Skip to content
Agentmart
Submit a tool

shadcnui-component-review

End-to-end review of shadcn/ui components in a component library.

Skill by CambridgeMonorail

IndexedMIT★ 3
Write a review

Chalk Labs

Need help deploying shadcnui-component-review?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/cambridgemonorail-shadcnui-component-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

End-to-end review of shadcn/ui components in a component library. Use when a new or modified shadcn/ui component needs standards review covering categorization, exports, accessibility, tests, and Storybook coverage.

Use cases: design, frontend, testing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/shadcnui-component-review

What's inside

Skill name
shadcnui-component-review
Description
End-to-end review of shadcn/ui components in a component library. Use when a new or modified shadcn/ui component needs standards review covering categorization, exports, accessibility, tests, and Storybook coverage.
License
MIT
Metadata
author: CambridgeMonorail · version: 1.0
Instructions
75 lines in SKILL.md · view on GitHub

Files (8)

  • SKILL.md
  • component.spec.template.tsx · assets/
  • component.stories.template.tsx · assets/
  • a11y-and-focus.md · references/
  • performance-and-bundle.md · references/
  • review-and-fix.md · references/
  • taxonomy-and-exports.md · references/
  • tests-and-storybook.md · references/

SKILL.md (first lines)

# Shadcn UI Component Review Skill

## Purpose

This skill performs an end-to-end review of a newly added or modified shadcn/ui component under your component library directory (e.g., `libs/shadcnui/src/lib`).

It will identify issues, apply straightforward fixes, and leave clear recommendations for anything that requires design decisions or larger refactors.

## When to use

Use this skill when:

- A new component has been added to shadcnui
- An existing component has been modified and needs standards review
- A component needs to be categorized correctly in the components taxonomy
- We want confidence in accessibility, exports, tests, and Storybook coverage

## Inputs required

The user should provide:

- Component path relative to your component library root (example: `data-display/badge`)
- Optional: special concerns (for example, accessibility, API design, variants, performance)

If the component path is missing, infer it from recent changes where possible. If you cannot infer it, ask once and stop.

## Output contract

The agent must output:

1. Actions taken
2. Issues found and fixes applied (with file paths)
3. Summary and next steps
4. Definition of done status

Do not paste full files unless necessary.

## Evidence and verification

After changes, the agent must run the minimum necessary checks to confirm health:

- lint
- typecheck
- tests
- build where relevant

Avoid redundant runs.

## Privacy and safety

Do not output secrets or sensitive data.
If a screenshot or browser tooling is involved elsewhere, use test accounts.

## Reference Files

- [Taxonomy and exports](references/taxonomy-and-exports.md) — category placement rules, barrel export conventions, naming patterns
- [Accessibility and focus](references/a11y-and-focus.md) — ARIA requirements, keyboard navigation, focus management by component type
- [Tests and Storybook](references/tests-and-storybook.md) — test patterns, coverage expectations, Storybook story conventions
- [Performance and bundle](references/performance-and-bundle.md) — tree-shaking, lazy loading, bundle size considerations
- [Review and fix workflow](references/review-and-fix.md) — step-by-step review process, common fixes, checklist

## Definition of done

A component review is “done” when:

- Category placement is correct
- No default exports exist
- Public API is clean (props, naming, variants)
- Accessibility expectations are met for the component type
- Barrel exports are correct
- Tests exist and pass
- Storybook story exists and renders key variants
- Lint and typecheck pass for the affected scope

From CambridgeMonorail/WallRun, MIT.

More from CambridgeMonorail/WallRun

Signals

Stars
3
Forks
0
Open issues
19
Last commit (this folder)
Mar 15, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1.0
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from CambridgeMonorail

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get shadcnui-component-review running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying shadcnui-component-review?

CallGet help
Cite this page

shadcnui-component-review skill. Agent Mart. https://agentmart.dev/skills/cambridgemonorail-shadcnui-component-review (last updated 2026-10-24)