garrytan/gstack▌

YC Office Hours with two modes. Startup mode asks six forcing questions around demand reality, status quo, specificity, wedge, observation, and future-fit. Builder mode is for side projects and open source. It saves a design doc and is intended to run before implementation work.

Launches a visible AI-controlled browser window with the GStack sidebar and anti-bot behavior for live observation and control.

Engineering-manager style review that hardens the plan around architecture, boundaries, state transitions, edge cases, tests, and diagrams before coding starts.

Fast headless browser for QA testing, deployment verification, and user flow dogfooding. \n \n Navigate URLs, interact with elements, verify page state, and take annotated screenshots with element labels and reference IDs \n Supports responsive layout testing (mobile/tablet/desktop), file uploads, form validation, and dialog handling with auto-accept \n Includes snapshot diffing to show exactly what changed after interactions, plus console and network inspection for debugging \n Persistent brows

PDF generation skill for turning markdown documents into publication-style PDFs with proper layout, TOC, pagination, and print polish.

Orchestrates CEO, design, eng, and DX reviews from disk and applies internal decision principles to auto-progress the plan, surfacing only taste-sensitive decisions at the end.

Variant-generation workflow for visual exploration. It shows multiple design directions, gathers structured feedback, and iterates toward a preferred direction.

Self-updater for gstack installs, including vendored/global detection and release summary output.

DevEx review for developer-facing products. It explores personas, benchmarks onboarding, and scores friction across APIs, CLIs, SDKs, libraries, docs, and platform flows.

Combines `/careful` and `/freeze` for maximum safety when working in sensitive environments.

Sets a session-wide edit boundary so file changes only happen inside a chosen directory.

Safety hook that intercepts destructive shell commands and asks before running risky operations like recursive delete, data-destruction SQL, reset-hard, or force-push.

Grants browser access to another AI agent with scoped permissions and per-agent tab/session isolation.

Imports cookies from a real browser into the headless browser context so authenticated flows can be tested.

Headless Chromium-based testing browser for screenshots, interaction, layout checking, form handling, and state verification.

After shipping, it syncs README, architecture docs, contributing docs, changelog, and related project documentation to match the current code.

Performance benchmarking skill focused on web loads, Core Web Vitals, and regressions across runs or changes.

Post-deploy monitoring loop that watches a live app for page failures, performance regressions, and console issues.

Continues from `/ship` by merging, waiting for CI/deploy completion, and then verifying production health.

Clears the directory edit boundary previously set by `/freeze`.

Detects platform-specific deployment details and writes the config needed for future `land-and-deploy` runs.

Manages long-lived learnings and recurring patterns that gstack has collected across sessions.

Saves decisions, git state, and pending work so future sessions can resume without reconstructing context from scratch.

Restores saved context, including across branch changes and workspace handoffs.

Weekly engineering retrospective over code activity, trends, and team contributions.

Quality dashboard skill that wraps project checks and reports a weighted health score and trend line.

Handles release preparation steps such as syncing base, running checks, updating release metadata, pushing, and opening the PR.

Wrapper around OpenAI Codex CLI for code review, adversarial challenge mode, and consultation with follow-up continuity.

Same testing methodology as `/qa`, but report-only. It is for bug finding without any code edits.

Cross-model benchmark skill for comparing Claude, GPT/Codex, and Gemini on the same prompt and optionally an LLM-judge quality pass.

Full QA loop that tests the product, fixes discovered issues, re-verifies the fixes, and can generate regression coverage. Supports multiple severity tiers.

Security-audit skill that combines application security, infrastructure review, CI/CD checks, supply-chain scanning, LLM security, OWASP framing, and STRIDE analysis.

Developer-experience audit that actually runs onboarding and documentation flows, measures time-to-happy-path, and compares reality against planning assumptions.

Debugging workflow with an explicit rule: no fixes until the root cause is understood. The flow is investigate, analyze, hypothesize, then implement.

Code-review pass focused on the actual diff, aimed at risks that often survive CI such as SQL safety, trust boundaries, and structural regressions.

Live-site visual QA plus fixes. It looks for spacing, hierarchy, AI slop, consistency, and interaction issues and can iterate with before/after verification.

Converts an approved mockup or design direction into production-oriented HTML/CSS with computed layout and framework-aware output expectations.

Design system creation workflow that researches comparable products, proposes an aesthetic system, and writes `DESIGN.md` as the canonical design source of truth.

Lets users tune how often gstack asks certain planning questions and inspect the psychographic/developer profile inferred from prior interactions.

Interactive design-plan review that scores design quality, identifies unresolved UX issues, and improves the plan before anyone ships UI.

Founder-mode review that asks what product is really being built, not just what feature was requested. Supports scope expansion, selective expansion, hold-scope, and scope-reduction modes.