planning — for Claude Code planning, community, for Claude Code, ide skills, auth.uid() = user_id, user_id, created_at, updated_at, develop, checkpoint

v1.0.0

Sobre este Skill

Cenario recomendado: Ideal for AI agents that need planning — app architecture & implementation plan. Resumo localizado: A high-fidelity interaction kit for crafting premium products with taste. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Recursos

Planning — App Architecture & Implementation Plan
Type Input Planning Scope
------ ------- ---------------
Idea → App Store card Full (screens + data + phases)
New feature Feature description Feature scope only

# Core Topics

taewoongheo taewoongheo
[0]
[0]
Updated: 4/4/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 10/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution Quality floor passed for review
Review Score
10/11
Quality Score
52
Canonical Locale
ko
Detected Body Locale
ko

Cenario recomendado: Ideal for AI agents that need planning — app architecture & implementation plan. Resumo localizado: A high-fidelity interaction kit for crafting premium products with taste. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Por que usar essa habilidade

Recomendacao: planning helps agents planning — app architecture & implementation plan. A high-fidelity interaction kit for crafting premium products with taste. This AI agent skill supports Claude Code, Cursor, and

Melhor para

Cenario recomendado: Ideal for AI agents that need planning — app architecture & implementation plan.

Casos de Uso Práticos for planning

Caso de uso: Applying Planning — App Architecture & Implementation Plan
Caso de uso: Applying Type Input Planning Scope
Caso de uso: Applying ------ ------- ---------------

! Segurança e Limitações

  • Limitacao: New feature Feature description Feature scope only
  • Limitacao: Dependencies (do other features require this?)
  • Limitacao: Requires repository-specific context from the skill documentation

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is planning?

Cenario recomendado: Ideal for AI agents that need planning — app architecture & implementation plan. Resumo localizado: A high-fidelity interaction kit for crafting premium products with taste. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

How do I install planning?

Run the command: npx killer-skills add taewoongheo/taste/planning. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for planning?

Key use cases include: Caso de uso: Applying Planning — App Architecture & Implementation Plan, Caso de uso: Applying Type Input Planning Scope, Caso de uso: Applying ------ ------- ---------------.

Which IDEs are compatible with planning?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for planning?

Limitacao: New feature Feature description Feature scope only. Limitacao: Dependencies (do other features require this?). Limitacao: Requires repository-specific context from the skill documentation.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add taewoongheo/taste/planning. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use planning immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

planning

A high-fidelity interaction kit for crafting premium products with taste. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows. Planning —

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Planning — App Architecture & Implementation Plan

Scope Assessment

TypeInputPlanning Scope
Idea → AppStore cardFull (screens + data + phases)
New featureFeature descriptionFeature scope only
RefactoringTarget codeChange scope + migration

Screen Design

Screen & Route (Expo Router)

  • File-based routing: app/(tabs)/, app/(modals)/
  • One route file per screen
  • Leverage nested layouts

UI Pattern Selection (Apple HIG Basis)

Determine navigation, layout, and core components for each screen:

PatternUse Case
Push navigationHierarchical browsing (list → detail)
Modal / Bottom sheetTemporary task, creation
Tab barTop-level section switching
Scroll + sectionsLong content, dashboard
Flat listHomogeneous item listing
GridVisual-centric content
FormInput collection

Data Model

Supabase Design Principles

  • Minimize tables. Pragmatism over normalization.
  • RLS (Row Level Security) required: auth.uid() = user_id
  • Common patterns: user_id, created_at, updated_at

Phase Separation

Priority Criteria

  1. Dependencies (do other features require this?)
  2. Core experience (P0 — without this, it's not the app)
  3. Experience enhancement (P1 — much better with it)
  4. Quality polish (P2 — baseline quality)

Command Recommendations

Task TypeRecommended Command
모든 구현 (로직, UI, 인터랙션)/develop
Step completion/checkpoint

Phase Format

markdown
1### Phase 1: Core (P0) 2- [ ] Task (file: path) 3- [ ] (TDD) Task (file: path) ← 비즈니스 로직 4 5### Phase 2: Interaction (P1) 6- [ ] Task (file: path) 7 8### Phase 3: Polish (P2) 9- [ ] Task (file: path)

(TDD) 기준: 비즈니스 로직 (데이터 처리, 상태 관리, 유틸, 유효성 검증) 안 붙임: UI 렌더링, 인터랙션, 애니메이션, 네비게이션

Checkbox rules:

  • /develop marks - [x] on task completion
  • Running /develop without arguments auto-selects the first - [ ] task

Risk Assessment

TypeQuestion
TechnicalAny first-time libraries/APIs?
PerformanceAny animation-heavy screens?
ScopeWhat can be cut first if time is short?

산출물 포맷

/architect 가 생성하는 문서. pipeline.md의 artifact 계약을 따른다.

PRD.md

markdown
1# [이름] 2 3## 핵심 경험 4## 메타포 5## 화면 목록 6| 화면 | Route | 우선순위 | 7## 아키텍처 8## 데이터 모델 9## 수익화 10## Fidelity Map 11## 완료 기준 12## Non-Goals 13## 의존성

도메인 CLAUDE.md (src/features/[domain]/CLAUDE.md)

markdown
1# [도메인명] 2 3## 역할 4## 컴포넌트 5- 기존 (taste-kit): [wireframe의 data-component에서 추출] 6- 신규: [ComponentName — 용도] 7## 기능 명세 8[유저 행동 → 결과] 9## 태스크 10- [ ] [행동] — [결과물] 11- [ ] (TDD) [행동] — [결과물] 12## 주의사항

Principles

  • Ship fast, iterate with feedback
  • Core features first, interaction layer next
  • One component per file, max 200 lines
  • Split each phase into testable units

Answer in Korean.

Habilidades Relacionadas

Looking for an alternative to planning or another community skill for your workflow? Explore these related open-source skills.

Ver tudo

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

widget-generator

Logo of f
f

Gerar plugins de widgets personalizáveis para o sistema de feed do prompts.chat

flags

Logo of vercel
vercel

O Framework React

138.4k
0
Navegador

pr-review

Logo of pytorch
pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

98.6k
0
Desenvolvedor