# shadcn-view-plan

shadcn-view-plan — a Claude Code command that produces a structured implementation plan for a single frontend view and writes it to .ai/{view}-view-implementation-plan.md.

- command · `type=command` · Claude Code, Codex, GitHub Copilot, Gemini CLI · ★ 267 repo stars
- Author: przeprogramowani
- License: AGPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/przeprogramowani/ai-rules-builder/tree/HEAD/.claude/commands/shadcn-view-plan.md
- Updated: 2026-02-20
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/commands/shadcn-view-plan

## What it does

The command works through seven placeholders that reference project files: `prd.md`, a view description from `ui-plan.md`, endpoint specs from `api-plan.md`, endpoint implementations such as `@generations.ts` or `@flashcards.ts`, `types.ts`, and `tech-stack.md`. Before writing the plan, the agent runs an internal breakdown inside `<implementation_breakdown>` tags — that analysis stays out of the final file.

The output covers component hierarchy, per-component details including HTML elements and props, DTO and ViewModel types, state management, API integration with request and response types, user interaction handling, validation conditions, error scenarios, and a step-by-step implementation guide. All of this is written in Polish — the prompt hardcodes the output language.

Every placeholder must be filled before the command runs: missing `prd.md` or an empty view description from `ui-plan.md` will leave sections blank.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/commands/shadcn-view-plan.md` — Call it with /shadcn-view-plan. For all projects use ~/.claude/commands/

### Codex

**Manually: put the files in place**
- File: `~/.codex/prompts/shadcn-view-plan.md` — Call it with /prompts:shadcn-view-plan. Codex marks this format deprecated in favour of skills

### GitHub Copilot

**Manually: put the files in place**
- File: `.github/prompts/shadcn-view-plan.prompt.md`

### Gemini CLI

**Manually: put the files in place**
- File: `.gemini/commands/shadcn-view-plan.toml` — Gemini stores commands as TOML: the prompt text goes into the prompt field

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/przeprogramowani/ai-rules-builder/tree/HEAD/.claude/commands/shadcn-view-plan.md

## When to use it
- generate a view implementation plan before writing any code
- break a UI screen into components with props and event descriptions
- document DTOs and ViewModels for a specific frontend route
- map PRD user stories to concrete components and functions
- describe API endpoint integration at the frontend layer

## Example prompts
- Run `/shadcn-view-plan` for the registration screen using `@prd.md` and the view description from `ui-plan.md`
- Build a dashboard view plan from `@tech-stack.md` and the endpoints in `@generations.ts`
- Create `.ai/login-view-implementation-plan.md` from user stories and `@types.ts`

## Similar
- [shadcn-component-discovery](https://affpapa.org/en/nevibecode/skills/shadcn-component-discovery.md) — skill · 773 installs
- [shadcn](https://affpapa.org/en/nevibecode/skills/shadcn-ui-shadcn.md) — skill · 150100 installs
- [shadcn-svelte](https://affpapa.org/en/nevibecode/skills/shadcn-svelte.md) — skill · 7600 installs
- [shadcn-component-boundaries](https://affpapa.org/en/nevibecode/skills/shadcn-component-boundaries.md) — skill · 5700 installs
- [shadcn-vue-skilld](https://affpapa.org/en/nevibecode/skills/shadcn-vue-skilld.md) — skill · 174 installs
- [tanstack-start-shadcn-tailwind](https://affpapa.org/en/nevibecode/rules/tanstack-start-shadcn-tailwind.md) — rule · ★ 41430 repo stars

From the same set: [przeprogramowani/ai-rules-builder](https://affpapa.org/en/nevibecode/by/przeprogramowani/ai-rules-builder.md) — 24 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
