native-feel-skill Skill
What it does
An Agent Skill for designing cross-platform desktop apps that feel native — distilled from Raycast's 2.0 deep-dive and reverse engineering of Raycast Beta.app. Eight architectural tenets, four-layer architecture, WebKit/WebView2 survival guide, 75-item ship audit.
- Connects Instruction files the AI reads; connects to nothing
- Account or key No key needed
- Category Coding
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/yetone-native-feel-skill)Use together with
MCP servers that connect the AI to services for the same work
Fallow
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
Desktop Commander
MCP server for terminal commands, file operations, and process management
Similar Skills
Same kind of work, ordered like the Skills list
| This one native-feel-skill | rea | graphify | archify | security-audit-skill | |
|---|---|---|---|---|---|
| Maker | yetone | morluto | Graphify-Labs | tt-a1i | cloudflare |
| Skills | 1 | 1 | 1 | 1 | 1 |
| GitHub stars | 1,965 | 461,751 | 148,352 | 96,757 | 73,156 |
| Last code change | May 30, 2026 | Nov 16, 2026 | Nov 16, 2026 | Nov 15, 2026 | Sep 15, 2026 |
| License | MIT | MIT | Apache-2.0 | Apache-2.0 | MIT |
1 skills (instruction sets) by yetone that an AI reads and follows · not an MCP server
How a Skill differs from MCP
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.
Works with
Claude CodeCursor
From the maker’s README and the folders in the repo
Install
Is it safe?
- Who made it
GitHub account yetone (person), 14 years old
- Use and upkeep
★ 1,965 stars · code last changed May 30, 2026
- Any scripts?
No, plain text files the AI reads and follows
- Uses the internet?
No scripts, so it does not go online by itself
- Changes machine-wide settings?
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 9bd88c6 (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
Option 1Upload to claude.ai (web and app)
Uploading to claude.ai would fail: the description is over 200 characters (654). Use "Let the AI install it" instead
Option 1Let Claude Code install it
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 /native-feel-skill or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
The maker’s recommended way
Install Node.js (if you don’t have it)
Already installed? Check first · Open Terminal, type this command and press Enter
node -v- A version number such as v26.13.1 = installed, skip this step
- "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
How to open Terminal
Mac: 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
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.claude/skills
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
Restart Claude Code, then type /native-feel-skill or ask for a matching task and Claude picks it up
ChatGPT desktop app
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Option 1Let ChatGPT install it
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
Option 2Put the folder there yourself
Put the native-feel-cross-platform-desktop folder at ~/.agents/skills/native-feel-cross-platform-desktop
~ is your home folder ($HOME)
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
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
After installing
- ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
- 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
- Codex picks up newly installed skills by itself; if one does not show up, restart Codex
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
ChatGPT on the web and mobile
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
Option 1Let Codex install it
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
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
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
Restart Codex, then ask for a matching task; Codex lists the skill
Option 1Let Cursor install it
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 native-feel-skill
Checked against official docs Nov 12, 2026 · Source: cursor.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.cursor/skills
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
In Cursor’s Agent chat, type / and pick native-feel-skill
Option 1Let the AI install it
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
For Terminal users
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
View the original SKILL.md
The text below comes from the maker’s repo, not from PopNx MCP
6,105 characters · Open the full file on GitHub
---
name: native-feel-cross-platform-desktop
description: Use when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a native app to its users — fast launch, native windowing, native input handling, native materials. Trigger words include "cross-platform desktop", "Electron alternative", "Tauri vs native", "WebView wrapper", "near-native performance", "Raycast architecture", "WebKit/WebView2 quirks", "WKWebView", "system tray app", "global hotkey app", "launcher app". Do NOT trigger this skill for pure web apps, pure mobile apps, or for greenfield projects that have no native-feel requirement.
---
# Native-Feel Cross-Platform Desktop
You are advising on the architecture of a cross-platform desktop app that must *feel native*. This skill captures the philosophy, architecture, and concrete pitfalls — distilled from Raycast's public technical deep-dive on their 2.0 rewrite and verified by reverse-engineering the shipping `Raycast Beta.app` binary on macOS.
## How to use this skill
1. **Start with the philosophy in `references/01-philosophy.md`.** It frames the central tension this architecture resolves — *how to get cross-platform DX and near-native performance at the same time* — and gives you eight tenets that name the structural moves. Every concrete decision later flows from one of those tenets. If the user is making a decision that contradicts a tenet, surface the tenet by number and short name and explain the trade-off.
2. **Match the user's question to a reference file.** Don't dump the whole skill — load only what's needed:
- Architecture / "which layers should I have?" → `references/02-architecture.md`
- "Why does my WebView flicker / stutter / freeze when hidden?" → `references/03-webview-survival.md` (the highest-density file — every item is a real bug with a real fix)
- "How do I type my IPC across Rust/Swift/C#/TS?" → `references/04-ipc-contract.md`
- "Why does Activity Monitor say 400 MB?" → `references/05-memory-truths.md`
- "How do I make it not feel like a webpage?" → `references/06-native-conventions.md`
- "What does Raycast actually ship?" (concrete evidence) → `references/07-evidence-raycast.md`
3. **Before recommending an architecture, run the decision tree in `checklists/decision-tree.md`.** It rules this stack OUT for several common project shapes — say so directly.
4. **Before the user claims their app "feels native", run `checklists/ship-readiness.md`.** It's a 30-item audit; most apps fail 5–10 items on first pass.
## The one-paragraph version
A native-feel cross-platform desktop app is **not a web app with native hooks** and **not Electron with a custom theme**. It is a **native shell** (Swift/AppKit on macOS, C#/WPF on Windows) that owns the window, the hotkeys, the menu bar, the materials, and the lifecycle — and embeds the system WebView (WKWebView or WebView2) purely as a *rendering surface* for a shared React/TypeScript UI. Business logic lives in a long-lived Node process bundled with the app. Performance-critical subsystems (file indexing, calculation, crypto) live in Rust, shared across platforms and exposed through UniFFI-generated typed bindings. Four runtimes communicate through a single declared interface that generates typed clients for each side. The whole thing fits in ~400 MB resident memory, of which ~150 MB is the inescapable WebView+Node baseline. You pay that baseline so that one React codebase serves both OSes; you earn it back through hot-reload iteration speed and a shared extension API that already runs thousands of community plugins on both platforms.
## Core anti-patterns to call out immediately
When you see the user doing any of these, stop and ask:
- **"Let's just use Electron and theme it"** → Electron abstracts away the system WebView, window class, and material APIs you need for native feel. You cannot get Liquid Glass / acrylic / true vibrancy through Electron's abstraction without forking it. Recommend `references/02-architecture.md` instead.
- **"Let's use Tauri — it's like Electron but lighter"** → Tauri ships its own WebView wrapper and abstracts platform APIs. Same control-loss problem as Electron, plus less mature. Acceptable for utilities; not for apps where every window animation has to match the OS.
- **"Let's render UI in Swift/C# and share business logic"** → You will maintain two UI codebases forever. Every feature ships twice. Designers maintain two specs. Recommend WebView-as-renderer instead.
- **"WebKit is throttling us; let's spin our own polling loop"** → No. The throttling is solvable with two specific `WKWebView` configuration flags. See `references/03-webview-survival.md` § "Hidden window throttling".
- **"Memory is bad — we're at 400 MB"** → Probably wrong measurement. Activity Monitor double-counts shared frameworks and treats compressed pages as resident. See `references/05-memory-truths.md` before optimizing anything.
- **"Let's hand-write the IPC types in each language"** → They will drift within a sprint. Use UniFFI (for Rust ↔ Swift/Kotlin/C#) or hand-roll a single IDL that generates clients. See `references/04-ipc-contract.md`.
- **"Adding `cursor: pointer` to make it feel responsive"** → That's exactly what makes it feel *web*. Native UIs do not change the cursor on hoverable rows. See `references/06-native-conventions.md`.
## Output style
When advising:
- Quote the specific tenet from `references/01-philosophy.md` that applies (e.g., *"T3 — adopt the platform; don't compete with it: the OS draws blur better than you can"*).
- Cite the file and section, not the whole skill.
- For each recommendation, name what the user is **giving up** in exchange. There are no free wins in this architecture — the whole skill is about deliberate trade-offs.
- If you're unsure whether the user's project should even use this architecture, run them through `checklists/decision-tree.md` before giving advice. It is okay to conclude "this skill doesn't apply — build a normal Electron app."
Discussion
Ask, 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.
From GitHub
- GitHub stars
- 1,965
- Maker
- yetone
- License
- MIT
- Last code change
- May 30, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 1