Agent skill

Working With Playground App

by PackmindHub in PackmindHub/packmind

This skill provides guidance for building UI/UX prototypes in the Packmind playground app.

Apache-2.0Auto-check passedFrontend & Design

Install Working With Playground App

skills CLI
$ npx skills add PackmindHub/packmind --skill working-with-playground-app -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install PackmindHub/packmind working-with-playground-app --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/PackmindHub/packmind.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/working-with-playground-app .claude/skills/working-with-playground-app && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
working-with-playground-app
GitHub stars
317
Token cost
~2.1k tokens
SKILL.md length
955 words
Files
2 (incl. references)
Skills in repo
35
Repo updated
First seen
Licence
Apache-2.0

At a glance

This skill provides guidance for building UI/UX prototypes in the Packmind playground app.

  • Works in 3 steps: Create the Prototype Directory → Build the Prototype Component → Register the Prototype
  • Mentions of playground
  • SKILL.md covers Overview, UX Design Thinking, Running the Playground and Creating a New Prototype, plus 2 more sections
  • Calls nx

What it does

Working With Playground App is an agent skill from PackmindHub/packmind. This skill provides guidance for building UI/UX prototypes in the Packmind playground app. It should be used when creating a new prototype, iterating on an existing prototype, or working with files in apps/playground/. Triggers on mentions of "playground", "prototype", or direct work within the apps/playground/ directory.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/frontend-domain-structure.md`).

It sits in Frontend & Design, covering UI design. The repository describes itself as: Packmind seamlessly captures your engineering playbook and turns it into AI context, guardrails, and governance. The licence is Apache-2.0.

When your agent uses it

  • Mentions of playground
  • Direct work within the apps/playground/ directory

Example prompts

  • “playground”
  • “prototype”
  • “/working-with-playground-app”

Requirements

  • Docker

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Create the Prototype Directory
  2. Build the Prototype Component
  3. Register the Prototype

What it can do on your machine

Read from SKILL.md and the folder at commit 67de8a2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • nx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • chakra-ui.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Working With Playground App loads about 2.1k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 955 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~88
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from PackmindHub/packmind at commit 67de8a2, republished under its Apache-2.0 licence (© PackmindHub). 955 words, ~2,111 tokens.

Download SKILL.mdSave it as .claude/skills/working-with-playground-app/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
working-with-playground-app
description
This skill provides guidance for building UI/UX prototypes in the Packmind playground app. It should be used when creating a new prototype, iterating on an existing prototype, or working with files in apps/playground/. Triggers on mentions of "playground", "prototype", or direct work within the apps/playground/ directory.

Working With the Playground App

Overview

The playground app (apps/playground/) is a standalone Vite + React environment for iterating on UI/UX of Packmind features — both new and existing. Prototypes built here are meant to be easily convertible into production-ready code.

UX Design Thinking

Before writing any code, think like a UX designer. The playground exists to explore how a feature feels to use — not just how it looks. Apply these principles to every prototype:

Design All States First

Never prototype only the happy path. Before building, identify and plan for every state the user might encounter:

  • Empty state — What does the user see before any data exists? Guide them toward the first action.
  • Loading state — What appears while data is being fetched? Use skeletons or spinners to set expectations.
  • Populated state — The standard view with data. Test with both minimal and full datasets.
  • Error state — What happens when something fails? Show a clear message and a recovery path.
  • Edge cases — What about a single item? Hundreds? An extremely long name that might overflow?

Prototype each state explicitly — use local state toggles or tabs to let reviewers switch between them.

Use Realistic, Varied Data

Mock data should stress-test the design, not just fill space:

  • Include long names that could wrap or overflow, short names that could look sparse, and special characters.
  • Vary counts: 0 items, 1 item, a handful, and many (50+). Layouts that work for 5 items often break at 50.
  • Include missing optional fields — not every record will be complete.
  • Use recognizable but realistic content so reviewers can evaluate readability, not just layout.
Design for Interaction

Prototypes should be clickable and stateful, not static mockups:

  • Wire up buttons, toggles, and form inputs with local state so reviewers experience the flow.
  • Simulate async operations (e.g., a brief delay before showing a success toast) to prototype timing and feedback.
  • Show what happens after an action — does a list update? Does a confirmation appear? Does the user navigate somewhere?
Establish Visual Hierarchy

Guide the user's eye to what matters most:

  • One primary action per view. If everything is bold, nothing is. Use a primary button for the main action, secondary/ghost for the rest.
  • Group related information with spacing and borders, not just proximity.
  • Size and weight signal importance. Headings, subheadings, and body text should create a clear reading order.
  • Use whitespace deliberately — it separates sections and reduces cognitive load.
Make Affordance Obvious

Users should understand what they can do without instructions:

  • Clickable elements should look clickable. Buttons look like buttons, links look like links.
  • Destructive actions should look dangerous — use red/warning styling and require confirmation.
  • Disabled states should be visually distinct and ideally explain why they're disabled (tooltip or helper text).
  • Feedback should be immediate — hover states, active states, and loading indicators tell the user the system responded.
Manage Information Density

Show enough to be useful, hide enough to avoid overwhelm:

  • Lead with a summary, offer detail on demand. Use accordions, expandable rows, or drill-down views for secondary information.
  • Don't front-load every field. Tables and lists should show the most important 3–5 columns; offer a detail view for the rest.
  • Use progressive disclosure — reveal complexity as the user engages deeper (overview → detail → advanced settings).
Show full SKILL.md (424 more words)Show less
Stay Consistent With the Product

Before designing something new, check how the existing product handles similar patterns:

  • Browse apps/frontend/src/domain/ for existing feature implementations. If a similar interaction exists, match its layout and behavior before inventing alternatives.
  • Reuse established patterns — if the product uses a sidebar + main content layout for listings, don't prototype a card grid for the same type of data without good reason.
  • Follow the same information architecture — similar actions in the same position, similar data in the same format.
  • When diverging from existing patterns, call it out explicitly so reviewers can evaluate the change intentionally.

Running the Playground

To start the playground dev server:

bash
nx dev playground

The app runs on localhost:4300. It is not part of the Docker Compose setup — it runs in isolation via Vite's dev server.

Creating a New Prototype

1. Create the Prototype Directory

Each prototype lives under apps/playground/src/prototypes/. For non-trivial prototypes, create a dedicated folder organized by domain — mirroring the frontend app structure. Consult references/frontend-domain-structure.md for the domain folder list.

apps/playground/src/prototypes/
├── index.ts                          # Prototype registry
├── ButtonsPrototype.tsx              # Simple single-file prototype
└── my-feature/                       # Multi-component prototype
    ├── MyFeaturePrototype.tsx        # Root component (entry point)
    ├── components/
    │   ├── domain-a/
    │   │   ├── SomeComponent.tsx
    │   │   └── AnotherComponent.tsx
    │   └── domain-b/
    │       └── SomethingElse.tsx
    └── types.ts                      # Shared types for this prototype

For simple prototypes (e.g., showcasing a single component), a single file is acceptable.

2. Build the Prototype Component

Create a default-exported React component:

tsx
import { PMBox, PMHeading } from '@packmind/ui';

export default function MyFeaturePrototype() {
  return (
    <PMBox padding="6">
      <PMHeading size="lg">My Feature</PMHeading>
      {/* Prototype content */}
    </PMBox>
  );
}
3. Register the Prototype

Add the prototype to apps/playground/src/prototypes/index.ts:

tsx
import MyFeaturePrototype from './my-feature/MyFeaturePrototype';

export const prototypes: Prototype[] = [
  // ... existing prototypes
  {
    name: 'My Feature',
    description: 'Optional description',
    component: MyFeaturePrototype,
  },
];

The prototype will appear in the dropdown selector in the playground nav bar.

Mandatory Rules

Data
  • Always use stub/mock data. Never make actual calls to the backend. Define realistic mock data inline or in a dedicated data.ts file within the prototype folder.
Dependencies
  • Never install new dependencies without explicit user approval.
  • Never modify files outside apps/playground/. No changes to other apps or packages.
Reusing Existing Code
  • Prototypes can import presentational components and types from the frontend app (apps/frontend/src/) and shared type packages (packages/).
  • Prototypes must not import services, gateways, hooks with side effects, or anything that calls the backend.
UI Components
  • Use PM* components from @packmind/ui (e.g., PMBox, PMButton, PMHeading, PMVStack, PMHStack, PMText).
  • When a needed component is not available in the Packmind UI kit, browse Chakra UI v3 components for reference, then map to the corresponding PM* wrapper before using. If no wrapper exists, ask the user before using the raw Chakra component.
  • Icons come from react-icons/lu (Lucide icons, prefixed with Lu).
Code Quality
  • Prototypes must be production-ready in structure. Follow React best practices: split responsibility, create as many components as needed, organize by domain.
  • Use useState, useCallback, useMemo for local state and performance.
  • Define TypeScript types for all data structures.
  • Keep components focused — each component should have a single responsibility.

Resources

references/
  • frontend-domain-structure.md — Domain folder structure from the frontend app, to guide component organization in prototypes.

© PackmindHub, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in .agents/skills/working-with-playground-app of PackmindHub/packmind.

  • SKILL.md
  • references/frontend-domain-structure.md

Open the folder on GitHubat commit 67de8a2

Compare with similar skills

Working With Playground App next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Working With Playground App compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Working With Playground App this skillPackmindHub/packmind317—~2.1kAutomated safety check: PassApache-2.0
Lofisu Personazclllyybb/lofisu-identity-engine454—~2.8kAutomated safety check: PassUnlicense
Liteyuki Webui FrontendLiteyukiStudio/LiteyukiBot157—~2.5kAutomated safety check: PassCustom licence
Fix PR Design Notesdifferent-ai/openwork24k—~824Automated safety check: PassCustom licence
Refactoring UI Designchaxus/ran271—~1.9kAutomated safety check: PassMIT
Live UX PolishEveryInc/compound-engineering-plugin25k—~777Automated safety check: PassMIT

Similar skills

  • Lofisu Persona

    zclllyybb/lofisu-identity-engine

    LofiSu的行为人格Skill。基于GitHub公开数据(282次commit/150次README迭代/50+fork/100+contribution) 的Codex深度挖掘分析报告+小红书卖课行为报告的系统蒸馏, 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。

    454 GitHub stars~2.8k tokensUpdated 3 mo ago
    Frontend & DesignAuto-check passed
  • Liteyuki Webui Frontend

    LiteyukiStudio/LiteyukiBot

    Build, review, or test LiteyukiBot v7's React/Vite WebUI under webui/ and its packaged static delivery in packages/webui/.

    157 GitHub stars~2.5k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed
  • Fix PR Design Notes

    different-ai/openwork

    Reads the advisory design review attached to a pull request's screenshots, fixes the flagged UI problems in product code, and proves each note is gone.

    24k GitHub stars~824 tokensUpdated today
    Frontend & DesignAuto-check passed
  • A skill your agent uses when designing, reviewing, or improving web UI visual quality, especially when a developer-built interface feels cluttered, flat, generic, poorly spaced, weakly hierarchical…

    271 GitHub stars~1.9k tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed
  • Live UX Polish

    EveryInc/compound-engineering-plugin

    Collects your feedback on a running feature, typed or spoken and drawn in the browser, and turns it into focused UX fixes saved as local commits.

    25k GitHub stars~777 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • SVG Precision Skill

    dkyazzentwatwa/chatgpt-skills

    Generate deterministic SVGs from structured specs with validation and rendering.

    115 GitHub stars~223 tokensUpdated 6 mo ago
    Frontend & DesignAuto-check passed

More from PackmindHub/packmind

All 35 skills in this repo
  • Michel CLI Demo Recorder

    PackmindHub/packmind

    Produce proof-of-execution demos of the Packmind CLI (packmind-cli) as terminal-styled images (colors and formatting preserved exactly), for embedding in a GitHub PR.

    317 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Michel UI Demo Recorder

    PackmindHub/packmind

    Record polished UI demo videos and screenshots of a running web app using Playwright MCP — for client deliverables, release notes, feature walkthroughs, or bug repros.

    317 GitHub stars~6.4k tokensUpdated today
    Auto-check passed
  • Packmind Create Skill

    PackmindHub/packmind

    Guide for creating effective skills. An agent skill from PackmindHub/packmind.

    317 GitHub stars~3.5k tokensUpdated today
    Auto-check: notes
  • Doc Audit

    PackmindHub/packmind

    Audit Packmind end-user documentation (apps/doc/) for broken links, outdated CLI references, non-existent concepts, misleading information, and missing coverage.

    317 GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Feature Sprint

    PackmindHub/packmind

    Execute the implementation plan produced by /feature-spec. An agent skill from PackmindHub/packmind.

    317 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Review an implemented GitHub issue the way a senior Packmind engineer would — the human-judgment checks that ESLint, the TypeScript compiler, and e2e tests cannot catch (authorization scoping…

    317 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

Questions about Working With Playground App

What does Working With Playground App do?

This skill provides guidance for building UI/UX prototypes in the Packmind playground app. Working With Playground App is an agent skill from PackmindHub/packmind. This skill provides guidance for building UI/UX prototypes in the Packmind playground app.

When should I use Working With Playground App?

Working With Playground App fits situations like: mentions of playground; direct work within the apps/playground/ directory.

How do I install Working With Playground App in Claude Code?

Run `npx skills add PackmindHub/packmind --skill working-with-playground-app -a claude-code`. Or copy the skill folder (.agents/skills/working-with-playground-app in PackmindHub/packmind) into .claude/skills/working-with-playground-app in your project. Claude Code loads it when a task matches its description.

How do I install Working With Playground App in Codex?

Run `npx skills add PackmindHub/packmind --skill working-with-playground-app -a codex`. Or copy the skill folder (.agents/skills/working-with-playground-app in PackmindHub/packmind) into .agents/skills/working-with-playground-app in your project. Codex loads it when a task matches its description.

Can I use Working With Playground App in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add PackmindHub/packmind --skill working-with-playground-app -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/working-with-playground-app, .gemini/skills/working-with-playground-app, .github/skills/working-with-playground-app and .opencode/skills/working-with-playground-app in your project.

What does Working With Playground App need to run?

Going by SKILL.md and its folder, Working With Playground App needs the command-line tools its instructions call (nx). Our summary lists: Docker.

Does Working With Playground App access the network?

SKILL.md names 1 domain. As links in the text: chakra-ui.com. This is read from the text; nothing was executed.

Is Working With Playground App safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Working With Playground App use?

Working With Playground App is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Working With Playground App use?

About 2.1k tokens (SKILL.md is roughly 8.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 216 tokens, read only when the agent opens those files.

What are the alternatives to Working With Playground App?

Skills that share tags, products or a category with Working With Playground App: Lofisu Persona (zclllyybb/lofisu-identity-engine, 454 stars), Liteyuki Webui Frontend (LiteyukiStudio/LiteyukiBot, 157 stars), Fix PR Design Notes (different-ai/openwork, 24k stars) and Refactoring UI Design (chaxus/ran, 271 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Working With Playground App?

PackmindHub (a GitHub organization) maintains it in PackmindHub/packmind, which has 317 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 9, 2026.

Source: PackmindHub/packmind on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.