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。
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/oil-oil-beautify-github-readme)MCP servers that connect the AI to services for the same work
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.
Same kind of work, ordered like the Skills list
| This one beautify-github-readme | impeccable | diagram-design | frontend-slides | guizang-ppt-skill | |
|---|---|---|---|---|---|
| Maker | oil-oil | pbakaus | cathrynlavery | zarazhangrui | op7418 |
| Skills | 1 | 1 | 1 | 1 | – |
| GitHub stars | 1,979 | 111,265 | 67,613 | 32,407 | 29,891 |
| Last code change | Nov 16, 2026 | Nov 17, 2026 | Nov 13, 2026 | Jun 24, 2026 | Oct 30, 2026 |
| License | MIT | Apache-2.0 | MIT | MIT | AGPL-3.0 |
1 skills (instruction sets) by oil-oil that an AI reads and follows · not an MCP server
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Codex
From the maker’s README and the folders in the repo
GitHub account oil-oil (person), 7 years old
★ 1,979 stars · code last changed Nov 16, 2026
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
First: which AI do you use?
Pick your app and this page shows only how to install it there
Uploading to claude.ai would fail: the description is over 200 characters (661). Use "Let the AI install it" instead
Copy this sentence and paste it into a Claude Code 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
Restart Claude Code, then type /beautify-github-readme or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Already installed? Check first · Open Terminal, type this command and press Enter
node -vMac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed
Open the Node.js download page ↗
When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v
Install once; it works for everything that needs Node.js
Checking the commands · copy buttons appear once they pass
Copied from the maker’s README; it downloads and runs the maker’s code
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Open Codex in the ChatGPT desktop app and paste this sentence into the chat
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
Put the beautify-github-readme folder at ~/.agents/skills/beautify-github-readme
~ is your home folder ($HOME)
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Skills you install yourself do not work here; only skills that come with a plugin from the directory
To use this skill with ChatGPT, use the ChatGPT desktop app as above
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension
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 picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Copy this sentence and paste it into a Cursor 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
In Cursor’s Agent chat, type / and pick beautify-github-readme
Checked against official docs Nov 12, 2026 · Source: cursor.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · 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 Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.
Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026
The text below comes from the maker’s repo, not from PopNx MCP
Showing the first 8,000 characters · Open the full file on GitHub
---
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 archAsk, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.