跳到正文
cccskills
免费在 GitHub 公开

contact-widget

Build a floating contact widget as a single HTML file, with a welcome screen, social links, meeting booking link, and offline form. The message field provides an interface that can optionally connect to a backend.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

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

集成工具TelegramInstagram
查看安装方法

适用场景

  • Adding a contact widget to a portfolio
  • Grouping social links and meeting booking
  • Showing a contact form while unavailable
  • Prototyping a branded contact interface

包含的文件(2)

  • SKILL.md6.2 KB
  • example.html15.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Contact Widget

What this skill produces

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

  1. Chat bubble — fixed bottom-right circular button, opens/closes the panel
  2. Welcome home screen — agent avatar + name + online status + greeting message
  3. Message input — text field with emoji/send icons (UI only; wire to your own backend)
  4. Social links — row of circular icons (Telegram, WhatsApp, Instagram, Messenger, Discord, Slack — only the ones the user provides)
  5. Meeting card — optional "Book a meeting" entry with calendar icon, links to user-provided URL (Calendly, Cal.com, Lark, etc.)
  6. Offline form — fallback contact form (name, email, message) when is_available=false
  7. 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:

InputTypeDefaultDescription
primary_colorcolor#4F7CFFDrives bubble, header, send button, accents
agent_namestringAssistantDisplayed in header greeting
greetingstringHello! How can I help you today?Subtitle in header
is_availablebooleantrueOnline status; false shows offline form
social_telegramstring(empty)Telegram link — omitted if empty
social_whatsappstring(empty)WhatsApp link — omitted if empty
social_instagramstring(empty)Instagram link — omitted if empty
meeting_urlstring(empty)Booking URL (Calendly, Cal.com, etc.) — omitted if empty
offline_messagestringWe're currently offline. Leave a message and we'll get back to you!Shown when is_available=false

Workflow

  1. 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.
  2. Generate one HTML file with all provided values inlined as literals (no template engine, no {{ }} placeholders in the output)
  3. Open the widget panel by default on first paint so the preview is useful
  4. 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:

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

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Create a three-scene video composition in a retro pixel style using a Hyperframes HTML template. Customize titles, labels, and colors while preserving scene transitions, short scene durations, and repeatable animation timing.

中文简介正在准备中。当前显示英语简介。

  • Create a retro pixel presentation video
  • Customize a three-scene video template
  • Preview scene transitions and motion in HTML
nexu-io/open-design10.2万2026年10月18日 更新

Create and revise headlines, descriptions, and main text for paid social and search ads. Use it to develop ad copy options and refine wording through repeated rounds of revision.

中文简介正在准备中。当前显示英语简介。

  • Drafting headlines for paid social ads
  • Creating descriptions for search ads
  • Revising the main text of an ad
nexu-io/open-design10.2万2026年10月18日 更新

Create a three-page editorial motion sequence with dark backgrounds, serif typography, staged text reveals, and chapter transitions. The result is a single HTML file suited to fashion-inspired storytelling and short visual presentations.

中文简介正在准备中。当前显示英语简介。

  • Creating a fashion-inspired motion presentation
  • Presenting a short story across three pages
  • Applying existing brand rules to a dark editorial sequence
nexu-io/open-design10.2万2026年10月18日 更新

Inspect and test web pages through a browser automation command-line tool. Navigate, click, enter text, capture screenshots, and extract page details, with a focus on checking local OpenDesign previews and reviewing web app quality.

中文简介正在准备中。当前显示英语简介。

  • Checking local OpenDesign previews
  • Testing clicks and text entry in web apps
  • Capturing page or element screenshots
nexu-io/open-design10.2万2026年10月18日 更新

Plan an AI music album from its concept through lyric drafts, track order, and export. Intended for independent album experiments and brand soundtracks, with the full production workflow provided through a separately installed upstream bundle.

中文简介正在准备中。当前显示英语简介。

  • Planning an experimental independent album
  • Drafting lyrics around an album concept
  • Deciding the running order of tracks
nexu-io/open-design10.2万2026年10月18日 更新

Create generative art, or images made with programmed rules, using p5.js. Fixed random seeds make each rendering reproducible, supporting procedural posters, still images that suggest motion, and studies of artistic frame composition.

中文简介正在准备中。当前显示英语简介。

  • Posters generated with programmed rules
  • Still images that suggest motion
  • Studies of artistic frame composition
nexu-io/open-design10.2万2026年10月18日 更新

查看 nexu-io 的全部技能

报告此技能的问题