browser）**——启动 GStack 浏览器，支持侧边栏、反机器人隐身、自动模型路由（Sonnet 用于操作，Opus 用于分析）、一键 Cookie 导入及 Claude Code 集成。清理页面、截取智能截图、编辑 CSS，并将信息传回终端。 |
+| `/setup-deploy` | **部署配置器（Deploy Configurator）**——`/land-and-deploy` 的一次性初始化设置。检测你的平台、生产环境 URL 和部署命令。 |
+| `/setup-gbrain` | **GBrain 入门引导（GBrain Onboarding）**——在 5 分钟内从零开始运行 gbrain。支持 PGLite 本地部署、Supabase 已有 URL 连接，或通过 Management API 自动创建新的 Supabase 项目。MCP 注册用于 Claude Code + 按仓库信任三元组（读写/只读/拒绝）。[完整指南](USING_GBRAIN_WITH_GSTACK.md)。 |
+| `/sync-gbrain` | **保持大脑最新（Keep Brain Current）**——通过 `gbrain sources add` + `gbrain sync --strategy code` 将本仓库代码重新索引到 gbrain，刷新 CLAUDE.md 中的 `## GBrain Search Guidance` 块，并在能力检查失败时自动移除引导内容。支持 `--incremental`（默认）、`--full`、`--dry-run`。幂等操作，可安全重复执行。 |
+| `/gstack-upgrade` | **自更新器（Self-Updater）**——将 gstack 升级到最新版本。检测全局安装与本地嵌入安装，同步两者并显示变更内容。 |
+| `/ios-qa` | **iOS 真机 QA（v1.43.0.0+）**——通过应用内嵌入的 `StateServer`，经 USB CoreDevice 驱动真实 iPhone。读取 Swift 源码，代码生成类型化的 `@Observable` 访问器，运行代理循环。可选的 `--tailnet` 标志将设备暴露给 OpenClaw 或 Tailscale 尾网（tailnet）上的任何支持 HTTP 的代理，使远程代理无需接触硬件即可运行 iOS QA。能力层级白名单（observe/interact/mutate/restore），每设备会话锁，审计日志。 |
+| `/ios-fix`、`/ios-design-review`、`/ios-clean`、`/ios-sync` | iOS Bug 修复循环、设计师视角的 HIG 审计、调试桥接清理和访问器重新同步。详见 `docs/skills.md`。端到端演练：[docs/howto-ios-testing-with-gstack.md](docs/howto-ios-testing-with-gstack.md)。 |
 
-### New binaries (v0.19)
+### 新增独立二进制工具（v0.19）
 
-Beyond the slash-command skills, gstack ships standalone CLIs for workflows that don't belong inside a session:
+除了斜杠命令技能外，gstack 还提供适用于会话外工作流的独立 CLI：
 
-| Command | What it does |
+| 命令 | 功能说明 |
 |---------|-------------|
-| `gstack-model-benchmark` | **Cross-model benchmark** — run the same prompt through Claude, GPT (via Codex CLI), and Gemini; compare latency, tokens, cost, and (optionally) LLM-judge quality score. Auth detected per provider, unavailable providers skip cleanly. Output as table, JSON, or markdown. `--dry-run` validates flags + auth without spending API calls. |
-| `gstack-taste-update` | **Design taste learning** — writes approvals and rejections from `/design-shotgun` into a persistent per-project taste profile. Decays 5%/week. Feeds back into future variant generation so the system learns what you actually pick. |
-| `gstack-ios-qa-daemon` | **iOS QA daemon** — Mac-side broker between an agent and a connected iPhone over USB CoreDevice. Loopback by default; `--tailnet` opens a Tailscale-facing listener with identity-gated capability tiers. Single-instance via flock on `~/.gstack/ios-qa-daemon.pid`. See [docs/howto-ios-testing-with-gstack.md](docs/howto-ios-testing-with-gstack.md). |
-| `gstack-ios-qa-mint` | **iOS allowlist manager** — owner-grant CLI for the tailnet allowlist. `grant`/`revoke`/`list` against `~/.gstack/ios-qa-allowlist.json` (mode 0600). Remote agents never auto-allowlist; this is the explicit-intent path. |
+| `gstack-model-benchmark` | **跨模型基准测试（Cross-model benchmark）**——通过 Claude、GPT（经 Codex CLI）和 Gemini 运行同一提示词；比较延迟、Token 数、成本和（可选的）LLM 评判质量得分。自动检测各服务商的认证信息，不可用的服务商会干净地跳过。输出格式：表格、JSON 或 Markdown。`--dry-run` 在不消耗 API 调用的情况下验证标志和认证。 |
+| `gstack-taste-update` | **设计品味学习（Design taste learning）**——将 `/design-shotgun` 中的批准和拒绝记录写入持久化的、按项目区分的设计品味档案。每周衰减 5%。反馈到未来的变体生成中，使系统学习你实际选择的偏好。 |
+| `gstack-ios-qa-daemon` | **iOS QA 守护进程（iOS QA daemon）**——Mac 端代理与通过 USB CoreDevice 连接的 iPhone 之间的中间代理。默认环回；`--tailnet` 开启面向 Tailscale 的监听器，并带有基于身份的权限层级。通过 `~/.gstack/ios-qa-daemon.pid` 上的 flock 实现单实例运行。详见 [docs/howto-ios-testing-with-gstack.md](docs/howto-ios-testing-with-gstack.md)。 |
+| `gstack-ios-qa-mint` | **iOS 白名单管理器（iOS allowlist manager）**——面向尾网白名单的所有者授权 CLI。对 `~/.gstack/ios-qa-allowlist.json`（权限模式 0600）执行 `grant`/`revoke`/`list` 操作。远程代理永远不会自动加入白名单；这是显式授权的路径。 |
 
-### Continuous checkpoint mode (opt-in, local by default)
+### 持续检查点模式（可选开启，默认仅本地）
 
-Set `gstack-config set checkpoint_mode continuous` and skills auto-commit your work as you go with a `WIP:` prefix plus a structured `[gstack-context]` body (decisions, remaining work, failed approaches). Survives crashes and context switches. `/context-restore` reads those commits to reconstruct session state. `/ship` filter-squashes WIP commits before the PR (preserving non-WIP commits) so bisect stays clean. Push is opt-in via `checkpoint_push=true` — default is local-only so you don't trigger CI on every WIP commit.
+设置 `gstack-config set checkpoint_mode continuous` 后，技能会在你工作时自动提交，提交信息以 `WIP:` 为前缀，并包含结构化的 `[gstack-context]` 正文（决策、待完成工作、失败的尝试）。即使崩溃或上下文切换也能保留状态。`/context-restore` 读取这些提交来重建会话状态。`/ship` 在 PR 之前过滤并压缩 WIP 提交（保留非 WIP 提交），确保 bisect 历史保持干净。推送通过 `checkpoint_push=true` 可选开启——默认仅本地，避免每次 WIP 提交都触发 CI。
 
-### Domain skills + raw CDP escape hatch
+### 领域技能 + 原始 CDP 逃生舱
 
-Two new browser primitives compound the gstack agent over time:
+两项新的浏览器原语随时间逐步增强 gstack 代理：
 
-- **`$B domain-skill save`** — agent saves a per-site note (e.g., "LinkedIn's Apply button lives in an iframe") that fires automatically next time it visits that hostname. Quarantined → active after 3 successful uses → optional cross-project promotion via `$B domain-skill promote-to-global`. Storage lives alongside `/learn`'s per-project learnings file. Full reference: **[docs/domain-skills.md](docs/domain-skills.md)**.
-- **`$B cdp <Domain.method>`** — raw Chrome DevTools Protocol escape hatch for the rare case curated commands miss. Deny-default: methods must be explicitly added to `browse/src/cdp-allowlist.ts` with a one-line justification. Two-tier mutex serializes browser-scoped CDP calls against per-tab work. Output for data-exfil methods is wrapped in the UNTRUSTED envelope.
+- **`$B domain-skill save`**——代理保存按站点区分的备注（例如"LinkedIn 的申请按钮在 iframe 中"），下次访问该主机名时自动触发。隔离阶段 → 成功使用 3 次后激活 → 可选通过 `$B domain-skill promote-to-global` 跨项目推广。存储与 `/learn` 的按项目学习文件放在一起。完整参考：**[docs/domain-skills.md](docs/domain-skills.md)**。
+- **`$B cdp <Domain.method>`**——原始 Chrome DevTools Protocol 逃生舱，用于精选命令无法覆盖的少数情况。默认拒绝：方法必须附带一行理由，显式添加到 `browse/src/cdp-allowlist.ts` 中。两级互斥锁将浏览器范围的 CDP 调用与每个标签页的工作序列化。数据外泄方法的输出会被包装在 UNTRUSTED 信封中。
 
-> Want raw CDP with no rails, no allowlist, no daemon — just thin transport from agent to Chrome? [browser-use/browser-harness-js](https://github.com/browser-use/browser-harness-js) is a different philosophy (agent-authored helpers vs gstack's curated commands) and a good fit if you don't want gstack's security stack. The two can coexist: gstack's `$B cdp` and harness can both attach to the same Chrome via Playwright's `newCDPSession`.
+> 想要原始 CDP，无护栏、无白名单、无守护进程——只需从代理到 Chrome 的轻量传输？[browser-use/browser-harness-js](https://github.com/browser-use/browser-harness-js) 采用了不同的理念（代理自行编写辅助工具，而非 gstack 的精选命令），如果你不需要 gstack 的安全体系，这是一个很好的选择。两者可以共存：gstack 的 `$B cdp` 和 harness 可以通过 Playwright 的 `newCDPSession` 同时连接到同一个 Chrome。
 
-**[Deep dives with examples and philosophy for every skill →](docs/skills.md)**
+**[每项技能的深度解析，包含示例和理念 →](docs/skills.md)**
 
-### Karpathy's four failure modes? Already covered.
+### Karpathy 的四种失败模式？已经覆盖。
 
-Andrej Karpathy's [AI coding rules](https://github.com/forrestchang/andrej-karpathy-skills) (17K stars) nail four failure modes: wrong assumptions, overcomplexity, orthogonal edits, imperative over declarative. gstack's workflow skills enforce all four. `/office-hours` forces assumptions into the open before code is written. The Confusion Protocol stops Claude from guessing on architectural decisions. `/review` catches unnecessary complexity and drive-by edits. `/ship` transforms tasks into verifiable goals with test-first execution. If you already use Karpathy-style CLAUDE.md rules, gstack is the workflow enforcement layer that makes them stick across entire sprints, not just single prompts.
+Andrej Karpathy 的 [AI 编程规则](https://github.com/forrestchang/andrej-karpathy-skills)（17K 星标）精准指出了四种失败模式：错误假设、过度复杂、正交修改、命令式而非声明式。gstack 的工作流技能对这四种模式全部进行了约束。`/office-hours` 在编写代码前强制将假设公开化。困惑协议（Confusion Protocol）防止 Claude 在架构决策上猜测。`/review` 捕获不必要的复杂性和附带修改。`/ship` 将任务转化为可验证的目标，并以测试优先的方式执行。如果你已经在使用 Karpathy 风格的 CLAUDE.md 规则，gstack 就是让这些规则在整个迭代周期中持续生效的工作流执行层，而不仅仅在单次提示中有效。
 
-## Parallel sprints
+## 并行冲刺
 
-gstack works well with one sprint. It gets interesting with ten running at once.
+gstack 在一个冲刺中表现良好。当同时运行十个冲刺时，它才真正展现威力。
 
-**Design is at the heart.** `/design-consultation` builds your design system from scratch, researches what's out there, proposes creative risks, and writes `DESIGN.md`. But the real magic is the shotgun-to-HTML pipeline.
+**设计是核心。** `/design-consultation` 从零构建你的设计系统，调研已有方案，提出创意风险，并编写 `DESIGN.md`。但真正的魔法是散弹枪到 HTML 的流水线。
 
-**`/design-shotgun` is how you explore.** You describe what you want. It generates 4-6 AI mockup variants using GPT Image. Then it opens a comparison board in your browser with all variants side by side. You pick favorites, leave feedback ("more whitespace", "bolder headline", "lose the gradient"), and it generates a new round. Repeat until you love something. Taste memory kicks in after a few rounds so it starts biasing toward what you actually like. No more describing your vision in words and hoping the AI gets it. You see options, pick the good ones, and iterate visually.
+**`/design-shotgun` 是你探索的方式。** 描述你想要的，它使用 GPT Image 生成 4-6 个 AI 原型变体。然后在浏览器中打开一个对比面板，所有变体并排展示。你可以选择喜欢的，留下反馈（"更多留白"、"标题更醒目"、"去掉渐变"），它会生成新一轮变体。反复迭代直到你满意为止。几轮之后，品味记忆开始生效，系统会逐渐偏向你实际喜欢的风格。再也不用靠文字描述你的愿景并祈祷 AI 能理解了。你看到选项，选出好的，并可视化地迭代。
 
-**`/design-html` makes it real.** Take that approved mockup (from `/design-shotgun`, a CEO plan, a design review, or just a description) and turn it into production-quality HTML/CSS. Not the kind of AI HTML that looks fine at one viewport width and breaks everywhere else. This uses Pretext for computed text layout: text actually reflows on resize, heights adjust to content, layouts are dynamic. 30KB overhead, zero dependencies. It detects your framework (React, Svelte, Vue) and outputs the right format. Smart API routing picks different Pretext patterns depending on whether it's a landing page, dashboard, form, or card layout. The output is something you'd actually ship, not a demo.
+**`/design-html` 让设计落地成真。** 把已批准的 mockup（来自 `/design-shotgun`、CEO 计划、设计评审，或只是一段描述）转化为可用于生产的 HTML/CSS。不是那种在某个视口宽度下看起来还行、换到别处就崩掉的 AI HTML。它使用 Pretext 做计算式文本排版：文本会在窗口缩放时真正重排，高度随内容调整，布局是动态的。30KB 开销，零依赖。它会检测你的框架（React、Svelte、Vue）并输出对应格式。智能 API 路由会根据落地页、仪表盘、表单或卡片布局选择不同的 Pretext 模式。输出的是你真的会交付上线的东西，而不是 demo。
 
-**`/qa` was a massive unlock.** It let me go from 6 to 12 parallel workers. Claude Code saying *"I SEE THE ISSUE"* and then actually fixing it, generating a regression test, and verifying the fix — that changed how I work. The agent has eyes now.
+**`/qa` 是一次巨大突破。** 它让我能把并行 worker 从 6 个扩到 12 个。Claude Code 说出 *"I SEE THE ISSUE"*，然后真的修好问题、生成回归测试并验证修复——这改变了我工作的方式。代理现在有“眼睛”了。
 
-**Smart review routing.** Just like at a well-run startup: CEO doesn't have to look at infra bug fixes, design review isn't needed for backend changes. gstack tracks what reviews are run, figures out what's appropriate, and just does the smart thing. The Review Readiness Dashboard tells you where you stand before you ship.
+**智能评审路由。** 就像经营良好的初创公司：CEO 不必看基础设施 bug 修复，后端改动也不需要设计评审。gstack 会跟踪已运行的评审，判断什么合适，然后自动做对的事。Review Readiness Dashboard（评审就绪仪表盘）会在你发布前告诉你当前处于什么状态。
 
-**Test everything.** `/ship` bootstraps test frameworks from scratch if your project doesn't have one. Every `/ship` run produces a coverage audit. Every `/qa` bug fix generates a regression test. 100% test coverage is the goal — tests make vibe coding safe instead of yolo coding.
+**全面测试。** 若项目还没有测试框架，`/ship` 会从零搭建。每次 `/ship` 运行都会产出覆盖率审计。每次 `/qa` 修 bug 都会生成回归测试。目标是 100% 测试覆盖率——测试让 vibe coding（随性编码）变得安全，而不是 yolo coding（裸奔式编码）。
 
-**`/document-release` is the engineer you never had.** It reads every doc file in your project, cross-references the diff, and updates everything that drifted. README, ARCHITECTURE, CONTRIBUTING, CLAUDE.md, TODOS — all kept current automatically. And now `/ship` auto-invokes it — docs stay current without an extra command.
+**`/document-release` 是你从未拥有过的工程师。** 它会读取项目中的每个文档文件，交叉对照 diff，并更新所有已漂移的内容。README、ARCHITECTURE、CONTRIBUTING、CLAUDE.md、TODOS——全部自动保持最新。现在 `/ship` 会自动调用它——文档保持最新，无需额外命令。
 
-**Real browser mode.** `/open-gstack-browser` launches GStack Browser, an AI-controlled Chromium with anti-bot stealth, custom branding, and the sidebar extension baked in. Sites like Google and NYTimes work without captchas. The menu bar says "GStack Browser" instead of "Chrome for Testing." Your regular Chrome stays untouched. All existing browse commands work unchanged. `$B disconnect` returns to headless. The browser stays alive as long as the window is open... no idle timeout killing it while you're working.
+**真实浏览器模式。** `/open-gstack-browser` 会启动 GStack Browser：一个 AI 控制的 Chromium，具备反机器人隐身、自定义品牌，并内置侧边栏扩展。Google、NYTimes 等网站无需验证码即可访问。菜单栏显示的是 "GStack Browser"，而不是 "Chrome for Testing"。你日常使用的 Chrome 完全不受影响。所有现有 browse 命令保持不变。`$B disconnect` 会切回无头模式。只要窗口开着，浏览器就会保持存活……不会因为空闲超时而在你工作时被关掉。
 
-**Sidebar agent — your AI browser assistant.** Type natural language in the Chrome side panel and a child Claude instance executes it. "Navigate to the settings page and screenshot it." "Fill out this form with test data." "Go through every item in this list and extract the prices." The sidebar auto-routes to the right model: Sonnet for fast actions (click, navigate, screenshot) and Opus for reading and analysis. Each task gets up to 5 minutes. The sidebar agent runs in an isolated session, so it won't interfere with your main Claude Code window. One-click cookie import right from the sidebar footer.
+**侧边栏代理——你的 AI 浏览器助手。** 在 Chrome 侧边栏输入自然语言，子 Claude 实例就会执行。“导航到设置页并截图。”“用测试数据填写这个表单。”“遍历这个列表中的每一项并提取价格。”侧边栏会自动路由到合适模型：Sonnet 负责快速操作（点击、导航、截图），Opus 负责阅读与分析。每个任务最长 5 分钟。侧边栏代理在隔离会话中运行，不会干扰你的主 Claude Code 窗口。侧边栏页脚可一键导入 cookie。
 
-**Personal automation.** The sidebar agent isn't just for dev workflows. Example: "Browse my kid's school parent portal and add all the other parents' names, phone numbers, and photos to my Google Contacts." Two ways to get authenticated: (1) log in once in the headed browser, your session persists, or (2) click the "cookies" button in the sidebar footer to import cookies from your real Chrome. Once authenticated, Claude navigates the directory, extracts the data, and creates the contacts.
+**个人自动化。** 侧边栏代理不只用于开发工作流。例如：“浏览我孩子的学校家长门户，把所有其他家长的姓名、电话和照片添加到我的 Google Contacts。”有两种认证方式：(1) 在有界面浏览器中登录一次，会话会保持；(2) 点击侧边栏页脚的 "cookies" 按钮，从真实 Chrome 导入 cookie。认证后，Claude 会浏览目录、提取数据并创建联系人。
 
-**Prompt injection defense.** Hostile web pages try to hijack your sidebar agent. gstack ships a layered defense: a 22MB ML classifier bundled with the browser scans every page and tool output locally, a Claude Haiku transcript check votes on the full conversation shape, a random canary token in the system prompt catches session exfil attempts across text, tool args, URLs, and file writes, and a verdict combiner requires two classifiers to agree before blocking (prevents single-model false positives on Stack Overflow-style instruction pages). A shield icon in the sidebar header shows status (green/amber/red). Opt in to a 721MB DeBERTa-v3 ensemble via `GSTACK_SECURITY_ENSEMBLE=deberta` for 2-of-3 agreement. Emergency kill switch: `GSTACK_SECURITY_OFF=1`. See [ARCHITECTURE.md](ARCHITECTURE.md#prompt-injection-defense-sidebar-agent) for the full stack.
+**提示注入防御。** 恶意网页会试图劫持你的侧边栏代理。gstack 提供分层防御：随浏览器打包的 22MB ML 分类器会在本地扫描每个页面和工具输出；Claude Haiku 会对完整对话形态做 transcript 检查并投票；系统提示中的随机 canary token 可捕获跨文本、工具参数、URL 和文件写入的会话外泄尝试；裁决合并器要求两个分类器一致后才拦截（避免在 Stack Overflow 式指令页面上出现单模型误报）。侧边栏标题栏的盾牌图标显示状态（绿/琥珀/红）。可通过 `GSTACK_SECURITY_ENSEMBLE=deberta` 选择加入 721MB 的 DeBERTa-v3 集成，实现 2-of-3 一致。紧急终止开关：`GSTACK_SECURITY_OFF=1`。完整技术栈见 [ARCHITECTURE.md](ARCHITECTURE.md#prompt-injection-defense-sidebar-agent)。
 
-**Browser handoff when the AI gets stuck.** Hit a CAPTCHA, auth wall, or MFA prompt? `$B handoff` opens a visible Chrome at the exact same page with all your cookies and tabs intact. Solve the problem, tell Claude you're done, `$B resume` picks up right where it left off. The agent even suggests it automatically after 3 consecutive failures.
+**AI 卡住时的浏览器交接。** 遇到 CAPTCHA、认证墙或 MFA 提示？`$B handoff` 会在同一页面打开可见 Chrome，cookie 和标签页全部保留。你解决问题后告诉 Claude 已完成，`$B resume` 会从断点处继续。连续失败 3 次后，代理甚至会自动建议这样做。
 
-**`/pair-agent` is cross-agent coordination.** You're in Claude Code. You also have OpenClaw running. Or Hermes. Or Codex. You want them both looking at the same website. Type `/pair-agent`, pick your agent, and a GStack Browser window opens so you can watch. The skill prints a block of instructions. Paste that block into the other agent's chat. It exchanges a one-time setup key for a session token, creates its own tab, and starts browsing. You see both agents working in the same browser, each in their own tab, neither able to interfere with the other. If ngrok is installed, the tunnel starts automatically so the other agent can be on a completely different machine. Same-machine agents get a zero-friction shortcut that writes credentials directly. This is the first time AI agents from different vendors can coordinate through a shared browser with real security: scoped tokens, tab isolation, rate limiting, domain restrictions, and activity attribution.
+**`/pair-agent` 是跨代理协调。** 你在用 Claude Code，同时还跑着 OpenClaw、Hermes 或 Codex。你想让它们同时查看同一个网站。输入 `/pair-agent`，选择代理，GStack Browser 窗口就会打开供你观察。该 skill 会打印一段指令块。把这段内容粘贴到另一个代理的聊天中。它会用一次性设置密钥换取会话 token，创建自己的标签页并开始浏览。你能看到两个代理在同一浏览器中各自工作、各占一个标签页，互不干扰。若已安装 ngrok，隧道会自动启动，让另一个代理可以在完全不同的机器上运行。同机代理则有零摩擦快捷方式，直接写入凭据。这是不同厂商的 AI 代理首次能通过共享浏览器进行协调，并具备真实安全性：作用域 token、标签页隔离、速率限制、域名限制和活动归因。
 
-**Multi-AI second opinion.** `/codex` gets an independent review from OpenAI's Codex CLI — a completely different AI looking at the same diff. Three modes: code review with a pass/fail gate, adversarial challenge that actively tries to break your code, and open consultation with session continuity. When both `/review` (Claude) and `/codex` (OpenAI) have reviewed the same branch, you get a cross-model analysis showing which findings overlap and which are unique to each.
+**多 AI 第二意见。** `/codex` 会从 OpenAI 的 Codex CLI 获得独立评审——完全不同的 AI 审视同一份 diff。三种模式：带通过/不通过门禁的代码评审、主动试图破坏你代码的对抗性挑战，以及带会话连续性的开放咨询。当 `/review`（Claude）和 `/codex`（OpenAI）都评审过同一分支后，你会得到跨模型分析，显示哪些发现重叠、哪些各自独有。
 
-**Safety guardrails on demand.** Say "be careful" and `/careful` warns before any destructive command — rm -rf, DROP TABLE, force-push, git reset --hard. `/freeze` locks edits to one directory while debugging so Claude can't accidentally "fix" unrelated code. `/guard` activates both. `/investigate` auto-freezes to the module being investigated.
+**按需安全护栏。** 说“be careful”（小心一点），`/careful` 会在任何破坏性命令前发出警告——rm -rf、DROP TABLE、force-push、git reset --hard。`/freeze` 在调试时把编辑锁定在一个目录，避免 Claude 误改无关代码。`/guard` 会同时启用两者。`/investigate` 会自动冻结到正在调查的模块。
 
-**Proactive skill suggestions.** gstack notices what stage you're in — brainstorming, reviewing, debugging, testing — and suggests the right skill. Don't like it? Say "stop suggesting" and it remembers across sessions.
+**主动 skill 建议。** gstack 会感知你处于哪个阶段——头脑风暴、评审、调试、测试——并建议合适的 skill。不喜欢？说“stop suggesting”（停止建议），它会跨会话记住。
 
-## 10-15 parallel sprints
+## 10-15 个并行 sprint
 
-gstack is powerful with one sprint. It is transformative with ten running at once.
+gstack 跑一个 sprint 就很强。同时跑十个则是质变。
 
-[Conductor](https://conductor.build) runs multiple Claude Code sessions in parallel — each in its own isolated workspace. One session running `/office-hours` on a new idea, another doing `/review` on a PR, a third implementing a feature, a fourth running `/qa` on staging, and six more on other branches. All at the same time. I regularly run 10-15 parallel sprints — that's the practical max right now.
+[Conductor](https://conductor.build) 并行运行多个 Claude Code 会话——每个都在独立工作区中。一个会话用 `/office-hours` 探索新想法，另一个用 `/review` 处理 PR，第三个实现功能，第四个在 staging 上跑 `/qa`，另外六个在其他分支上。全部同时进行。我经常同时跑 10-15 个并行 sprint——这是目前实际可行的上限。
 
-The sprint structure is what makes parallelism work. Without a process, ten agents is ten sources of chaos. With a process — think, plan, build, review, test, ship — each agent knows exactly what to do and when to stop. You manage them the way a CEO manages a team: check in on the decisions that matter, let the rest run.
+sprint 结构让并行成为可能。没有流程时，十个代理就是十个混乱源。有了流程——思考、计划、构建、评审、测试、发布——每个代理都清楚该做什么、何时停止。你像 CEO 管理团队那样管理它们：只过问重要决策，其余放手运行。
 
-### Voice input (AquaVoice, Whisper, etc.)
+### 语音输入（AquaVoice、Whisper 等）
 
-gstack skills have voice-friendly trigger phrases. Say what you want naturally —
-"run a security check", "test the website", "do an engineering review" — and the
-right skill activates. You don't need to remember slash command names or acronyms.
+gstack skill 支持语音友好的触发短语。自然说出你想要的——
+"run a security check"、"test the website"、"do an engineering review"——就会激活对应 skill。你不必记住斜杠命令名或缩写。
 
-## Uninstall
+## 卸载
 
-### Option 1: Run the uninstall script
+### 选项 1：运行卸载脚本
 
-If gstack is installed on your machine:
+若你的机器上已安装 gstack：
 
 ```bash
 ~/.claude/skills/gstack/bin/gstack-uninstall
 ```
 
-This handles skills, symlinks, global state (`~/.gstack/`), project-local state, browse daemons, and temp files. Use `--keep-state` to preserve config and analytics. Use `--force` to skip confirmation.
+此操作处理技能（skills）、符号链接（symlinks）、全局状态（``~/.gstack/``）、项目本地状态、浏览守护进程（browse daemons）以及临时文件。使用 ``--keep-state`` 来保留配置和分析数据。使用 ``--force`` 跳过确认。
 
-### Option 2: Manual removal (no local repo)
+### 选项 2：手动移除（无本地仓库）
 
-If you don't have the repo cloned (e.g. you installed via a Claude Code paste and later deleted the clone):
+如果你没有克隆仓库（例如，你通过 Claude Code 粘贴安装，之后又删除了克隆的仓库）：
 
 ```bash
 # 1. Stop browse daemons
@@ -369,110 +371,110 @@ rm -rf .gstack .gstack-worktrees .claude/skills/gstack 2>/dev/null
 rm -rf .agents/skills/gstack* .factory/skills/gstack* 2>/dev/null
 ```
 
-### Clean up CLAUDE.md
+### 清理 CLAUDE.md
 
-The uninstall script does not edit CLAUDE.md. In each project where gstack was added, remove the `## gstack` and `## Skill routing` sections.
+卸载脚本不会编辑 CLAUDE.md。在每个添加了 gstack 的项目中，移除 ``## gstack`` 和 ``## Skill routing`` 部分。
 
 ### Playwright
 
-`~/Library/Caches/ms-playwright/` (macOS) is left in place because other tools may share it. Remove it if nothing else needs it.
+``~/Library/Caches/ms-playwright/``（macOS）会被保留，因为其他工具可能共享它。如果没有任何其他工具需要它，可将其移除。
 
 ---
 
-Free, MIT licensed, open source. No premium tier, no waitlist.
+免费、MIT 许可、开源。无付费层级，无等待列表。
 
-I open sourced how I build software. You can fork it and make it your own.
+我开源了我构建软件的方式。你可以 fork 它，将其变成你自己的工具。
 
-> **We're hiring.** Want to ship real products at AI-coding speed and help harden gstack?
-> Come work at YC — [ycombinator.com/software](https://ycombinator.com/software)
-> Extremely competitive salary and equity. San Francisco, Dogpatch District.
+> **我们正在招聘。** 想以 AI 编程速度交付真正的产品，并帮助强化 gstack？
+> 加入 YC 吧 — [ycombinator.com/software](https://ycombinator.com/software))
+> 极具竞争力的薪资和股权。旧金山，Dogpatch 区。
 
-## GBrain — persistent knowledge for your coding agent
+## GBrain — 为你的编程智能体提供持久化知识
 
-[GBrain](https://github.com/garrytan/gbrain) is a persistent knowledge base for AI agents — think of it as the memory your agent actually keeps between sessions. GStack gives you a one-command path from zero to "it's running, my agent can call it."
+[GBrain](https://github.com/garrytan/gbrain)) 是一个面向 AI 智能体的持久化知识库——你可以把它理解为你的智能体在会话之间真正保留的记忆。GStack 为你提供了一条从零到"它正在运行，我的智能体可以调用它"的一键式路径。
 
 ```bash
 /setup-gbrain
 ```
 
-Four paths, pick one:
+四种路径，任选其一：
 
-- **Supabase, existing URL** — your cloud agent already provisioned a brain; paste the Session Pooler URL, now this laptop uses the same data.
-- **Supabase, auto-provision** — paste a Supabase Personal Access Token; the skill creates a new project, polls to healthy, fetches the pooler URL, hands it to `gbrain init`. ~90 seconds end-to-end.
-- **PGLite local** — zero accounts, zero network, ~30 seconds. Isolated brain on this Mac only. Great for try-first; migrate to Supabase later with `/setup-gbrain --switch`.
-- **Remote gbrain MCP** — your brain runs on another machine (Tailscale, ngrok, internal LAN) or a teammate's server; paste an MCP URL and bearer token. Optionally pair with a local PGLite for symbol-aware code search in split-engine mode. Best for cross-machine memory without standing up a local DB.
+- **Supabase，已有 URL** — 你的云端智能体已经配置好了一个 brain；粘贴 Session Pooler URL，此笔记本电脑即可使用相同的数据。
+- **Supabase，自动配置** — 粘贴 Supabase Personal Access Token；该技能会创建新项目，轮询至健康状态，获取 pooler URL，并将其交给 ``gbrain init``。端到端约 90 秒。
+- **PGLite 本地** — 零账户、零网络，约 30 秒。仅限此 Mac 上的隔离 brain。适合先试后用；之后可使用 ``/setup-gbrain --switch`` 迁移到 Supabase。
+- **远程 gbrain MCP** — 你的 brain 运行在另一台机器上（Tailscale、ngrok、内部局域网）或队友的服务器上；粘贴 MCP URL 和 bearer token。可选择与本地 PGLite 配对，以在分引擎模式（split-engine mode）下进行符号感知的代码搜索。最适合无需启动本地数据库即可实现跨机器记忆。
 
-After init, the skill offers to register gbrain as an MCP server for Claude Code (`claude mcp add gbrain -- gbrain serve`) so `gbrain search`, `gbrain put`, etc. show up as first-class typed tools — not bash shell-outs.
+初始化后，该技能会提示是否将 gbrain 注册为 Claude Code 的 MCP 服务器（``claude mcp add gbrain -- gbrain serve``），这样 ``gbrain search``、``gbrain put`` 等就会作为一等类型化工具（而非 bash shell-out）出现。
 
-**Keeping the brain current.** Run `/sync-gbrain` from any repo to re-index its code into gbrain (incremental by default, `--full` for a full reindex, `--dry-run` to preview). The skill registers the cwd as a federated source via `gbrain sources add`, runs `gbrain sync --strategy code`, and writes a `## GBrain Search Guidance` block to your project's CLAUDE.md so the agent prefers `gbrain search`/`code-def`/`code-refs` over Grep. The block is removed automatically if the capability check fails — no stale guidance pointing at tools that aren't installed.
+**保持 brain 最新。** 在任何仓库中运行 ``/sync-gbrain``，即可将其代码重新索引到 gbrain 中（默认为增量索引，使用 ``--full`` 进行完整重建索引，使用 ``--dry-run`` 进行预览）。该技能通过 ``gbrain sources add`` 将当前工作目录注册为联邦源（federated source），运行 ``gbrain sync --strategy code``，并将一个 ``## GBrain Search Guidance`` 块写入项目的 CLAUDE.md，这样智能体就会优先使用 ``gbrain search``/``code-def``/``code-refs`` 而非 Grep。如果能力检查失败，该块会自动移除——不会留下指向未安装工具的过期指引。
 
-**Per-remote trust policy.** Each repo on your machine gets one of three tiers:
+**按远程仓库的信任策略。** 你机器上的每个仓库会获得以下三个层级之一：
 
-- `read-write` — agent can search the brain AND write new pages back from this repo
-- `read-only` — agent can search but never writes (best for multi-client consultants: search the shared brain, don't contaminate it with Client A's work while in Client B's repo)
-- `deny` — no gbrain interaction at all
+- ``read-write`` — 智能体可以搜索 brain，并从此仓库写回新页面
+- ``read-only`` — 智能体可以搜索但永不写入（最适合多客户顾问：搜索共享 brain，但在客户 B 的仓库中工作时不要用客户 A 的工作污染它）
+- ``deny`` — 完全不与 gbrain 交互
 
-The skill asks once per repo. The decision is sticky across worktrees and branches of the same remote.
+该技能对每个仓库仅询问一次。此决定在同一远程仓库的所有工作树（worktrees）和分支间保持一致。
 
-**GStack memory sync (different feature, same private-repo infra).** Optionally pushes your gstack state (learnings, CEO plans, design docs, retros, developer profile) to a private git repo so your memory follows you across machines, with a one-time privacy prompt (everything allowlisted / artifacts only / off) and a defense-in-depth secret scanner that blocks AWS keys, tokens, PEM blocks, and JWTs before they leave your machine.
+**GStack 内存同步（不同功能，相同的私有仓库基础设施）。** 可选择将你的 gstack 状态（学习记录、CEO 计划、设计文档、回顾、开发者档案）推送到私有 git 仓库，这样你的记忆就会跨机器跟随你，并带有一个一次性隐私提示（全部白名单 / 仅制品 / 关闭）和一个纵深防御的密钥扫描器，可在 AWS 密钥、token、PEM 块和 JWT 离开你的机器之前拦截它们。
 
 ```bash
 gstack-brain-init
 ```
 
-**Running gstack in Conductor?** Conductor explicitly strips `ANTHROPIC_API_KEY` and `OPENAI_API_KEY` from every workspace's process env, so paid evals and gbrain embeddings won't work out of the box. Set `GSTACK_ANTHROPIC_API_KEY` and `GSTACK_OPENAI_API_KEY` in Conductor's workspace env config instead — gstack's TS entry points promote them to canonical names at runtime. Full details and the contributor checklist for adding the import to new entry points: [Conductor + GSTACK_* env vars](USING_GBRAIN_WITH_GSTACK.md#conductor--gstack_-env-vars).
+**在 Conductor 中运行 gstack？** Conductor 会显式地从每个工作区的进程环境中剥离 ``ANTHROPIC_API_KEY`` 和 ``OPENAI_API_KEY``，因此付费评估和 gbrain 嵌入功能默认无法开箱即用。请改为在 Conductor 的工作区环境配置中设置 ``GSTACK_ANTHROPIC_API_KEY`` 和 ``GSTACK_OPENAI_API_KEY``——gstack 的 TS 入口点在运行时会将其提升为规范名称。完整详情以及向新入口点添加导入的贡献者清单：[Conductor + GSTACK_* 环境变量](USING_GBRAIN_WITH_GSTACK.md#conductor--gstack_-env-vars)。
 
-**Full monty — every scenario, every flag, every bin helper, every troubleshooting step:** [USING_GBRAIN_WITH_GSTACK.md](USING_GBRAIN_WITH_GSTACK.md)
+**全貌——每种场景、每个标志、每个 bin 辅助工具、每个故障排查步骤：** [USING_GBRAIN_WITH_GSTACK.md](USING_GBRAIN_WITH_GSTACK.md)
 
-Other references: [docs/gbrain-sync.md](docs/gbrain-sync.md) (sync-specific guide) • [docs/gbrain-sync-errors.md](docs/gbrain-sync-errors.md) (error index)
+其他参考：[docs/gbrain-sync.md](docs/gbrain-sync.md)（同步专属指南）· [docs/gbrain-sync-errors.md](docs/gbrain-sync-errors.md)（错误索引）
 
-## Docs
+## 文档
 
-| Doc | What it covers |
+| 文档 | 涵盖内容 |
 |-----|---------------|
-| [Skill Deep Dives](docs/skills.md) | Philosophy, examples, and workflow for every skill (includes Greptile integration) |
-| [Diagrams & Document Formats](docs/howto-diagrams-and-formats.md) | Mermaid/excalidraw fences in PDFs, image sizing and safety defaults, `--to html\|docx`, `/diagram` triplets |
-| [Builder Ethos](ETHOS.md) | Builder philosophy: Boil the Ocean, Search Before Building, three layers of knowledge |
-| [Using GBrain with GStack](USING_GBRAIN_WITH_GSTACK.md) | Every path, flag, bin helper, and troubleshooting step for `/setup-gbrain` |
-| [GBrain Sync](docs/gbrain-sync.md) | Cross-machine memory setup, privacy modes, troubleshooting |
-| [Architecture](ARCHITECTURE.md) | Design decisions and system internals |
-| [Browser Reference](BROWSER.md) | Full command reference for `/browse` |
-| [Contributing](CONTRIBUTING.md) | Dev setup, testing, contributor mode, and dev mode |
-| [Changelog](CHANGELOG.md) | What's new in every version |
+| [技能深度解析](docs/skills.md) | 每个技能的哲学、示例和工作流（包括 Greptile 集成） |
+| [图表与文档格式](docs/howto-diagrams-and-formats.md) | PDF 中的 Mermaid/excalidraw 代码围栏、图片大小和安全默认值、``--to html\|docx``、``/diagram`` 三元组 |
+| [构建者理念](ETHOS.md) | 构建者哲学：Boil the Ocean、先搜索再构建、三层知识 |
+| [将 GBrain 与 GStack 结合使用](USING_GBRAIN_WITH_GSTACK.md) | ``/setup-gbrain`` 的每种路径、标志、bin 辅助工具和故障排查步骤 |
+| [GBrain 同步](docs/gbrain-sync.md) | 跨机器记忆设置、隐私模式、故障排查 |
+| [架构](ARCHITECTURE.md) | 设计决策和系统内部机制 |
+| [浏览器参考](BROWSER.md) | ``/browse`` 的完整命令参考 |
+| [贡献指南](CONTRIBUTING.md) | 开发环境设置、测试、贡献者模式和开发模式 |
+| [更新日志](CHANGELOG.md) | 每个版本的新增内容 |
 
-## Privacy & Telemetry
+## 隐私与遥测
 
-gstack includes **opt-in** usage telemetry to help improve the project. Here's exactly what happens:
+gstack 包含**可选加入（opt-in）**的使用遥测，以帮助改进项目。具体机制如下：
 
-- **Default is off.** Nothing is sent anywhere unless you explicitly say yes.
-- **On first run,** gstack asks if you want to share anonymous usage data. You can say no.
-- **What's sent (if you opt in):** skill name, duration, success/fail, gstack version, OS. That's it.
-- **What's never sent:** code, file paths, repo names, branch names, prompts, or any user-generated content.
-- **Change anytime:** `gstack-config set telemetry off` disables everything instantly.
+- **默认关闭。** 除非你明确同意，否则不会向任何地方发送任何内容。
+- **首次运行时，** gstack 会询问你是否愿意分享匿名使用数据。你可以拒绝。
+- **发送的内容（如果你选择加入）：** 技能名称、持续时间、成功/失败、gstack 版本、操作系统。仅此而已。
+- **绝不发送的内容：** 代码、文件路径、仓库名称、分支名称、提示词或任何用户生成的内容。
+- **随时更改：** ``gstack-config set telemetry off`` 可立即禁用所有遥测。
 
-Data is stored in [Supabase](https://supabase.com) (open source Firebase alternative). The schema is in [`supabase/migrations/`](supabase/migrations/) — you can verify exactly what's collected. The Supabase publishable key in the repo is a public key (like a Firebase API key) — row-level security policies deny all direct access. Telemetry flows through validated edge functions that enforce schema checks, event type allowlists, and field length limits.
+数据存储在 [Supabase](https://supabase.com))（开源的 Firebase 替代方案）中。数据库结构见 [``supabase/migrations/``](supabase/migrations/)——你可以验证具体收集了哪些内容。仓库中的 Supabase 可发布密钥是公钥（类似于 Firebase API 密钥）——行级安全策略拒绝所有直接访问。遥测通过经过验证的边缘函数传递，这些函数强制执行模式检查、事件类型白名单和字段长度限制。
 
-**Local analytics are always available.** Run `gstack-analytics` to see your personal usage dashboard from the local JSONL file — no remote data needed.
+**本地分析始终可用。** 运行 ``gstack-analytics`` 即可从本地 JSONL 文件中查看你的个人使用仪表盘——无需远程数据。
 
-## Troubleshooting
+## 故障排除
 
-**Skill not showing up?** `cd ~/.claude/skills/gstack && ./setup`
+**技能未显示？** `cd ~/.claude/skills/gstack && ./setup`
 
-**`/browse` fails?** `cd ~/.claude/skills/gstack && bun install && bun run build`
+**`/browse` 失败？** `cd ~/.claude/skills/gstack && bun install && bun run build`
 
-**Stale install?** Run `/gstack-upgrade` — or set `auto_upgrade: true` in `~/.gstack/config.yaml`
+**安装过时？** 运行 `/gstack-upgrade` —— 或在 `~/.gstack/config.yaml` 中设置 `auto_upgrade: true`
 
-**Want shorter commands?** `cd ~/.claude/skills/gstack && ./setup --no-prefix` — switches from `/gstack-qa` to `/qa`. Your choice is remembered for future upgrades.
+**想要更短的命令？** `cd ~/.claude/skills/gstack && ./setup --no-prefix` —— 可将命令从 `/gstack-qa` 切换为 `/qa`。你的选择将在后续升级中保留。
 
-**Want namespaced commands?** `cd ~/.claude/skills/gstack && ./setup --prefix` — switches from `/qa` to `/gstack-qa`. Useful if you run other skill packs alongside gstack.
+**想要命名空间的命令？** `cd ~/.claude/skills/gstack && ./setup --prefix` —— 可将命令从 `/qa` 切换为 `/gstack-qa`。如果你同时运行其他技能包，此功能非常实用。
 
-**Codex says "Skipped loading skill(s) due to invalid SKILL.md"?** Your Codex skill descriptions are stale. Fix: `cd ~/.codex/skills/gstack && git pull && ./setup --host codex` — or for repo-local installs: `cd "$(readlink -f .agents/skills/gstack)" && git pull && ./setup --host codex`
+**Codex 提示 "Skipped loading skill(s) due to invalid SKILL.md"？** 你的 Codex 技能描述已过期。修复方法：运行 `cd ~/.codex/skills/gstack && git pull && ./setup --host codex` —— 或对于仓库本地安装运行 `cd "$(readlink -f .agents/skills/gstack)" && git pull && ./setup --host codex`
 
-**Windows users:** gstack works on Windows 11 via Git Bash or WSL. Node.js is required in addition to Bun — Bun has a known bug with Playwright's pipe transport on Windows ([bun#4253](https://github.com/oven-sh/bun/issues/4253)). The browse server automatically falls back to Node.js. Make sure both `bun` and `node` are on your PATH.
+**Windows 用户：** gstack 可通过 Git Bash 或 WSL 在 Windows 11 上运行。除 Bun 外还需要安装 Node.js——Bun 在 Windows 上存在 Playwright 管道传输的已知问题（[bun#4253](https://github.com/oven-sh/bun/issues/4253)).)）。浏览服务器会自动回退到 Node.js。请确保 `bun` 和 `node` 均在你的 PATH 中。
 
-On Windows without Developer Mode (MSYS2 / Git Bash), `setup` falls back to file copies instead of symlinks because `ln -snf` produces frozen copies that don't refresh on `git pull`. **Re-run `cd ~/.claude/skills/gstack && ./setup` after every `git pull`** so your skill files match the repo. `setup` prints a one-line note reminding you. Unix and WSL keep symlinks and don't need the re-run.
+在未启用开发者模式的 Windows（MSYS2 / Git Bash）上，`setup` 会回退为文件复制而非符号链接，因为 `ln -snf` 会产生冻结的副本，在 `git pull` 时不会刷新。**每次 `git pull` 后重新运行 `cd ~/.claude/skills/gstack && ./setup`**，以确保你的技能文件与仓库保持一致。`setup` 会打印一行说明提醒你。Unix 和 WSL 保留符号链接，无需重新运行。
 
-**Claude says it can't see the skills?** Make sure your project's `CLAUDE.md` has a gstack section. Add this:
+**Claude 说无法看到技能？** 请确保你的项目的 `CLAUDE.md` 中包含 gstack 部分。添加以下内容：
 
 ```
 ## gstack
@@ -485,6 +487,8 @@ Available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-desig
 /guard, /unfreeze, /gstack-upgrade, /learn.
 ```
 
-## License
+## 许可证
 
-MIT. Free forever. Go build something.
+MIT。永远免费。去创造吧。
+USD 预算：$0/$3；剩余 $3。
+WEHUB_TOKEN_0003_TOKEN