> ## Documentation Index
> Fetch the complete documentation index at: https://prof-lee.zikun.me/llms.txt
> Use this file to discover all available pages before exploring further.

# The 47 Skills

> Every slash command in the repository, grouped by lifecycle phase.

gstack ships forty-seven skills. One top-level meta-skill at the repository root routes user requests to the right specialist. The remaining forty-six split into three groups. Twenty-three lifecycle specialists run a sprint end to end. Eight power tools sit alongside as safety guardrails, second opinions, and self-updaters. Fifteen supporting skills are infrastructure. Orchestration, semantic memory, context save and restore, browser primitives, and code-quality dashboards.

Each card below names the slash command, the persona it role-plays inside the model, and the single action it owns.

***

## Think

<CardGroup cols={2}>
  <Card title="/office-hours" icon="lightbulb">
    **YC Office Hours partner.** Six forcing questions that expose demand, status quo, specificity, the narrowest wedge, observation, and future fit. Ends with a design doc written to disk.
  </Card>
</CardGroup>

## Plan

<CardGroup cols={2}>
  <Card title="/plan-ceo-review" icon="crown">
    **CEO / founder mode.** Four modes. Expansion, Selective Expansion, Hold Scope, Reduction. Finds the 10-star product hiding inside the request.
  </Card>

  <Card title="/plan-eng-review" icon="hard-hat">
    **Engineering manager mode.** Locks architecture, data flow, ASCII diagrams, edge cases, and the test plan. `/ship` checks the Review Readiness Dashboard for it and falls back to its own pre-landing review when it is missing.
  </Card>

  <Card title="/plan-design-review" icon="paintbrush">
    **Senior designer mode.** Rates each design dimension 0 to 10, explains what a 10 looks like, then edits the plan to get there. Detects "AI slop" patterns.
  </Card>

  <Card title="/plan-devex-review" icon="users">
    **DX lead mode.** Interactive review that explores personas, benchmarks against competitors, designs magical moments, and traces friction. Three modes. Expansion, Polish, Triage.
  </Card>

  <Card title="/design-consultation" icon="swatch-book">
    **Design partner.** Builds a complete design system from scratch. Typography, color, spacing, motion. Writes `DESIGN.md` as the project's design source of truth.
  </Card>
</CardGroup>

## Build and Review

<CardGroup cols={2}>
  <Card title="/review" icon="search-check">
    **Paranoid staff engineer.** Finds the bugs that pass CI but blow up in production. N+1 queries, race conditions, enum gaps, escaping bugs. Auto-fixes mechanical issues. Batches judgment calls.
  </Card>

  <Card title="/investigate" icon="microscope">
    **Systematic debugger.** Iron Law. No fixes without root-cause investigation. Three-strike rule on failed hypotheses. Auto-freezes edits to the affected module.
  </Card>

  <Card title="/design-review" icon="eye">
    **Designer who codes.** 80-item visual audit on a live site, then a fix loop with atomic commits and before/after screenshots.
  </Card>

  <Card title="/devex-review" icon="play">
    **DX tester.** Walks the actual onboarding flow, measures time-to-hello-world, screenshots errors, compares results against `/plan-devex-review` scores.
  </Card>

  <Card title="/design-shotgun" icon="shuffle">
    **Design explorer.** Generates AI mockup variants (default 3, up to 8 for important screens), opens a side-by-side comparison board in the browser, iterates until the user approves. Taste memory learns preferences across sessions.
  </Card>

  <Card title="/design-html" icon="code">
    **Design engineer.** Generates production HTML using Pretext computed layout. Text actually reflows on resize. Heights adjust to content. 30 KB overhead, zero dependencies.
  </Card>
</CardGroup>

## Test

<CardGroup cols={2}>
  <Card title="/qa" icon="bug">
    **QA lead.** Tests a live site, fixes bugs with atomic commits, auto-generates regression tests, re-verifies. Self-regulates with a WTF-likelihood heuristic that caps at 50 fixes.
  </Card>

  <Card title="/qa-only" icon="clipboard-list">
    **QA reporter.** Same methodology as `/qa` but report-only. Use when a pure bug list is wanted without any source-code edits.
  </Card>

  <Card title="/pair-agent" icon="link">
    **Cross-vendor agent orchestrator.** Shares the browser with OpenClaw, Codex, Cursor, or Hermes through a scoped token plus an optional ngrok tunnel. Each agent gets its own tab.
  </Card>

  <Card title="/cso" icon="shield-alert">
    **Chief Security Officer.** Fifteen-phase audit. Secrets archaeology, dependency supply chain, CI/CD security, LLM-specific risks, OWASP Top 10, STRIDE threat modeling.
  </Card>
</CardGroup>

## Ship

<CardGroup cols={2}>
  <Card title="/ship" icon="rocket">
    **Release engineer.** Twenty sequential steps. Merge base, run tests and evals, audit coverage, plan-completion audit, pre-landing review, version bump, bisectable commits, push, document, open PR.
  </Card>

  <Card title="/land-and-deploy" icon="ship">
    **Release engineer (post-merge).** Merges the PR, waits for CI, waits for deploy, runs canary checks. One command from "approved" to "verified in production."
  </Card>

  <Card title="/canary" icon="activity">
    **Site reliability engineer.** Post-deploy monitoring loop. Console errors, performance regressions, visual diffs against a pre-deploy baseline.
  </Card>

  <Card title="/benchmark" icon="gauge">
    **Performance engineer.** Baselines page load times, Core Web Vitals, and resource sizes. Compares before and after on every PR.
  </Card>
</CardGroup>

## Document and Reflect

<CardGroup cols={2}>
  <Card title="/document-release" icon="file-pen-line">
    **Technical writer.** Cross-references the diff against every `.md` file in the project. Updates README, ARCHITECTURE, CONTRIBUTING, CLAUDE.md as needed. Catches stale architecture diagrams.
  </Card>

  <Card title="/document-generate" icon="book-marked">
    **Documentation author.** Diataxis-framework generator. Tutorial, how-to, reference, and explanation pages produced from the code itself.
  </Card>

  <Card title="/retro" icon="calendar-clock">
    **Engineering manager retrospective.** Team-aware weekly summary. Commits, LOC, test ratio, hotspots, per-person praise plus growth opportunities. `/retro global` runs across all projects. Stores JSON snapshots for trend lines.
  </Card>
</CardGroup>

***

## The eight power tools

<CardGroup cols={2}>
  <Card title="/codex" icon="brain-circuit">
    **Second opinion.** Wraps OpenAI Codex CLI with three modes. Review (pass/fail gate), challenge (adversarial), consult (open conversation with session continuity). Cross-model overlap analysis when both `/review` and `/codex` have run.
  </Card>

  <Card title="/careful" icon="circle-alert">
    **Safety guardrails.** `PreToolUse` hook that warns before `rm -rf`, `DROP TABLE`, `git push --force`, `git reset --hard`, `kubectl delete`, `docker system prune`. Override any warning.
  </Card>

  <Card title="/freeze" icon="lock">
    **Edit lock.** Blocks `Edit` and `Write` outside a specified directory. Prevents Claude from "fixing" unrelated code while debugging.
  </Card>

  <Card title="/guard" icon="shield">
    **Full safety.** `/careful` plus `/freeze` combined. Maximum protection for production work.
  </Card>

  <Card title="/unfreeze" icon="lock-open">
    **Unlock.** Removes the `/freeze` boundary, returning to unrestricted edits.
  </Card>

  <Card title="/open-gstack-browser" icon="monitor">
    **GStack Browser.** Launches a visible Chromium with the sidebar extension auto-loaded. Anti-bot stealth, auto model routing (Sonnet for actions, Opus for analysis), one-click cookie import.
  </Card>

  <Card title="/setup-deploy" icon="server-cog">
    **Deploy configurator.** One-time detection of the deploy platform (Fly.io, Render, Vercel, Netlify, Heroku, or GitHub Actions) and the production URL.
  </Card>

  <Card title="/gstack-upgrade" icon="refresh-cw">
    **Self-updater.** Detects global versus vendored install, runs the upgrade, syncs both copies if dual-installed, prints the changelog.
  </Card>
</CardGroup>

***

## The fifteen supporting skills

Infrastructure and orchestration layer. `/browse` powers every QA flow. `/learn` is the institutional memory every other skill writes to and queries from. `/autoplan` runs the full review gauntlet automatically.

<CardGroup cols={2}>
  <Card title="/browse" icon="globe">
    **Headless browser primitive.** Powers `/qa`, `/design-review`, `/canary`, `/benchmark`, `/devex-review`. Roughly 100 ms per call after warm-up.
  </Card>

  <Card title="/autoplan" icon="workflow">
    **Review pipeline orchestrator.** Reads every plan-review skill file from disk and runs CEO, then Design, then Eng, then DX sequentially. Auto-decides via six encoded principles. Surfaces only taste decisions for user approval.
  </Card>

  <Card title="/setup-browser-cookies" icon="cookie">
    **Session manager.** Imports cookies from Chrome, Arc, Brave, or Edge via the macOS Keychain into the headless Playwright session.
  </Card>

  <Card title="/setup-gbrain" icon="database">
    **Semantic memory onboarding.** Installs gbrain (local PGLite or Supabase) and registers it as an MCP tool for cross-machine memory sync.
  </Card>

  <Card title="/sync-gbrain" icon="refresh-ccw">
    **Index refresh.** Re-indexes the repository into gbrain's native code surfaces. `code-def`, `code-refs`, `code-callers`, `code-callees`.
  </Card>

  <Card title="/learn" icon="brain">
    **Institutional memory manager.** Review, search, prune, and export the per-project learnings JSONL. Other skills append to it automatically and query it via the `{{LEARNINGS_SEARCH}}` template at the right moments in their prompts.
  </Card>

  <Card title="/plan-tune" icon="sliders-horizontal">
    **Question sensitivity.** Per-question AskUserQuestion preferences. Mark never-ask, always-ask, or only-for-one-way-doors. Observational profile of declared versus inferred behavior.
  </Card>

  <Card title="/context-save" icon="save">
    **State capture.** Saves git state, decisions made, and remaining work so a future session can resume, even across Conductor workspace handoffs.
  </Card>

  <Card title="/context-restore" icon="history">
    **State restore.** Loads the most recent saved context across all branches and presents the resume summary.
  </Card>

  <Card title="/health" icon="heart-pulse">
    **Code-quality dashboard.** Composite weighted 0 to 10 score across type checker, linter, tests, and dead-code detection. Tracks trends over time.
  </Card>

  <Card title="/landing-report" icon="layout-dashboard">
    **Version queue snapshot.** Read-only dashboard of which `VERSION` slots are claimed by open PRs and which sibling Conductor worktrees have WIP.
  </Card>

  <Card title="/benchmark-models" icon="chart-bar">
    **Cross-model benchmark.** Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini. Compares latency, tokens, cost, and optional LLM-judge quality.
  </Card>

  <Card title="/make-pdf" icon="file-text">
    **Publication-quality PDF.** Turns any markdown file into a Faber and Faber-style PDF with 1-inch margins, page numbers, cover pages, clickable TOC.
  </Card>

  <Card title="/scrape" icon="download">
    **Read-only web scraping.** First call prototypes via `$B` primitives (around 30 seconds). Subsequent calls on a matching intent run the codified skill in around 200 ms.
  </Card>

  <Card title="/skillify" icon="package">
    **Codifier.** Walks back through the conversation, locates the last `/scrape` prototype, synthesizes a Playwright-via-`browse-client` script plus test plus fixture, and writes a permanent browser-skill on disk after the test passes.
  </Card>
</CardGroup>