gstack 部署

安装插件

  • 支持 10 个 AI 编码代理，不仅仅是 Claude。设置会自动检测你安装了哪些代理

    git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/gstack
cd ~/gstack && ./setup
  • AgentFlagSkills install to
    OpenAI Codex CLI--host codex~/.codex/skills/gstack-*/
    OpenCode--host opencode~/.config/opencode/skills/gstack-*/
    Cursor--host cursor~/.cursor/skills/gstack-*/
    Factory Droid--host factory~/.factory/skills/gstack-*/
    Slate--host slate~/.slate/skills/gstack-*/
    Kiro--host kiro~/.kiro/skills/gstack-*/
    Hermes--host hermes~/.hermes/skills/gstack-*/
    GBrain (mod)--host gbrain~/.gbrain/skills/gstack-*/

效果

  • 示例

    You:    I want to build a daily briefing app for my calendar.
You:    /office-hours
Claude: [asks about the pain — specific examples, not hypotheticals]

You:    Multiple Google calendars, events with stale info, wrong locations.
        Prep takes forever and the results aren't good enough...

Claude: I'm going to push back on the framing. You said "daily briefing
        app." But what you actually described is a personal chief of
        staff AI.
        [extracts 5 capabilities you didn't realize you were describing]
        [challenges 4 premises — you agree, disagree, or adjust]
        [generates 3 implementation approaches with effort estimates]
        RECOMMENDATION: Ship the narrowest wedge tomorrow, learn from
        real usage. The full vision is a 3-month project — start with
        the daily briefing that actually works.
        [writes design doc → feeds into downstream skills automatically]

You:    /plan-ceo-review
        [reads the design doc, challenges scope, runs 10-section review]

You:    /plan-eng-review
        [ASCII diagrams for data flow, state machines, error paths]
        [test matrix, failure modes, security concerns]

You:    Approve plan. Exit plan mode.
        [writes 2,400 lines across 11 files. ~8 minutes.]

You:    /review
        [AUTO-FIXED] 2 issues. [ASK] Race condition → you approve fix.

You:    /qa https://staging.myapp.com
        [opens real browser, clicks through flows, finds and fixes a bug]

You:    /ship
        Tests: 42 → 51 (+9 new). PR: github.com/you/app/pull/42
  • sprint
  • SkillYour specialistWhat they do
    /office-hoursYC Office HoursStart 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-reviewCEO / FounderRethink the problem. Find the 10-star product hiding inside the request. Four modes: Expansion, Selective Expansion, Hold Scope, Reduction.
    /plan-eng-reviewEng ManagerLock in architecture, data flow, diagrams, edge cases, and tests. Forces hidden assumptions into the open.
    /plan-design-reviewSenior DesignerRates 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-reviewDeveloper Experience LeadInteractive 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-consultationDesign PartnerBuild a complete design system from scratch. Researches the landscape, proposes creative risks, generates realistic product mockups.
    /reviewStaff EngineerFind the bugs that pass CI but blow up in production. Auto-fixes the obvious ones. Flags completeness gaps.
    /investigateDebuggerSystematic root-cause debugging. Iron Law: no fixes without investigation. Traces data flow, tests hypotheses, stops after 3 failed fixes.
    /design-reviewDesigner Who CodesSame audit as /plan-design-review, then fixes what it finds. Atomic commits, before/after screenshots.
    /devex-reviewDX TesterLive 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-shotgunDesign 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-htmlDesign EngineerTurn 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.
    /qaQA LeadTest your app, find bugs, fix them with atomic commits, re-verify. Auto-generates regression tests for every fix.
    /qa-onlyQA ReporterSame methodology as /qa but report only. Pure bug report without code changes.
    /pair-agentMulti-Agent CoordinatorShare 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.
    /csoChief Security OfficerOWASP 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.
    /shipRelease EngineerSync main, run tests, audit coverage, push, open PR. Bootstraps test frameworks if you don't have one.
    /land-and-deployRelease EngineerMerge the PR, wait for CI and deploy, verify production health. One command from "approved" to "verified in production."
    /canarySREPost-deploy monitoring loop. Watches for console errors, performance regressions, and page failures.
    /benchmarkPerformance EngineerBaseline page load times, Core Web Vitals, and resource sizes. Compare before/after on every PR.
    /document-releaseTechnical WriterUpdate all project docs to match what you just shipped. Catches stale READMEs automatically.
    /retroEng ManagerTeam-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).
    /browseQA EngineerGive 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-cookiesSession ManagerImport cookies from your real browser (Chrome, Arc, Brave, Edge) into the headless session. Test authenticated pages.
    /autoplanReview PipelineOne command, fully reviewed plan. Runs CEO → design → eng review automatically with encoded decision principles. Surfaces only taste decisions for your approval.
    /learnMemoryManage 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.
  • Which review should I use?
  • Building for...Plan stage (before code)Live audit (after shipping)
    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)—
  • 强大工具
  • SkillWhat it does
    /codexSecond 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.
    /carefulSafety Guardrails — warns before destructive commands (rm -rf, DROP TABLE, force-push). Say "be careful" to activate. Override any warning.
    /freezeEdit Lock — restrict file edits to one directory. Prevents accidental changes outside scope while debugging.
    /guardFull Safety — /careful + /freeze in one command. Maximum safety for prod work.
    /unfreezeUnlock — remove the /freeze boundary.
    /open-gstack-browserGStack 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-deployDeploy Configurator — one-time setup for /land-and-deploy. Detects your platform, production URL, and deploy commands.
    /gstack-upgradeSelf-Updater — upgrade gstack to latest. Detects global vs vendored install, syncs both, shows what changed.