HyperFrames by HeyGen
Official HyperFrames by HeyGen: the best AI video editor in chat. Captions, motion graphics, MP4.
README design skill for Claude Code & Codex. 帮你把 GitHub README 做得好看又好懂。
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/oil-oil-beautify-github-readme)在同一工作中把 AI 连到服务的 MCP
Official HyperFrames by HeyGen: the best AI video editor in chat. Captions, motion graphics, MP4.
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.
同类工作,排序与 Skill 列表相同
| 本项 beautify-github-readme | impeccable | diagram-design | frontend-slides | guizang-ppt-skill | |
|---|---|---|---|---|---|
| 作者 | oil-oil | pbakaus | cathrynlavery | zarazhangrui | op7418 |
| Skill 数 | 1 | 1 | 1 | 1 | – |
| GitHub 星标 | 1,979 | 111,265 | 67,613 | 32,407 | 29,891 |
| 最近代码更新 | 2026年11月16日 | 2026年11月17日 | 2026年11月13日 | 2026年6月24日 | 2026年10月30日 |
| 许可证 | MIT | Apache-2.0 | MIT | MIT | AGPL-3.0 |
oil-oil 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
Codex
依据开发者 README 和 repo 中的文件夹
GitHub account oil-oil (person), 7 years old
★ 1,979 stars · code last changed 2026年11月16日
2 scripts that can run on a computer: scripts/audit_readme.py, scripts/render_motion_gif.py
No internet calls found in the scripts
No hooks or writes to machine settings found
Checked automatically from the repo files at commit e2a8e38 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
Uploading to claude.ai would fail: the description is over 200 characters (661). Use "Let the AI install it" instead
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /beautify-github-readme,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
正在检查命令 · 通过后才会显示复制按钮
摘自开发者 README,会下载并运行开发者的代码
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 beautify-github-readme 文件夹放到 ~/.agents/skills/beautify-github-readme
~ 是你的主文件夹($HOME)
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 beautify-github-readme
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
显示前 8,000 个字符 · 在 GitHub 打开完整文件
---
name: beautify-github-readme
description: Redesign GitHub README homepages or create project-native pure SVG, hybrid SVG-composed PNG/WebP, and opt-in animated GIF assets. Use when a user asks to beautify, redesign, rebrand, visually upgrade, simplify, or audit a GitHub README; create only a hero, section headers, diagrams, badges, motion graphics, showcase modules, or other README assets; or turn a repository homepage into a cohesive visual story. If whole-README work versus asset-only work is unclear, ask which scope the user wants. For hero-like assets where pure SVG and generated raster material are both viable, explain the tradeoffs and confirm the implementation before creating the asset.
---
# Beautify GitHub README
Turn a repository homepage or requested visual asset into a concise, theme-specific visual story. Treat Markdown as the content layer, deterministic SVG as the layout system, and generated raster material as an optional visual ingredient.
## Workflow
### 1. Confirm the mode before editing
Use exactly one execution mode:
- **README mode** — improve the whole README: information order, copy hierarchy, proof, Markdown, and visual system.
- **Asset-only mode** — create only the requested static SVG or visual asset set. Static SVG is the default. Only after the user explicitly opts into meaningful motion, optionally deliver a GitHub-safe GIF while keeping the SVG as the editable fallback. Do not rewrite, reorder, or embed anything in the README unless the user explicitly adds that scope.
If the mode is not explicit, ask one compact question before making changes:
> Would you like me to improve the whole README or only create visual assets? If asset-only, tell me whether you need a hero, section headers, workflow, badge, motion graphic, or a coordinated set.
When a hero, badge, workflow, or diagram has meaningful motion and the user has not specified static or animated output, ask one compact follow-up:
> Should this stay as a static SVG, or would you like a GitHub-safe GIF animation with the SVG kept as the editable fallback?
GIF is opt-in and never the default. If the user declines, does not answer, or has no meaningful motion case, continue with static SVG only. Do not ask when motion would be purely decorative or the user already chose the output. Read-only inspection is allowed before the answer when it helps understand the repository. Do not interpret “use this Skill,” a repository path, or “beautify it” as permission to modify the whole README. Once the user chooses asset-only mode, expanding into README edits requires new authorization.
If the user explicitly asks only for an audit, audit without editing and do not force the two-mode question.
### 2. Inspect before designing
- Read the existing README, repository tree, package metadata, screenshots, examples, design tokens, logo, and real outputs.
- In asset-only mode, inspect only the context needed to design the requested assets. Reading the README for context does not authorize changing it.
- For a GitHub URL, inspect the current remote page and default branch before proposing changes.
- Identify the audience, the problem solved, the clearest proof, the shortest path to first use, and any claims that lack evidence.
- When the repository is public or about to be published, list what would ship and keep private material out by default: personal absolute paths, private project code or names, raw logs, transcripts, raw benchmark runs, and credentials. Do not link to or quote it in the README or its assets; an anonymized summary of results is fine. In README mode, also exclude it from the published files, for example with `.gitignore`. Report what you excluded instead of asking whether it should ship.
- Preserve unrelated user changes. Start read-only; do not commit, push, rename, or publish without explicit authorization.
### 3. Confirm the visual implementation before creating hero-like assets
For a hero, large banner, showcase board, or expressive title system where both implementations are viable, explain the difference and ask before producing the asset:
> Which implementation would you like?
>
> - **Pure SVG** — fully deterministic, lightweight, sharply scalable, easy to edit, and best for typography, diagrams, code, icons, and geometric or pixel-art scenes. It does not use image generation and is weaker for realistic people, hair, organic texture, complex materials, or cinematic lighting.
> - **Hybrid SVG composition** — use SVG for layout and typography, optionally use ImageGen for a project-specific raster subject, remove its background when appropriate, and compose the layers into a final PNG/WebP. It supports richer characters, materials, and lighting, but is heavier, partly stochastic, and requires generation plus visual validation. Keep the SVG layout source and transparent subject PNG.
Do not ask this question when the user already chose an implementation, requested an audit, or the asset is obviously deterministic, such as a workflow, architecture diagram, badge, compact section header, or code-native illustration. Do not suggest hybrid composition merely to add decoration. Prefer real screenshots, outputs, logos, or existing project art over generated material.
If the user delegates the decision, default to pure SVG unless generated or photographic material clearly communicates the repository's identity or mechanism better. Do not begin ImageGen work until the user selects hybrid composition or explicitly delegates the choice.
Hybrid composition is an implementation source, not normally the published SVG. Relative raster references inside SVG are unreliable across renderers, while base64-embedded raster layers can make the SVG unnecessarily large. Publish the verified final PNG/WebP by default and keep the SVG layout plus raster layers as editable sources.
### 4. Extract the project story
Write these before drawing:
```text
Audience:
One-sentence value:
Primary proof:
First successful action:
Visual theme:
```
Do not invent adoption, benchmarks, compatibility, testimonials, or features. When proof comes from small or noisy tests, state magnitudes or ranges with the test conditions instead of precise figures. Prefer a real screenshot, output, diagram, or generated artifact over decorative stock imagery.
### 5. Define a theme-specific visual system
Read [references/visual-direction.md](references/visual-direction.md). Freeze a compact art-direction spec:
```text
Palette: background / foreground / primary / accent / muted
Typography: system font stack / scale / weight contrast
Shape: radius / stroke / grid / spacing
Motif: one recurring project-specific visual cue
Composition: calm / editorial / technical / playful / cinematic
```
Derive the motif from the project. A terminal tool may use prompts and cursor marks; an icon system may use keylines and cutouts; a research project may use coordinates and evidence labels. Never apply the same yellow-grid template to every repository.
Before designing the hero, read [references/project-native-hero.md](references/project-native-hero.md). Build the title from project content rather than treating it as a banner placed above the proof. Choose the typography, composition, and right-side material from the repository itself.
### 6. Execute only the selected mode
#### README mode
Decide how deeply the README needs to change:
- **Full redesign** — restructure the story and build a new visual system.
- **Visual refresh** — preserve the information architecture while replacing weak or inconsistent presentation.
Use the smallest change inside README mode that can produce a meaningful improvement. Rebuild the reading order only when the selected scope requires it. A strong default is:
1. Hero: name + plain-language value.
2. Proof: screenshots, outputs, or a showcase wall.
3. What it is: one short explanation.
4. Why it is different: mechanism, not slogans.
5. How it works: a short process or arch提问、分享技巧或报告无法使用。按“有帮助”数量排序。