Agent skill

App Builder

by softspark in softspark/ai-toolkit

App scaffolding: Next.js, Vite, Nuxt, Astro, FastAPI, Django, Laravel, RN, Flutter.

Apache-2.0Auto-check passedBackend & APIs

Install App Builder

skills CLI
$ npx skills add softspark/ai-toolkit --skill app-builder -a claude-code

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

GitHub CLI
$ gh skill install softspark/ai-toolkit app-builder --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/softspark/ai-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/app/skills/app-builder .claude/skills/app-builder && 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
app-builder
GitHub stars
179
Token cost
~2.2k tokens
SKILL.md length
831 words
Files
1
Skills in repo
112
Repo updated
First seen
Licence
Apache-2.0

At a glance

App scaffolding: Next.js, Vite, Nuxt, Astro, FastAPI, Django, Laravel, RN, Flutter.

  • Works in 3 steps: Design Context Gate → Pre-Flight Scan (Existing Projects) → Structural Variety & Macrostructures
  • Tasks that involve Backend development
  • SKILL.md covers Project Type Detection, Tech Stack Selection (2025), Project Templates and Design Context Gate &…, plus 6 more sections
  • Calls npm and npx

What it does

App Builder is an agent skill from softspark/ai-toolkit. App scaffolding: Next.js, Vite, Nuxt, Astro, FastAPI, Django, Laravel, RN, Flutter. Triggers: scaffold, bootstrap, new project, starter, dashboard, mobile app.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering Backend development, Cross-platform mobile apps and Project scaffolding. It works with Next.js, FastAPI, Vite and Astro. The repository describes itself as: Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Backend development
  • Tasks that involve Cross-platform mobile apps
  • Tasks that involve Project scaffolding

Example prompts

  • “/app-builder”

Requirements

  • Node.js
  • Pre-approved tools (allowed-tools): Read

Workflow steps

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

  1. Design Context Gate
  2. Pre-Flight Scan (Existing Projects)
  3. Structural Variety & Macrostructures

What it can do on your machine

Read from SKILL.md and the folder at commit d64db2b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm
    • npx

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

  • Network

    No URLs in SKILL.md. Its commands use npm and npx, which can reach the network depending on how they are called.

    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

App Builder loads about 2.2k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 831 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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 softspark/ai-toolkit at commit d64db2b, republished under its Apache-2.0 licence (© softspark). 831 words, ~2,177 tokens.

Download SKILL.mdSave it as .claude/skills/app-builder/SKILL.md (or your agent's skills folder).
name
app-builder
description
App scaffolding: Next.js, Vite, Nuxt, Astro, FastAPI, Django, Laravel, RN, Flutter. Triggers: scaffold, bootstrap, new project, starter, dashboard, mobile app.
allowed-tools
Read
effort
medium
user-invocable
false

App Builder Skill

Project Type Detection

KeywordsProject TypePrimary Agents
landing, website, marketingStatic Sitefrontend-specialist
dashboard, admin, crudWeb Appfrontend + backend
api, rest, graphqlAPI Onlybackend-specialist
mobile, ios, androidMobile Appmobile-developer
cli, command, terminalCLI Toolbackend-specialist
game, unity, godotGamegame-developer
ai, ml, ragAI/MLai-engineer
e-commerce, shop, storeE-commercebackend + frontend

Tech Stack Selection (2025)

Web Applications
ScenarioStack
Full-stack, SSRNext.js 14+ (App Router)
SPA with APIReact + Vite
Vue ecosystemNuxt 3
Static/BlogAstro
E-commerceNext.js + Medusa/Shopify
Mobile Applications
ScenarioStack
Cross-platform (JS team)React Native + Expo
Cross-platform (any)Flutter
iOS onlySwiftUI
Android onlyKotlin + Jetpack Compose
Backend/API
ScenarioStack
Node.js, edge-readyHono
Node.js, high perfFastify
Python, asyncFastAPI
PHP, full-featuredLaravel
E-commerceMagento/Sylius/PrestaShop
Database
ScenarioStack
General purposePostgreSQL
ServerlessNeon (PG), Turso (SQLite)
Document storeMongoDB
Vector searchPostgreSQL + pgvector
CacheRedis / Upstash

Project Templates

Next.js Full-Stack
project/
├── src/
│   ├── app/              # App Router
│   │   ├── (auth)/       # Auth group
│   │   ├── api/          # API routes
│   │   ├── layout.tsx
│   │   └── page.tsx
│   ├── components/       # Shared components
│   │   └── ui/           # UI primitives
│   ├── lib/              # Utilities
│   └── server/           # Server-only code
├── prisma/               # Database schema
├── public/
├── next.config.ts
├── tailwind.config.ts
└── package.json
FastAPI Backend
project/
├── app/
│   ├── api/
│   │   └── v1/
│   │       └── endpoints/
│   ├── core/             # Config, security
│   ├── models/           # Pydantic models
│   ├── db/               # Database
│   └── main.py
├── tests/
├── alembic/              # Migrations
├── pyproject.toml
└── Dockerfile
React Native + Expo
project/
├── app/                  # Expo Router
│   ├── (tabs)/
│   ├── _layout.tsx
│   └── index.tsx
├── components/
├── hooks/
├── store/                # State management
├── services/             # API clients
├── app.json
└── package.json

Design Context Gate & Pre-Flight Discipline (Web & UI Projects)

Before scaffolding UI pages, establish the design foundation to avoid generic "AI slop":

1. Design Context Gate

Gather 3 essential dimensions (ask once, or infer with clear stated assumptions):

  • Audience: Who will use this? What do they care about?
  • Use Case: What is the single primary action the page drives? (Sign up, purchase, explore, read, configure?)
  • Tone: Pick an explicit extreme — editorial, brutalist, soft, utilitarian, luxury, playful, technical, austere ("clean and modern" is not a tone).
2. Pre-Flight Scan (Existing Projects)

Before generating new pages or components, scan:

  • design.md (or DESIGN.md) — if present, it is the locked design system and overrides defaults.
  • Font Stack — inspect package dependencies and CSS imports (preserve existing font pairings).
  • Palette Tokens — read :root variables, Tailwind @theme definitions, and OKLCH color spaces.
  • Motion Stance — detect installed motion libraries (framer-motion, motion, gsap) vs motion-cut projects.
  • Framework & Spacing Scale — conform to existing grid and spacing scale (4-pt / 8-pt).
3. Structural Variety & Macrostructures

Break the repetitive "Hero → 3 features → CTA → footer" template. Select a named whole-page macrostructure matched to the brief:

  • Bento Grid: Modular irregular grid where visual rhythm comes from varying card sizes and asymmetric spans.
  • Long Document: Literature-led, memo/journal prose format with inline section heads.
  • Marquee Hero: The hero fills the viewport above the fold; content shifts below the fold into a list or dense grid.
  • Stat-Led: A massive metric/number anchors the narrative; subsequent content qualifies the data.
  • Workbench: Guided product tour with real screenshots in frames; focus on functional workflow over marketing copy.
  • Conversational FAQ: Bold questions and honest accordion answers reading like an interview with the product.
  • Manifesto: Large declaration typography; establishes core philosophy before presenting product.
  • Photographic / Quote-Led: Led by primary imagery or borrowed credibility pull-quotes.

Agent Coordination

New Project Flow
1. project-planner     → Task breakdown & tech selection
2. database-architect  → Schema design & migrations
3. backend-specialist  → API & business logic implementation
4. frontend-specialist → UI implementation (anti-slop, 8 states)
5. test-engineer       → Unit, integration, and E2E test coverage
6. devops-implementer  → Deployment & CI/CD setup
Feature Addition Flow
1. explorer-agent      → Understand codebase
2. project-planner     → Plan changes
3. [appropriate agent] → Implement
4. test-engineer       → Add tests
5. code-reviewer       → Review

Common Patterns

Authentication
  • JWT for APIs
  • Session for web apps
  • OAuth for third-party
State Management
  • Server state: TanStack Query
  • Client state: Zustand/Jotai
  • Form state: React Hook Form
Styling
  • Tailwind CSS as default
  • CSS Modules for isolation
  • Styled Components for dynamic
Testing
  • Unit: Jest/Vitest
  • E2E: Playwright
  • API: Supertest

Show full SKILL.md (331 more words)Show less

Best Practices

  • ✅ Start with TypeScript

  • ✅ Add linting (ESLint/Biome)

  • ✅ Use environment variables

  • ✅ Set up CI/CD from start

  • ✅ Document as you build

  • ❌ Don't skip tests

  • ❌ Don't hardcode config

  • ❌ Don't ignore accessibility

  • ❌ Don't over-engineer early

Rules

  • MUST confirm the stack selection with the user before scaffolding — the matrix above is a default, not a verdict
  • MUST include .gitignore, .env.example, a README, a linter config, and a working test harness in every scaffold
  • NEVER overwrite an existing project directory without the user's explicit go-ahead
  • NEVER scaffold Create React App or other EOL starters — steer to Vite, Next.js, or Astro instead
  • CRITICAL: prefer the team's existing expertise over trend-chasing. If the team ships Laravel, scaffolding FastAPI "because it's faster" creates training debt that outweighs the runtime gain.

Gotchas

  • Next.js App Router (app/) and Pages Router (pages/) can coexist technically, but middleware, layouts, and loading-state conventions diverge. Pick one router per project and never mix inside a single feature — debugging the overlap wastes hours.
  • Expo Router (file-based, Expo SDK 49+) and React Navigation (imperative) use completely different navigation APIs. Tutorials mix freely; an agent copying code across the split produces uncompilable projects.
  • Prisma on SQLite silently ignores features that work on Postgres: no CHECK constraints, no deferrable foreign keys, no array columns, limited enum support. Dev-on-SQLite / prod-on-Postgres teams hit this at deploy time.
  • FastAPI --reload uses a file watcher that rebuilds Pydantic models on every edit — startup time doubles and benchmark numbers are unreliable. Disable reload for perf tests.
  • npm create vite@latest respects --template but npx create-next-app@latest prompts interactively even with flags. Fully unattended scaffolds need --ts --tailwind --eslint --app --src-dir --import-alias spelled out.

When NOT to Load

  • For modifying an existing project's stack — use /migrate or /refactor-plan
  • For adding a feature to a running app — use /plan and the relevant language-pattern skill (/typescript-patterns, etc.)
  • For onboarding to an unfamiliar codebase — use /onboard or /explore
  • For deciding between 2-3 specific stacks under stated constraints — use /architecture-decision
  • For plugin or agent scaffolding inside ai-toolkit itself — use /plugin-creator, /agent-creator

© softspark, 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

Just SKILL.md in app/skills/app-builder of softspark/ai-toolkit.

Open the folder on GitHubat commit d64db2b

Compare with similar skills

App Builder 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.

App Builder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
App Builder this skillsoftspark/ai-toolkit179—~2.2kAutomated safety check: PassApache-2.0
Spec To Repoalirezarezvani/claude-skills28k—~2.7kAutomated safety check: NotesMIT
Cloudbase Sites RuntimeTencentCloudBase/CloudBase-AI-Toolkit1.1k—~5kAutomated safety check: NotesMIT
Clerkgeekskai/blog1033 repos~1.5kAutomated safety check: PassMIT
PayRam Checkout IntegrationPayRam/payram-mcp158—~3.4kAutomated safety check: NotesNone
App BuilderxenitV1/Antigravity-Workflows1308 repos~767Automated safety check: NotesMIT

Similar skills

  • Spec To Repo

    alirezarezvani/claude-skills

    A skill your agent uses when the user says 'build me an app', 'create a project from this spec', 'scaffold a new repo', 'generate a starter', 'turn this idea into code', 'bootstrap a project', 'I…

    28k GitHub stars~2.7k tokensUpdated 1 mo ago
    Backend & APIsAuto-check: notes
  • Cloudbase Sites Runtime

    TencentCloudBase/CloudBase-AI-Toolkit

    A skill your agent uses when the user wants to develop, run, preview, save, deploy, or roll back a CloudBase Web app in this conversation as a Lovable/Codex-Sites-like vibe- coding session — i.e.

    1.1k GitHub stars~5k tokensUpdated yesterday
    MobileAuto-check: notes
  • Clerk

    geekskai/blog

    Clerk authentication router. An agent skill from geekskai/blog.

    103 GitHub starsUsed in 3 repos~1.5k tokens
    Backend & APIsAuto-check passed
  • Adds crypto checkout to a web app with PayRam: create a payment from your backend, send the customer to the payment page, then confirm the result.

    158 GitHub stars~3.4k tokensUpdated 1 mo ago
    Backend & APIsAuto-check: notes
  • App Builder

    xenitV1/Antigravity-Workflows

    Main application building orchestrator. An agent skill from xenitV1/Antigravity-Workflows.

    130 GitHub starsUsed in 8 repos~767 tokens
    DevelopmentAuto-check: notes
  • Integrate PayRam webhook handlers for real-time payment and payout event notifications.

    158 GitHub stars~3.6k tokensUpdated 1 mo ago
    Backend & APIsAuto-check: notes

More from softspark/ai-toolkit

All 112 skills in this repo
  • Prepare Test Env

    softspark/ai-toolkit

    Prepare or verify a project QA environment with source identity, readiness, browser access, evidence paths and owned cleanup.

    179 GitHub stars~1.8k tokensUpdated today
    Auto-check: notes
  • A11y Validate

    softspark/ai-toolkit

    Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. An agent skill from softspark/ai-toolkit.

    179 GitHub stars~3.8k tokensUpdated today
    Auto-check: notes
  • Analyze

    softspark/ai-toolkit

    Analyzes code quality, complexity, patterns across codebase.

    179 GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Autonomous Dev

    softspark/ai-toolkit

    Drives a brief, specification, issue or existing PR through implementation, review, tests and QA to a ready PR.

    179 GitHub stars~2.6k tokensUpdated today
    Auto-check: notes
  • Brand Voice

    softspark/ai-toolkit

    Direct technical voice for docs, README, user-facing text. An agent skill from softspark/ai-toolkit.

    179 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • CI

    softspark/ai-toolkit

    Detect/generate/debug CI pipeline config (GitHub Actions, GitLab CI).

    179 GitHub stars~1.1k tokensUpdated today
    Auto-check: notes

Questions about App Builder

What does App Builder do?

App scaffolding: Next.js, Vite, Nuxt, Astro, FastAPI, Django, Laravel, RN, Flutter. App Builder is an agent skill from softspark/ai-toolkit.js, Vite, Nuxt, Astro, FastAPI, Django, Laravel, RN, Flutter.

When should I use App Builder?

App Builder fits situations like: tasks that involve Backend development; tasks that involve Cross-platform mobile apps; tasks that involve Project scaffolding.

How do I install App Builder in Claude Code?

Run `npx skills add softspark/ai-toolkit --skill app-builder -a claude-code`. Or copy the skill folder (app/skills/app-builder in softspark/ai-toolkit) into .claude/skills/app-builder in your project. Claude Code loads it when a task matches its description.

How do I install App Builder in Codex?

Run `npx skills add softspark/ai-toolkit --skill app-builder -a codex`. Or copy the skill folder (app/skills/app-builder in softspark/ai-toolkit) into .agents/skills/app-builder in your project. Codex loads it when a task matches its description.

Can I use App Builder 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 softspark/ai-toolkit --skill app-builder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/app-builder, .gemini/skills/app-builder, .github/skills/app-builder and .opencode/skills/app-builder in your project.

What does App Builder need to run?

Going by SKILL.md and its folder, App Builder needs the command-line tools its instructions call (npm and npx). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Read.

Does App Builder access the network?

SKILL.md contains no URLs. Its commands use npm and npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is App Builder 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 App Builder use?

App Builder 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 App Builder use?

About 2.2k tokens (SKILL.md is roughly 8.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to App Builder?

Skills that share tags, products or a category with App Builder: Spec To Repo (alirezarezvani/claude-skills, 28k stars), Cloudbase Sites Runtime (TencentCloudBase/CloudBase-AI-Toolkit, 1.1k stars), Clerk (geekskai/blog, 103 stars) and PayRam Checkout Integration (PayRam/payram-mcp, 158 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains App Builder?

softspark (a GitHub user) maintains it in softspark/ai-toolkit, which has 179 GitHub stars. The repository holds 112 skills in this directory. The repository was last updated on October 7, 2026.

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