garrytan/gstack
An opinionated 23-skill suite that staffs a solo developer's agent with the roles a startup would hire: CEO review, design review, eng-manager review, QA, ship, deploy, and retro workflows. Agentiquette scores it 80/100 (A-tier), methodology v1.0, scored 2026-07-07.
Key facts
| Category | Framework |
|---|---|
| License | MIT |
| Maintainer | garrytan |
| Compatible agents | claude-code |
| File patterns | SKILL.md, slash-commands |
| Triggering | slash-command |
| GitHub metrics | 120,130 stars · 17,920 forks · 783 open issues (fetched 2026-07-07) |
| Last commit | 2026-06-25 |
| Created | 2026-03-11 |
Editorial analysis
The strongest workflow coverage in the index: where superpowers encodes engineering process, gstack encodes an entire company's review structure. The ship and QA loops have real verification steps and real exit criteria. Weaknesses: skills are slash-command-first, so nothing fires unless the operator remembers to invoke it, and the suite assumes its own full-stack conventions.
Risks
Deploy and ship skills execute git and shell operations; review the permission footprint before running against production repositories.
Evidence notes: Reliability: ship/QA loops verify outcomes (tests, browser checks) before declaring done. Leverage: one suite covers plan-review through deploy. Composability: skills interlock with each other more than with outside skills. Safety: destructive-command guard exists (/careful, /guard) but is opt-in.
Install and first run
Clone and register the skill directory with your Claude Code project settings.Scored skills in this repo
A complete landing pipeline: detect and merge base branch, run tests, review the diff, bump version, update changelog, commit, push, and…
Drives a headless browser through the running application, systematically exercising flows, logging defects, and fixing what it finds before…
A designer's-eye QA pass over a running interface: visual inconsistency, spacing, hierarchy, and interaction problems found and fixed…
Systematic debugging with root-cause discipline: reproduce, hypothesize, test one variable at a time, and distinguish confirmed from…
Reviews an implementation plan from a founder's perspective: scope, sequencing, user impact, and what to cut, before engineering effort is…
A fast headless-browser capability for QA and dogfooding: navigate, interact, read state, and screenshot the running application from within…
Alternatives in this category
A process-first skill framework for Claude Code: brainstorming, test-driven development, systematic debugging, and verification skills that…
A CLI for configuring Claude Code: install commands, agents, hooks, and settings from a large template catalog, plus usage monitoring.
A configuration framework layering specialized commands and cognitive personas onto Claude Code: an opinionated operating mode rather than a…
Compare with superpowers · Compare with claude-code-templates
Embed this badge
Maintainers of scored entries can embed their live badge; it updates when the score does and links back to this page.
[](https://agentiquette.com/index/repos/gstack)Frequently asked questions
Is garrytan/gstack good?
garrytan/gstack scores 80/100 (A-tier) on Agentiquette's methodology v1.0, scored 2026-07-07. Strengths and weaknesses are in the editorial analysis; the score is explained dimension by dimension in the scorecard.
What is garrytan/gstack for?
An opinionated 23-skill suite that staffs a solo developer's agent with the roles a startup would hire: CEO review, design review, eng-manager review, QA, ship, deploy, and retro workflows.
Is garrytan/gstack maintained?
Last commit 2026-06-25, 783 open issues at fetch time (2026-07-07). Maintenance is scored at 88 of 100.
Maintainer of garrytan/gstack? Claim this listing and suggest corrections.