AGENT SKILL

codex-interactive-capability-map

Turn a long-form article, thread, memo, or product narrative into a compact clickable capability map with a workflow loop, use-case matrix, and responsive detail panel.

License 许可
MIT
最近更新
2026-11-14
Stars
★ 1.1k
Forks
104

01 前言 Front Matter

od
{ "mode": "prototype", "preview": { "type": "html", "entry": "example.html" }, "surface": "web", "featured": 42, "platform": "desktop", "scenario": "knowledge", "design_system": { "requires": false }, "example_prompt": "Turn this long-form article or thread into a Codex-style interactive capability map. Extract the core concepts, organize them into a workflow loop and use-case matrix, then build a polished single-file HTML prototype with clickable cards and a detail panel." }
name
codex-interactive-capability-map
tags
[ "codex", "article", "thread", "knowledge", "map", "interactive", "capability", "explainer" ]
emoji
🗺️
en_name
Codex Interactive Capability Map
zh_name
Codex 交互式能力地图
category
prototype
featured
42
scenario
knowledge
example_id
sample-codex-interactive-capability-map
aspect_hint
desktop web prototype, responsive down to tablet
description
Turn a long-form article, thread, memo, or product narrative into a compact clickable capability map with a workflow loop, use-case matrix, and responsive detail panel.
example_desc
A long post transformed into a concise visual map with linked concepts, use cases, and detail cards.
example_name
Codex Interactive Capability Map · Operating Model
example_format
html
example_tagline
Long text → clickable operating model

02 资源文件 2

03 SKILL.md 正文

Codex Interactive Capability Map

Transform a long article, social thread, memo, product essay, or launch narrative into a visual explainer that people can scan and click through.

Use When

  • The input is mostly text and the user wants a clearer mental model.
  • The content contains repeated concepts, a process, a framework, capabilities, or operating principles.
  • The desired output is a polished web artifact, not a static summary.

Workflow

  1. Read the source material and extract 6-10 core concepts.
  2. Name the overall model in plain language. Prefer a short noun phrase such as "Operating Model", "Capability Map", or "Workflow Loop".
  3. Build three linked views:
    • A hero that frames the source and the promise.
    • A workflow loop that shows the main sequence or system.
    • A use-case matrix that combines concepts into practical scenarios.
  4. Add a right-side detail panel. Clicking any nav item, loop node, matrix card, or maturity level must update the panel.
  5. Make the clicked element and the detail panel visibly correspond through shared color, motion, icon/mark shape, or gradient.
  6. Keep copy short. The artifact should reduce reading effort, not recreate the article.

Visual Direction

  • Use a Codex-inspired refined product style with soft liquid motion, glassy surfaces, and crisp functional controls.
  • Make the first viewport feel like a finished product surface, not a wireframe.
  • Favor diagrams, loops, matrices, rails, cards, and progressive disclosure over paragraphs.
  • Use meaningful hover and active states. A click should feel consequential.
  • Avoid external image dependencies unless the user explicitly provides assets.

Interaction Requirements

  • All clickable elements must update content or scroll to a meaningful section.
  • The active state must be visually obvious.
  • The detail panel should animate on each change.
  • Long labels must wrap cleanly and never be clipped.
  • The layout must work at 1280px wide and collapse cleanly below 900px.

Output Contract

Emit one single-file HTML artifact:

<artifact identifier="codex-interactive-capability-map" type="text/html" title="Codex Interactive Capability Map">
<!doctype html>
<html>...</html>
</artifact>

Include all CSS and JavaScript inline. Do not use lorem ipsum. Do not leave placeholder cards. If the source does not include enough concrete details, infer a small, clearly labeled conceptual model from the source instead of inventing unrelated content.

04 同仓库更多 Skills

feimacode
feimacode/open-design-agent-kit

youtube-clipper

YouTube clip generation and editing with automated workflows — pull source video, slice highlights, add captions, and export.

★ 1.1k
feimacode
feimacode/open-design-agent-kit

writing-guidelines

Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".

★ 1.1k
feimacode
feimacode/open-design-agent-kit

wpds

WordPress Design System. Apply WordPress's official design tokens, typography, and component patterns to themes and sites.

★ 1.1k
feimacode
feimacode/open-design-agent-kit

weread-year-in-review-video-template

WeRead-inspired HyperFrames video template for vertical annual reading reports, personal reading dashboards, book-note recaps, and shareable year-in-review stories. Use when users want a 9:16 HTML-to-MP4 reading report with warm paper texture, editorial Chinese typography, book-page metaphors, data highlights, and deterministic motion.

★ 1.1k
feimacode
feimacode/open-design-agent-kit

web-design-guidelines

Review UI code for Web Interface Guidelines compliance by the Vercel engineering team. Covers layout, typography, color, motion, and accessibility for product UI.

★ 1.1k
feimacode
feimacode/open-design-agent-kit

web-clone

网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树,覆盖静态站 / React-Vue-Next 内容站 / WebGL-Canvas 重前端站三大分支,并强制核对任何 AI 二手分析里的可执行代码。

★ 1.1k