AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Prototype

skill-kriscard-skills-prototype · by kriscard

>-

No reviews yet
0 installs
38 views
0.0% view→install

Install

$ agentstack add skill-kriscard-skills-prototype

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets Used
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-kriscard-skills-prototype)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Prototype? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Prototype Workflow

Structured path from idea → working MVP. Most side projects die in "where do I even start" — this is the scaffolding. Discard it once momentum exists.

Phase 0 — Scope Calibration

Ask first. The answer changes everything.

> "Is this a quick side project or something you want to take seriously?"

  • Side project / weekend hack: skip formality, move fast, Phase 3 is a

one-liner, deployment is optional for now

  • Serious startup / real product: run all phases with full depth

Phase 1 — Clarify the Idea

3 questions max. Don't proceed until all 3 have clear answers.

  1. Who is this for? (specific person/role, not "everyone")
  2. What's the one thing it does? (if you need "and", it's two products)
  3. What does "done" look like for v1? (the minimum that a real user could

actually use)

If the user can't answer #2 without "and", help them cut.

Phase 2 — Tech Stack

Recommend based on project type and stated skills. Offer 2 options with honest trade-offs — don't just list everything.

Web app (default for solo dev speed):

  • Next.js + Vercel — fastest from zero to deployed, great DX, edge-ready
  • SvelteKit + Vercel — smaller bundle, less ecosystem, better if React fatigue

API / backend:

  • Hono + Bun — fast, minimal, TypeScript-first, great for side projects
  • FastAPI — Python, better if the user has ML or data science adjacent work

Mobile:

  • Expo (React Native) — ship to iOS + Android from one codebase, Vercel-style

DX for mobile

CLI:

  • Node.js + commander — if the user knows JS
  • Python + click or Typer — if the user knows Python

Database (don't overcomplicate v1):

  • Turso (libSQL) or Neon (Postgres) + Drizzle ORM — serverless, free tier
  • Supabase — if auth + realtime + storage are needed out of the box

State the trade-off plainly: "Next.js is the default because it ships fastest. Use SvelteKit if bundle size is a constraint or you dislike React's mental model."

Phase 3 — Architecture

One-paragraph overview only. No architecture astronautics.

Cover:

  • Data model (3–5 entities max for v1)
  • Key routes or components
  • Auth approach (no auth / magic link / OAuth — pick based on audience)

If the user is over-engineering, say so: "You don't need a message queue for an MVP with 10 users."

Phase 4 — Implementation

Use the Task tool to spawn a coder subagent with full context:

  • Stack decision + rationale
  • Data model
  • V1 scope (the "done" definition from Phase 1)

Set up in order: repo → CI if needed → core feature → README.

Phase 5 — Ship Checklist

Before declaring done:

  • [ ] Env vars not committed (.env in .gitignore)
  • [ ] Domain configured (or Vercel preview URL is fine for MVP)
  • [ ] Basic error monitoring (Sentry free tier — 5 min setup)
  • [ ] Rate limiting on public endpoints (Upstash is free + easy)
  • [ ] Analytics if you need user data (Vercel Analytics or Plausible)
  • [ ] README with one-liner description and setup instructions

Skip items that don't apply to a side project — the checklist is a prompt, not a requirement.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.