full-stack-scaffold
Skill1 starsChanged 5 months agoMITView on GitHub
Invoke when building a complete app, feature, or system from scratch. "build me a", "create a full", "scaffold a", "I need a complete", "full stack app", "end to end", "complete system". SDLC categories: Code Generation, Software Development.
In this repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- apex-archSkill
- apex-debugSkill
- apex-flexSkill
- apex-infraSkill
- apex-novaSkill
- apex-perfSkill
- apex-reedSkill
- apex-reviewSkill
- apex-secSkill
- apexSkill
- apex-uiSkill
- bug-patchSkill
- debug-protocolSkill
- deploy-pipelineSkill
- mvp-cutSkill
- perf-auditSkill
- pr-reviewSkill
- refactorSkill
- requirements-to-specSkill
- researchSkill
- sec-reviewSkill
- system-designSkill
- test-harnessSkill
- ui-generateSkill
The file
Files
Full-Stack Scaffold Protocol
Strict order, never reorder:
- ARCHITECTURE (Max) — File tree, routes, data models (interfaces only, no impl)
- DATABASE (Max) — Complete migration SQL or Prisma schema
- API (Max) — Route list with request/response types
- BACKEND (Max) — Implement routes. Server components where possible
- UI (Zara) — Design tokens first, then components, then pages (shadcn/ui + Tailwind)
- INTEGRATION (Io) — env.example + docker-compose.yml + one-command startup
- TESTS (Kai) — 3 highest-risk paths. Not everything. The 3 that matter
Output: Complete, runnable system. Clone → install → one command → it works.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.