# shadcn-plan-summary

shadcn-plan-summary — a command that captures decisions from UI architecture sessions. Extracts choices about layout, flows, API integration, and state management, then compiles them into a structured report for the next development phase.

- 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-plan-summary.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-plan-summary

## What it does

shadcn-plan-summary processes the full conversation history about interface design for an MVP: requirements, user screens, workflows, API integration strategy, and state handling. It identifies decisions by topic (responsiveness, accessibility, security), aligns them with model recommendations, and builds a structured markdown summary.

The output has four sections: enumerated decisions made during discussion, matched recommendations, a detailed planning summary (requirements, screens, integrations, gaps), and unresolved issues. This gives developers a solid starting point for implementation without losing the context of earlier design choices.

The command runs inside Claude Code and works best when your conversation history includes the product requirements document, tech stack, API plan, and the full Q&A exchange about UI architecture.

## Install

### Claude Code (native platform)

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

### Codex

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

### GitHub Copilot

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

### Gemini CLI

**Manually: put the files in place**
- File: `.gemini/commands/shadcn-plan-summary.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-plan-summary.md

## When to use it
- extract decisions from a long UI design conversation
- align interface architecture choices with best practices
- identify gaps before coding begins
- hand off planning results to the implementation phase

## Example prompts
- Run shadcn-plan-summary to pull together our UI architecture discussion into one report
- Use shadcn-plan-summary to capture all the interface design decisions we made
- Generate a structured summary of this planning session with shadcn-plan-summary

## Similar
- [alan-plan](https://affpapa.org/en/nevibecode/skills/alan-plan.md) — skill · 1800 installs
- [plan-harder](https://affpapa.org/en/nevibecode/skills/plan-harder.md) — skill · 1200 installs
- [exec-plan](https://affpapa.org/en/nevibecode/skills/exec-plan.md) — skill · 239 installs
- [plan](https://affpapa.org/en/nevibecode/commands/plan.md) — command · ★ 28179 repo stars
- [update-implementation-plan](https://affpapa.org/en/nevibecode/skills/update-implementation-plan.md) — skill · 11107 installs
- [Implementation Plan Generation Mode](https://affpapa.org/en/nevibecode/agents/implementation-plan-generation-mode.md) — subagent · ★ 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
