Pwa

Community

MartinOlivero

pwa

This skill should be used when turning a web app into a Progressive Web App — making it installable, work offline, cache assets, or send push notifications. Trigger phrases include "make it a PWA", "installable app", "work offline", "offline mode", "service worker", "web push", "push notifications", "add to home screen", "app manifest", "cache assets", "make it feel like a native app". It sets up vite-plugin-pwa with the right caching strategy and avoids the stale-service-worker trap.

Overview

Publisher	MartinOlivero
Repository	`saas-builder`
Skill name	`pwa`
Stars	4
Forks	2
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by MartinOlivero on GitHub. Read the source before you install it.

Installation

Install the Pwa AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/MartinOlivero/saas-builder/tree/main/skills/pwa
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/MartinOlivero/saas-builder.git /tmp/saas-builder
mkdir -p .claude/skills
cp -r /tmp/saas-builder/skills/pwa .claude/skills/pwa

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pwa in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pwa on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pwa is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PWA

This skill makes a React + Vite app installable and offline-capable — the realistic middle ground between a plain website and a full native app. For a web-SaaS builder, this is the common mobile need; full React Native is rare and better served by Expo's own skills.

Analogy: a PWA is a food truck. It's the same kitchen as the restaurant (your web app), but it can park on the user's home screen and keep serving when the main location's network is down. You don't need to build a second restaurant (a native app) to get there.

When to use this vs going native

PWA (this skill) → installable, offline, push for an existing web app. Covers most "we need mobile" requests.
Full React Native → only when you need deep native APIs, app-store presence, or heavy device integration. Delegate to expo/skills (official, ~2k⭐) rather than rebuilding it here. At most, share TS types/API client via a monorepo packages/shared.

Discovery (max 3 questions, only if unknown)

What's the goal — installable, offline reads, offline writes, or push notifications?
Is this an existing Vite app, or starting fresh?
Do you need push on iOS? (It only works for installed PWAs, Safari 16.4+.)

Step 1 — Install and configure

Add vite-plugin-pwa (~4k⭐, Workbox-based). Start with registerType: 'autoUpdate' and the generateSW strategy to precache the app shell + static assets. This plus a Web App Manifest and HTTPS = installable.

Step 2 — Author the manifest

Web App Manifest: name, short_name, theme_color, background_color, 192px and 512px maskable icons, display: standalone, start_url. The plugin can generate it from config.

Step 3 — Caching strategy

Cache-first for hashed static assets (they never change without a new hash).
Stale-while-revalidate for API/data (instant from cache, refresh in background).
Set navigateFallback so SPA routes work offline.

Step 4 — Offline writes (if needed)

Don't try to cache POSTs in the service worker. Pair the SW with IndexedDB (e.g. Dexie) + Workbox Background Sync to queue mutations and replay them on reconnect.

Step 5 — Push notifications (if needed)

Switch to injectManifest (custom SW) for push handlers.
Subscribe via PushManager, store the subscription server-side, send via VAPID.
iOS: web push works only for installed PWAs (16.4+) — set expectations.

Step 6 — Avoid the #1 PWA bug

A stale or over-aggressive service worker is the most common PWA support ticket. Always:

Ship a skipWaiting / update strategy.
Surface an in-app "New version available" prompt using the plugin's useRegisterSW — don't silently reload mid-session.
Provide a custom offline fallback page; test via the Lighthouse PWA audit + DevTools "Offline" before shipping.

Output

Deliver: the vite-plugin-pwa config, the manifest, the caching-strategy choices, the update prompt, and (if requested) the IndexedDB+Background-Sync or push setup.

Reference

vite-pwa/vite-plugin-pwa (~4k⭐), GoogleChrome/workbox (~13k⭐), web.dev Learn PWA, expo/skills (for native).

Frequently asked questions

What does the Pwa AI skill do?

Why use Pwa on TypingMind?

Because you install it once and use it with any model. Pwa is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pwa in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MartinOlivero/saas-builder/tree/main/skills/pwa. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pwa?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pwa?

As many as you like. As long as a model supports skills, you can use Pwa with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pwa AI skill free?

Yes. It is published on GitHub by MartinOlivero under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Doc Coauthoring

anthropics

OrganizationPopular

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This…

Caveman Discover

Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.

Complain

Autonomously yeet a brief, unstructured complaint about agent tooling or doing agent work. Preserve the raw voice. Submit proactively without permission, preview, or announcement, then continue the…

Contact Widget

Self-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

PWA

When to use this vs going native

Discovery (max 3 questions, only if unknown)

Step 1 — Install and configure

Step 2 — Author the manifest

Step 3 — Caching strategy

Step 4 — Offline writes (if needed)

Step 5 — Push notifications (if needed)

Step 6 — Avoid the #1 PWA bug

Output

Reference

Frequently asked questions

Related AI Skills

Set up your own AI workspace now