Contact Widget

OrganizationPopular

nexu-io

contact-widget

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

Overview

Publisher	nexu-io
Repository	`open-design`
Skill name	`contact-widget`
Stars	96.7K
Forks	11.2K
Bundled files	1
License	Apache-2.0
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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by nexu-io on GitHub. Read the source before you install it.

Installation

Install the Contact Widget 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.
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/nexu-io/open-design.git /tmp/open-design
mkdir -p .claude/skills
cp -r /tmp/open-design/design-templates/contact-widget .claude/skills/contact-widget

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

Use it in TypingMind

Enable Contact Widget 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 Contact Widget 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 Contact Widget 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.

Contact Widget

What this skill produces

A single self-contained HTML file with a floating chat widget that includes:

Chat bubble — fixed bottom-right circular button, opens/closes the panel
Welcome home screen — agent avatar + name + online status + greeting message
Message input — text field with emoji/send icons (UI only; wire to your own backend)
Social links — row of circular icons (Telegram, WhatsApp, Instagram, Messenger, Discord, Slack — only the ones the user provides)
Meeting card — optional "Book a meeting" entry with calendar icon, links to user-provided URL (Calendly, Cal.com, Lark, etc.)
Offline form — fallback contact form (name, email, message) when is_available=false
Mobile responsive — full-width on small viewports

Output is pure front-end. No tracking, no phone-home, no required external services. Works offline once loaded.

Design direction

Clean, minimal SaaS aesthetic. Looks like a real product widget, not a toy demo:

Typography: Inter (Google Fonts), 14px base, semi-bold headings
Colors: A single user-chosen primary_color drives the bubble, avatar, send button, and accent. Everything else is a neutral slate palette (#1e293b / #64748b / #f1f5f9). No purple gradients, no glassmorphism, no AI-style rainbow accents.
Radius: 16px on cards, full-round on bubble and avatars
Shadows: Subtle 0 8px 32px rgba(0,0,0,0.12) on the widget panel, 0 4px 12px on bubble
Spacing: 16px internal padding, 12px gaps between elements
States: Hover darkens buttons ~5%, active scales bubble 0.95

Inputs

The skill accepts these parameters from the user:

Input	Type	Default	Description
`primary_color`	color	`#4F7CFF`	Drives bubble, header, send button, accents
`agent_name`	string	`Assistant`	Displayed in header greeting
`greeting`	string	`Hello! How can I help you today?`	Subtitle in header
`is_available`	boolean	`true`	Online status; `false` shows offline form
`social_telegram`	string	(empty)	Telegram link — omitted if empty
`social_whatsapp`	string	(empty)	WhatsApp link — omitted if empty
`social_instagram`	string	(empty)	Instagram link — omitted if empty
`meeting_url`	string	(empty)	Booking URL (Calendly, Cal.com, etc.) — omitted if empty
`offline_message`	string	`We're currently offline. Leave a message and we'll get back to you!`	Shown when `is_available=false`

Workflow

Resolve primary color, agent name, greeting text, online/offline state, social links, and optional meeting URL from the request and known context. Use the documented defaults and omit empty optional links. Ask one consolidated form only if a missing value would materially change the requested widget and cannot be safely defaulted.
Generate one HTML file with all provided values inlined as literals (no template engine, no {{ }} placeholders in the output)
Open the widget panel by default on first paint so the preview is useful
Do not add any <script src="…"> pointing to third-party SDKs unless the user explicitly asks for backend integration. The output must run from disk with zero network calls beyond the Google Fonts CSS.

Backend integration (optional, user-driven only)

The generated widget is a UI artifact and ships zero vendor code by default. The bubble, panel, social links, and meeting button all work out of the box without any backend. Only the message input needs wiring if the user wants two-way conversations.

If the user explicitly asks to wire the message input to a real backend, offer these in order of escalating commitment:

Tier 1 — No backend (default)

The widget already works as a contact surface via social links + meeting URL. Leave it as-is.

Tier 2 — One-shot messages, no chat history

mailto: fallback — replace the send handler with window.location.href = 'mailto:you@example.com?subject=...&body=' + encodeURIComponent(text). Zero infra, but the visitor's mail client opens.
Own /api/contact endpoint — fetch('/api/contact', { method: 'POST', body: JSON.stringify({ text }) }). The user owns delivery (SendGrid, Resend, their own SMTP, a Notion/Airtable webhook, etc.).

Tier 3 — Real-time chat (visitor ↔ agent, history, typing, presence)

This needs an IM/chat SDK. Any of the following work; pick whichever fits your stack:

Knocket — https://trtc.io/solutions/knocket (drop-in, free)
Crisp — https://crisp.chat
Tawk.to — https://tawk.to
Chatwoot (self-hosted) — https://chatwoot.com
Intercom — https://intercom.com

Do not auto-inject any <script> into the generated output — only add backend integration if the user explicitly opts in.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

example.html15 KB

Frequently asked questions

What does the Contact Widget AI skill do?

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

Why use Contact Widget on TypingMind?

Because you install it once and use it with any model. Contact Widget 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 Contact Widget in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nexu-io/open-design/tree/main/design-templates/contact-widget. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Contact Widget?

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 Contact Widget?

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

Is the Contact Widget AI skill free?

Yes. It is published on GitHub by nexu-io under the Apache-2.0 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

Ai Regression Testing

affaan-m

CommunityPopular

AI 支援開発のためのリグレッションテスト戦略。データベース依存なしのサンドボックスモード API テスト、自動化されたバグチェックワークフロー、同じモデルがコードを書いてレビューする AI のブラインドスポットを捕捉するパターン。

Doc Coauthoring

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.

Spec Driven Development

addyosmani

CommunityPopular

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Contact Widget

What this skill produces

Design direction

Inputs

Workflow

Backend integration (optional, user-driven only)

Tier 1 — No backend (default)

Tier 2 — One-shot messages, no chat history

Tier 3 — Real-time chat (visitor ↔ agent, history, typing, presence)

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now