KS
Killer-Skills

plan-app — how to use plan-app how to use plan-app, plan-app setup guide, what is plan-app, plan-app alternative, plan-app vs Claude Code, plan-app install, guided app planning, parallel sub-agent execution, Claude Code training

v1.0.0
GitHub

About this Skill

Perfect for Development Agents needing rapid app prototyping and guided planning capabilities. plan-app is a skill that provides a workshop setup bootstrap for Claude Code training, guiding developers through a phased approach to build a complete app.

Features

Executes a phased approach with mandatory flow
Reads reference files in MD format, such as `reference/01-interview.md`
Supports parallel sub-agent execution for efficient app building
Guides developers through an interview phase to understand app concepts
Enables developers to describe the app concept back to users

# Core Topics

teren-papercutlabs teren-papercutlabs
[0]
[0]
Updated: 3/6/2026

Quality Score

Top 5%
26
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add teren-papercutlabs/pcl-workshop-setup/plan-app

Agent Capability Analysis

The plan-app MCP Server by teren-papercutlabs is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use plan-app, plan-app setup guide, what is plan-app.

Ideal Agent Persona

Perfect for Development Agents needing rapid app prototyping and guided planning capabilities.

Core Value

Empowers agents to build complete apps in ~2 hours through guided planning and parallel sub-agent execution, utilizing reference files and phased development, including interview, analysis, and execution phases.

Capabilities Granted for plan-app MCP Server

Rapidly prototyping mobile apps
Guiding developers through app planning
Executing parallel sub-agent tasks for efficient development

! Prerequisites & Limits

  • Requires ~2 hours of development time
  • Guided planning and parallel execution must be followed in order
Project
SKILL.md
2.5 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Plan App

Build a complete app in ~2 hours through guided planning and parallel sub-agent execution.

Flow (MANDATORY - IN ORDER)

Complete each phase before moving to the next. Read the reference file at the START of each phase.

Phase 1: INTERVIEW

Read: reference/01-interview.md When: Immediately after skill invoked Goal: Understand what they want to build, who uses it, core use cases Done when: You have clear app concept and can describe it back to them

Phase 2: SCREEN FLOWS

Read: reference/02-screen-flows.md When: Interview complete Goal: Create wireframes + user journeys (combined, not separate) Done when: Participant approves the screen flows

Phase 3: DECOMPOSITION

Read: reference/03-decomposition.md When: Screen flows approved Goal: Split work into Foundation + Feature agents Done when: Sub-agent MD files written to /docs/agents/

Phase 4: DISPATCH

Read: reference/04-dispatch.md When: MD files ready Goal: Run Foundation agent, then feature agents in parallel (same repo, file ownership prevents conflicts) Done when: All sub-agents have returned

Phase 5: TESTING

Read: reference/05-testing.md When: All sub-agents complete Goal: Automated verification + user testing Done when: All checks pass, user confirms it works

Phase 6: DEPLOY

Read: reference/06-deploy.md When: Testing complete Goal: Deploy to Vercel Done when: App running on Vercel with live URL

Project Location

Create the project folder in the current working directory. Use a slugified version of the app name:

  • "Campaign Archive" → ./campaign-archive/
  • "Team Wiki" → ./team-wiki/

Do not ask the user where to put it. Just create it in the current directory.

Hard Limits

Enforce these during interview. If app exceeds limits, help them cut scope.

  • Max 4 screens
  • Max 2 tables
  • Max 2 external APIs

Tech Stack (Non-negotiable)

Do not offer choices. These are prescribed:

  • Framework: Next.js (App Router)
  • Database: Supabase (via Vercel integration)
  • UI: ShadCN
  • Auth: Supabase Auth with email/password (if needed)
  • Hosting: Vercel

Planning Outputs

All written to /docs/ in the project:

FileContents
/docs/screen-flows.mdWireframes + user journeys (approved by participant)
/docs/agents/foundation.mdFoundation agent brief
/docs/agents/feature-*.mdFeature agent briefs (one per feature)

Related Skills

Looking for an alternative to plan-app or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication