REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Universal mobile devtool for Agents & Humans - control iOS Simulators, Android Emulators, and real devices from a single dashboard and CLI
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/pranshuchittora-simvyn)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 simvyn | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | pranshuchittora | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 447 | 465,460 | 233,910 | 149,364 | 144,149 |
| 最近代码更新 | 2026年10月29日 | 2026年11月17日 | 2026年4月20日 | 2026年11月17日 | 2026年11月17日 |
| 许可证 | MIT | MIT | – | Apache-2.0 | MIT |
pranshuchittora 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 pranshuchittora (person), 9 years old
★ 447 stars, few users so far · code last changed 2026年10月29日
1 scripts that can run on a computer: scripts/simvyn.mjs
No internet calls found in the scripts
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 198e1c1 (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 (296). 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 /simvyn,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 simvyn 文件夹放到 ~/.agents/skills/simvyn
~ 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 simvyn
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
3,751 个字符 · 在 GitHub 打开完整文件
---
name: simvyn
description: Operate iOS Simulators, Android Emulators, and connected mobile devices with Simvyn. Use for device discovery, app installation and launch, screenshots, logs, deep links, location simulation, app data inspection, device settings, and reusable device workflows through the Simvyn CLI or dashboard.
license: MIT
---
# Simvyn
Use Simvyn to inspect or operate the user's mobile development environment. This is a CLI workflow skill and does not register MCP tools. When the `simvyn`, `simvyn_screenshot`, `simvyn_logs`, and `simvyn_record` tools are available, as in Pi with the simvyn package installed, prefer them over the launcher: they resolve the CLI, bound log and recording captures, and return screenshots as images. The references below apply to both.
Requires Node.js 22 (22.14.0+) or 24+ and an installed or built Simvyn CLI. macOS supports iOS and Android; Linux supports Android. iOS requires Xcode and simulator runtimes; Android requires adb and configured devices or emulators. See the platform reference for operation-specific requirements.
## Start with the installed CLI
Resolve paths relative to this skill directory, not the user's project directory. The supplied launcher prefers the CLI bundled beside the installed skill, then a built Simvyn checkout, then `simvyn` on `PATH`. It does not download packages, build the project, or start a server on its own.
```bash
node /absolute/path/to/skills/simvyn/scripts/simvyn.mjs --version
node /absolute/path/to/skills/simvyn/scripts/simvyn.mjs device list --json
```
In the references, `simvyn` means this resolved invocation, or the user's existing `simvyn` executable when appropriate. Read `--help` for the installed command if its version differs from these references. Running with no arguments starts the dashboard; use an explicit subcommand for headless work.
Choose the full device ID from discovery and retain it through the task. Device name and ID-prefix matching are inconsistent across commands. Rediscover after booting an Android AVD because `avd:<name>` changes to an `emulator-<port>` ID. Most operations require a booted device. A discovered physical device may still need to be unlocked or trusted.
## Choose the relevant reference
- [CLI commands](references/cli.md): argument order, supported options, output forms, and commands missing from brief help examples.
- [Platform support](references/platforms.md): read before physical-device operations, permissions, app data inspection, clipboard work, or selecting an iOS/Android equivalent.
- [Recipes](references/recipes.md): app repro sessions, screenshots, Android local development, GPS and push testing, accessibility checks, and multi-device collections.
- [Automation and troubleshooting](references/automation.md): read for scripts/CI, JSON parsing, long-running processes, failed commands, and collection result interpretation.
## Execute and verify within the task
Use the actions needed for the user's request. Inspect an existing collection with `collections show` before applying it: its name does not reveal whether it erases data, launches apps, or changes settings. Preserve any existing authorization; when a requested diagnosis does not include deleting/resetting data, propose the concrete reset before doing it.
Save screenshots, recordings, and downloaded files to explicit paths and inspect the artifacts needed to substantiate the result. A screenshot command returns a path; the agent must use its own image-viewing tool to inspect the image. Report the device, actions performed, artifact locations, and observed failures or unsupported operations. Do not infer success from a command being available or from a collection's zero exit status alone.
提问、分享技巧或报告无法使用。按“有帮助”数量排序。