Give your AI coding assistant the habits of a senior engineering team.
One install. Slash commands that take you from a rough idea to a shipped, reviewed pull request.
If you use an AI coding assistant (Claude Code, Cursor, or Kiro), vibestack
adds a menu of expert workflows you trigger by typing /. Instead of "write me
some code," you get /office-hours to shape the idea, /review to catch bugs,
and /ship to open a clean pull request — each one a structured, opinionated
process, not a vague prompt.
For engineers: 50+ portable SKILL.md workflows — planning, TDD, security
audit, cross-model review, debugging, release. Same source installs into Claude
Code, Cursor, and Kiro. No lock-in, no telemetry, state stays in ~/.vibestack/.
Think of it as turning a junior-level "just do it" assistant into one that plans, gets a second opinion, tests, and ships like a team would.
git clone https://github.com/timurgaleev/vibestack ~/.claude/skills/vibestack
~/.claude/skills/vibestack/installThat's it. Open a new session of your agent and type /office-hours:
Before we dig in — what's your goal with this?
Building a startup (or thinking about it)
Hackathon / demo — time-boxed, need to impress
Open source / research — building for a community
Learning — teaching yourself to code, leveling up
Pick a mode and it walks you through the right questions, then saves a design
doc you can hand straight to /plan-eng-review. Every skill works like this —
guided, structured, no filler. If /office-hours clicks, the rest will too.
- 🚀 Idea → shipped, guided the whole way.
/office-hours→/plan-eng-review→/tdd→/review→/ship. The chain is built for you. - 🧠 A real second opinion. Reviews run a cross-model check (a different AI) automatically, so two models have to agree before you ship.
- 🔒 Yours, private. No telemetry, no accounts, no cloud. Everything lives on your machine in
~/.vibestack/. - 🔁 No lock-in. One source installs into Claude Code, Cursor, and Kiro alike. Switch tools, keep your workflow.
- 📋 Copy, run, done. Two commands to install,
git pull && ./installto update. Plain bash, zero runtime dependencies.
One set of skill files installs into whichever agent you use:
flowchart LR
S["📄 One SKILL.md source"] --> I(["./install"])
I --> A["Claude Code"]
I --> B["Cursor"]
I --> C["Kiro"]
A --> U["Type /command → expert workflow runs"]
B --> U
C --> U
Each skill is a plain SKILL.md file your agent discovers and exposes as a
/command. Install writes the file plus links to its helpers — so
git pull && ./install is the entire update story.
53 skills across planning, shipping, QA, design, and security. A few highlights:
| Command | What it does |
|---|---|
/office-hours |
Brainstorm an idea into a concrete design doc |
/plan-eng-review |
Pressure-test a plan — architecture, data, risk |
/tdd |
Test-driven development, red-green-refactor |
/review |
Pre-merge review — correctness, security, tests |
/ship |
Merge base, run tests, review, version bump, open the PR |
/investigate |
Systematic debugging — no fix without a confirmed root cause |
/cso |
Security audit — OWASP Top 10 + threat model |
👉 Full list of every skill: docs/skills.md
./install --target=all # Claude Code + Cursor + Kiro, non-interactive
./install --dry-run # Preview every change, write nothing
git pull && ./install # Update
~/.claude/skills/vibestack/uninstall --target=all # Removedocs/skills.md— all skills, with descriptionsETHOS.md— the five principles behind the designCONTRIBUTING.md— add your own skill in minutesdocs/agent-skills-compatibility-audit.md— per-agent behavior, incl. safety-hook tiersCHANGELOG.md·LICENSE(MIT)
Heads-up: the safety skills (
/careful,/freeze,/guard) enforce hard blocks on Claude Code. On Cursor/Kiro they fall back to a soft LLM nudge — details in the compatibility audit above.
If vibestack saves you time, give it a ⭐ — it's the simplest way to say opinionated workflows beat ad-hoc prompting.