AGENT SKILL

social-carousel

A three-card social-media carousel laid out as 1080×1080 squares — three cinematic, on-brand panels with display headlines that connect across the series ("onwards." → "to the next one." → "looking ahead."). Each card has a brand mark, a number / total, a caption, and a "loop" affordance. Use when the brief asks for a "carousel post", "social carousel", "Instagram carousel", "LinkedIn series", "X thread cards", or "三连发".

License 许可
MIT
最近更新
2026-11-10
Stars
★ 1
Forks
0

01 前言 Front Matter

od
{ "mode": "prototype", "preview": { "type": "html", "entry": "index.html" }, "platform": "desktop", "scenario": "marketing", "design_system": { "requires": true, "sections": [ "color", "typography", "layout", "components" ] }, "example_prompt": "Design a 3-card cinematic social carousel — ‘onwards.’, ‘to the next one.’, ‘looking ahead.’. 1080×1080 squares, drop-into-Instagram ready." }
name
social-carousel
triggers
[ "social carousel", "carousel post", "instagram carousel", "linkedin carousel", "x thread cards", "social series", "三连发", "轮播图" ]
description
A three-card social-media carousel laid out as 1080×1080 squares — three cinematic, on-brand panels with display headlines that connect across the series ("onwards." → "to the next one." → "looking ahead."). Each card has a brand mark, a number / total, a caption, and a "loop" affordance. Use when the brief asks for a "carousel post", "social carousel", "Instagram carousel", "LinkedIn series", "X thread cards", or "三连发".

02 资源文件 1

03 SKILL.md 正文

Social Carousel Skill

Produce a 3-panel social carousel on a single dark stage. Each panel is a 1080×1080 cinematic still — connected as a series, but each readable on its own.

Workflow

  1. Read the active DESIGN.md (injected above). Pick the loudest serif token for the headline lockups and a mono token for stamps / counters.
  2. Pick the theme + 3 captions from the brief. The captions must read as one sentence when stacked: ("onwards." → "to the next one." → "looking ahead." or "input." → "iterate." → "ship.").
  3. Stage — full-bleed dark page. Top header strip:
    • Left: serif italic display "Three posts. One beat."
    • Just below the title: a one-line description in muted mono ("1080×1080 · cinematic video loops · minimal type. Drop into Instagram, LinkedIn, or X — each post stands on its own or runs as a three-part series.").
    • Right: small mono badge "SERIES · 01 → 03".
  4. Cards — 3 squares in a horizontal row (wraps to stack on narrow viewports). Each card is aspect-ratio: 1 / 1 with rounded 12px corners and a subtle 1px border, plus a soft drop shadow.
    • Background: a layered gradient that suggests a cinematic photo — for example, panel 1 = warm dawn meadow (stacked greens with a cyan sky wash); panel 2 = forest dusk (warm oranges fading into deep teals); panel 3 = pink-mountain ridge (rosy peaks against a dim violet sky). Use radial-gradient + linear-gradient only — no images.
    • Top-left chip: brand wordmark in serif italic ("Jerrod Lew") with a small accent dot.
    • Top-left below chip: micro mono index "AI · 01 / 03" (and 02, 03).
    • Bottom-left: the headline lockup in white serif display, italic accent on one word.
    • Bottom-right corner: a 1× LOOP mono stamp inside a thin border.
    • Bottom strip caption: small caps mono describing the imagined frame ("Man, walking forward — close.", "Woman, stepping into frame.", "Woman, overlooking the city.").
  5. Write a single HTML document:
    • <!doctype html> through </html>, CSS inline.
    • Cards are sized via width: clamp(280px, 30vw, 380px) so 3 fit comfortably across most desktops and stack at < 1100px.
    • data-od-id on stage, each card, each headline.
  6. Self-check:
    • The three headlines together form one sentence and feel cinematic.
    • Mono is used only for the wordmark index, the loop stamp, and the bottom captions. The headlines stay serif.
    • Each panel's color story is distinct — no two share a dominant hue.

Output contract

Emit between <artifact> tags:

<artifact identifier="carousel-slug" type="text/html" title="Carousel — Title">
<!doctype html>
<html>...</html>
</artifact>

One sentence before the artifact, nothing after.

04 同仓库更多 Skills

YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

vercel-sandbox

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

slack

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

electron

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.

★ 1