gstack turns Claude Code from one generic assistant into a team of specialists you can summon on demand. Six opinionated workflow skills for Claude Code. Plan review, code review, one-command shipping, browser automation, and engineering retrospectives — all as slash commands.
Splitting planning, review, and shipping into separate slash commands is a great design choice. We've seen the same pattern in our own agent workflows: a single generic session trying to hold architecture context while also line-editing code always degrades quality on both fronts.
How does GStack handle state handoff between skills? For example, if /plan produces a spec, does /ship automatically pick up that context or do you need to manually bridge them?
The separation of planning, review, and shipping into distinct slash commands is a smart design choice. We've seen the same pattern in our own agent workflows — a single generic session trying to hold architecture context while line-editing code always degrades quality.
How does GStack handle state handoff between skills? For example, if /plan produces a spec, does /ship automatically pick up that context or do you need to manually bridge them?
The real gem here isn't just replicating Garry's setup—it's that someone finally packaged the actual prompt engineering patterns that separate "AI writes hello world" from "AI builds production features." I've been manually maintaining a similar Claude configuration for months and the context switching overhead is brutal. Does this handle multi-file refactoring across large codebases, or is it optimized for the YC startup sweet spot of <50 file projects?
This is exactly the direction Claude Code needs to evolve. I've been building native macOS apps (SwiftUI + AppKit) entirely with Claude Code and the biggest lesson matches what GStack is doing — you need structured roles, not a single "do everything" agent.
My setup uses a similar pattern: separate skills for planning, implementation, and code review, plus a CLAUDE.md that enforces TDD and incremental commits. The game changer was adding hooks (PostToolUse, Stop) for automated checks — so the agent can't ship code that doesn't compile or pass linting.
One thing I'd love to see in GStack: a "native app" skill that understands platform-specific constraints. Web devs can iterate fast with hot reload, but when you're building for macOS/iOS, the feedback loop is longer and the agent needs to be more cautious about breaking changes.
The headless browser piece with bun runtime is clever — that's been a gap in most setups. Great launch!
Who is Garry tan? This is like your average golfer buying the tiger woods edition putter. Assuming Garry is good at…whatever it is that he does, he could probably do it on a 2015 MacBook Air and sublimetext.
we arrived at the same pattern independently building health data infrastructure. curious how /browse handles auth behind enterprise tenant boundaries, we test clinical platforms behind NHS and pharma logins.
Just got here to support the legend Garry who’s now back to coding like he’s 21. Keep up the great momentum G!
This is amazing, Garry!
I am curious how you use it. do you usually run things sequentially, or is it parallel most of the time? And in the parallel case, how do you keep the flow in sync when each sub-agent is continuously making changes- do you use git worktree?
Really impressed by the slash command architecture. Treating these as specialized teammates you can summon instantly is exactly right. The separation of plan review from code review catches problems early. How do you handle priority when multiple skills could apply?
The slash command approach resonates with how we've been running Claude Code autonomously. We built 100+ SKILL.md files over 108 hours of unattended operation and the key insight was exactly this: specialized roles outperform a single generic agent. The biggest win was separating "plan review" from "code review" — when Claude tries to do both in one pass, it either rubber-stamps or gets lost in details. Question for the team: does GStack handle context window pressure when running multiple skills in sequence? That's been our main scaling challenge.
Why is this on Product Hunt? This is a bunch of prompts. You have got to be kidding.
Cool to see you launching this! Very useful too - I've already pulled in a few of these for my setup.
"Planning is not review. Review is not shipping. Founder taste is not engineering rigor. If you blur all of that together, you usually get a mediocre blend of all four."
I resonate with this so hard. Agents (like humans) can't perform as well when they wear too many hats. The future is coordinating teams of specialized agents like this with just the right amount of human in the loop.
That means you can have one session running /qa on staging, another doing /review on a PR, a third implementing a feature, and seven more working on other branches. All at the same time.
It's a freeing feeling when your workflows reach this level of parallelization. The productivity gains are insane.
Can't wait to try these out in Birdhouse. Thanks for sharing!
Nice to see Gary get the founder spotlight again. The amount of products he’s hunted and helped push to #1 is crazy.
I’ll be giving this stack a try! Congrats on the launch.
Splitting planning, review, and shipping into separate slash commands is a great design choice. We've seen the same pattern in our own agent workflows: a single generic session trying to hold architecture context while also line-editing code always degrades quality on both fronts.
How does GStack handle state handoff between skills? For example, if /plan produces a spec, does /ship automatically pick up that context or do you need to manually bridge them?