Agent skill · gstack
/office-hours Pressure-test an idea before your agent writes any code
Office hours casts the agent as a startup advisor who questions the problem before any solution. It sorts you into startup or builder mode, asks hard questions one at a time, challenges the premises, offers two or three approaches with effort and risk, and ends with a design document plus a concrete next action. Later planning skills read that document.
Works with
- Claude Code
- Codex, Cursor, OpenCode, Gemini CLI and other agents
Used forPlanning and specs
When to use it
- You have a product idea and are not sure it is the right problem to solve.
- You are about to start a feature and want the scope and approach agreed first.
- You want a written design doc that plan reviews and QA can build on.
How it works
- 1Gather context
The agent reads CLAUDE.md, TODOS.md and recent git history, lists earlier design docs and asks what your goal is.
- 2Question by mode
Startup and internal projects get a diagnostic of forcing questions; hackathons, learning and side projects get a brainstorming partner.
- 3Challenge premises
It states the premises behind the idea and asks you to agree or disagree with each before moving on.
- 4Compare approaches
It lays out at least a minimal option and an ideal-architecture option with effort, risk, pros and cons, then waits for your pick.
- 5Write the design doc
After approval it records the decisions, the signals it noticed and a real-world assignment for you.
What it steers the agent away from
- Writing code or scaffolding during the planning session.
- Batching several questions into one prompt.
- Searching the web with your stealth product name instead of general category terms.
Install this skill
It installs with the gstack pack.
Claude CodeThe README wraps this command in a prompt you paste into Claude Code, which also adds a short gstack section to CLAUDE.md.
git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setupClaude Code (team mode for a shared repo)Run inside your repo; it commits a bootstrap so teammates get gstack with auto-updates, and needs Node.js for the required hook.
(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"Codex, Cursor, OpenCode, Gemini CLI and other agentsUse --host auto for every detected agent or name one host; non-Claude hosts are listed as experimental.
git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/gstack
cd ~/gstack && ./setup --host auto # or: ./setup --host codex
./setup --status # one row per install: host, tier, scope, version, pathCommands come from the author’s README; check it for changes before you run them.
Questions
What if I already have a full plan?
It skips the questioning phase but still challenges the premises and makes you compare alternatives before writing the doc.
Does it share my idea with search engines?
Only after you agree, and it searches generalised category terms rather than your product name or concept.
More guides from gstack
/csoRun a security audit that keeps evidence separate from claimsAudits code, infrastructure, supply chain or skills for exploitable defects, challenges each finding and can reproduce fixes in Docker.Read the guide →/plan-ceo-reviewReview a plan for scope and ambition like a founderReviews a plan as a founder would, in expansion, selective, hold or reduction mode, and asks before adding or cutting any scope.Read the guide →/plan-eng-reviewLock architecture, edge cases and tests before you buildLocks a plan's architecture, data flow, edge cases and test coverage, with ASCII diagrams and a review report appended to the plan.Read the guide →/qaFind, reproduce and fix bugs with regression testsTests a site, API, CLI, job or webhook, reproduces each bug, writes a regression test first and commits each verified fix.Read the guide →/reviewCatch production bugs in a diff before it mergesReviews a branch diff for bugs that pass CI, dispatches specialist and adversarial passes, auto-fixes obvious issues and asks about the rest.Read the guide →/shipTake a branch from finished code to an open PRMerges the base branch, runs tests and reviews, bumps VERSION and CHANGELOG, verifies the frozen content, pushes and opens a PR.Read the guide →
Also in this pack
/benchmarkMeasures page load timings, Core Web Vitals and resource sizes in a real browser and compares them with a saved baseline.↗/browseDrives a real browser, preferring your signed-in Aside sessions, to open pages, click through flows, read the console and take screenshots.↗/canaryWatches a live URL after a deploy for console errors, failed pages and visual changes against baseline screenshots.↗/carefulWarns before destructive commands such as recursive deletes, dropped tables or force pushes, and hard-blocks the riskiest ones.↗/codexGets an independent review, challenge or consultation from the OpenAI Codex CLI and presents its output unedited.↗/design-consultationResearches your product space and proposes a full design system, written to a DESIGN.md file with font and colour previews.↗/design-htmlTurns an approved mockup into production HTML and CSS with computed text layout, detecting React, Svelte or Vue.↗/design-reviewAudits a live site for spacing, hierarchy and generated-looking patterns, then fixes them with atomic commits and before and after screenshots.↗/design-shotgunProduces several AI design mockups side by side in a browser board, collects your feedback and iterates until you pick a direction.↗/devex-reviewTests a developer product live by following its docs and getting-started flow, timing each step and comparing against the plan's scores.↗/diagramTurns an English description into a mermaid source, an editable Excalidraw file and rendered SVG and PNG, offline.↗/document-releaseChecks project docs against what changed in a release and updates the facts, asking about subjective edits.↗
Summary by trendhub. The skill itself lives in garrytan/gstack/office-hours by Garry Tan (MIT); read the full, current text there.