XcodeBuildMCP
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
Pagekin,免费 AI 小说写作软件,从设定、蓝图到正文、审稿、定稿;支持拆解仿写、续写、改写,可导入写作 Skill(如去 AI 味)。模型需自行配置,作品在本地。Pagekin (formerly AI Novel Writer): free, open-source AI novel writing app for long novels and web fiction. Imitate, continue, rewrite; import writing skills. Local-first, no model bundled. Windows & macOS.
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/ethanyoq-pagekin)MCP servers that connect the AI to services for the same work
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more
Same kind of work, ordered like the Skills list
| This one Pagekin | MinerU | watermarks-remover | obsidian-skills | anysearch-skill | |
|---|---|---|---|---|---|
| Maker | EthanYoQ | opendatalab | guillaumemeyer | kepano | anysearch-ai |
| Skills | 1 | 1 | 1 | 5 | 1 |
| GitHub stars | 2,697 | 83,919 | 27,723 | 53,104 | 6,905 |
| Last code change | Nov 18, 2026 | Nov 18, 2026 | Nov 17, 2026 | Sep 15, 2026 | Nov 13, 2026 |
| License | GPL-3.0 | – | MIT | MIT | Apache-2.0 |
1 skills (instruction sets) by EthanYoQ 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.
Claude Code
From the maker’s README and the folders in the repo
GitHub account EthanYoQ (person) is only 9 months old: take extra care
★ 2,697 stars · code last changed Nov 18, 2026
No, plain text files the AI reads and follows
No scripts, so it does not go online by itself
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 1993b76 (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
This skill uses the GPL-3.0 license, which is not on the list we redistribute, so we do not hand out a ZIP from our site. Download it from GitHub and arrange the folder yourself, or use "Let the AI install it" above, which is easier
Download from GitHub (whole repo) ↗
Unzip it, then zip only the .claude/skills/verify folder again. The ZIP must have a verify folder with SKILL.md at the top level, no loose files
+Create skillUpload a skillpick verify.zip
SettingsCapabilitiesCode execution and file creation
Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free
Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)
Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)
Checked against official docs Nov 12, 2026 · Source: support.claude.com, support.claude.com, code.claude.com
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 /verify 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.
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
git clone --depth 1 https://github.com/ethanyoq/pagekin.git /tmp/popnx-skill-ethanyoq-pagekin-1993b76 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-ethanyoq-pagekin-1993b76/.claude/skills/verify' ~/.claude/skills/verifyThe 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 verify folder at ~/.agents/skills/verify
~ 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
git clone --depth 1 https://github.com/ethanyoq/pagekin.git /tmp/popnx-skill-ethanyoq-pagekin-1993b76 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-ethanyoq-pagekin-1993b76/.claude/skills/verify' ~/.agents/skills/verifyChecked 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
git clone --depth 1 https://github.com/ethanyoq/pagekin.git /tmp/popnx-skill-ethanyoq-pagekin-1993b76 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-ethanyoq-pagekin-1993b76/.claude/skills/verify' ~/.agents/skills/verifyCopy 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 verify
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
git clone --depth 1 https://github.com/ethanyoq/pagekin.git /tmp/popnx-skill-ethanyoq-pagekin-1993b76 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-ethanyoq-pagekin-1993b76/.claude/skills/verify' ~/.cursor/skills/verifyFor 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
✓ Commands checked Nov 16, 2026
The text below comes from the maker’s repo, not from PopNx MCP
3,886 characters · Open the full file on GitHub
---
name: verify
description: 在真实 Electron 里驱动书童做实机验证:截图、复现界面缺陷、跑 redesign 场景、测启动耗时与内存、读只读诊断。Use for real-app verification of Pagekin (书童) - screenshots, reproducing UI bugs, running redesign scenarios, startup timing, idle memory, read-only DOM and console diagnostics.
---
# verify
驱动脚本是 `scripts/redesign/drive.mjs`。它用 Playwright 的 `_electron` 启动当前工作树的构建产物(`electron .`),每个会话(一次冷启动)一个全新的隔离目录,模型调用默认走本机假服务,不调用真实模型;只有带 `--real-model` 跑 `real-*` 场景时,请求发往硅基流动 `https://api.siliconflow.cn/v1/`。单跑一个场景就是只含这个场景的会话。
窗口开在屏幕外,不抢焦点,不打扰正在用电脑的人。不碰 `%APPDATA%\ai-novel-writer`,也不碰维护者正在运行的书童。
## 启动前
在要验证的工作树根目录依次运行。Windows 用 Git Bash(Bash 工具)。`cmd //c` 是 Git Bash 的写法,在 PowerShell 里它只打开一个提示符、不执行命令;在 PowerShell 里要写成 `cmd /c`。
```bash
fnm exec --using=22.23.1 -- cmd //c pnpm install --frozen-lockfile --ignore-scripts
fnm exec --using=22.23.1 -- node node_modules/electron/install.js
fnm exec --using=22.23.1 -- cmd //c pnpm build
```
macOS 没有 `cmd`,在终端里直接调 `pnpm`:
```bash
fnm exec --using=22.23.1 -- pnpm install --frozen-lockfile --ignore-scripts
fnm exec --using=22.23.1 -- node node_modules/electron/install.js
fnm exec --using=22.23.1 -- pnpm build
```
- 驱动直接 import 应用里的 `.ts`,要 Node 自带的类型剥离。本机默认 Node 不一定满足,统一用 fnm 的 22.23.1 跑驱动。版本不对时驱动报错并给出这条命令。
- 驱动加载的是 `dist/` 与 `dist-electron/`,改了 `src/` 或 `electron/` 必须重新 `pnpm build`。没构建时驱动退出码 2,并提示先构建。
- `better-sqlite3` 是 Node-API 预编译包,vitest 与 Electron 共用同一份二进制,跑测试和驱动之间不用切换。
## 命令
```bash
fnm exec --using=22.23.1 -- node scripts/redesign/drive.mjs --scenario <名称> [--theme light|dark] [--out <目录>] [--dump-dom] [--console] [--video] [--app-root <目录>] [--shell writer|stage] [--real-model]
```
- 参考文件里的命令都省略了前缀,运行时补上:`node …` 前加 `fnm exec --using=22.23.1 --`;`pnpm …` 在 Windows 的 Git Bash 里加 `fnm exec --using=22.23.1 -- cmd //c`(`fnm exec` 找不到 `pnpm.cmd`,直接写 `pnpm` 会报 program not found),macOS 加 `fnm exec --using=22.23.1 --`。
- 不带参数运行会打印全部场景名,退出码 2。场景定义在 `scripts/redesign/*-scenarios.mjs`。
- `--theme` 默认 `light`(浅色),`dark` 为深色。界面类改动浅色、深色各截一次。
- `--out` 默认 `.runtime/redesign-baseline/`。batch 线按任务书指定的截图目录传。
- `--dump-dom` 在每个截图点另写 `.dom.html` 与 `.aria.yml`。`--console` 写渲染进程、主进程与假模型的日志。排查时两个一起开。
- `--video` 录屏,要本机有 `ffmpeg`。
- `--app-root` 指向另一个已构建的工作树,用同一个驱动测 trunk 与 head。
- `--shell` 只对 RD-10 之前的 trunk 有意义。当前构建只有纸墨外壳,不要传。
- `--real-model` 只用于 `real-*` 场景,密钥从环境变量 `SILICONFLOW_API_KEY` 读,不要打印。
## 输出
在 `--out` 目录下:
- `<场景>-<主题>.png`:截图,1440×900。
- `<场景>-<主题>.json`:结果数组,每个截图点一项。`measured` 是场景自己的断言值,`error` 写失败原因。
- 失败时另有 `<失败场景>-<主题>.failure.png`、`.dom.html`、`.aria.yml` 和 `<会话>-<主题>.console.log`,隔离目录保留以便排查。
## 退出码
- 0:全部通过。
- 1:有场景失败,或会话结束检查没过。检查三项:主进程没有放出外部请求(`externalRequests`),应用关闭后没有残留进程(`residualProcesses`),真实配置目录没有新写入(`externalWrites`)。
- 2:参数错误、场景名不对,或目标工作树没构建。
退出码 1 先看结果 JSON 的 `error`,再看 `.failure.png` 和 `.console.log`。不要只凭退出码 0 宣称验证通过,还要看截图。
## 截图规则
- 每张截图都用 Read 工具亲自看,不只看退出码和 `measured`。
- 截图说明逐项写出画面上每个动态值的期望值,并和同屏其他值互相核对。动态值指时间、计数、章号、字数、进度这类会随数据变化的值。
- 反例:batch10 #600 的一屏里有两个时间,相差 8 小时。验收只看了文案长短,没有核对两个时间是否一致,缺陷被放行了。
- 写法:「<位置 A> 的 <值>:期望 X,实际 X;与 <位置 B> 的同一值 X 一致」。同一事件在两处显示的时间、同一计数在标题和列表里的数目、当前章号在各处的显示,都要两两对上。
- 改界面的 PR,浅色、深色各一张。宽度敏感的改动加跑 1280 宽的场景(见 `references/rd-review-scenarios.md` 的 `rd10-widths`)。
- 比较前后截图,先确认同一场景连续跑稳定,再谈差异。做法见 `references/measurement.md`。
## 什么时候读哪份参考
| 要做的事 | 读 |
|---|---|
| 查参数细节、结果 JSON 每个字段、会话结束检查的范围、只读诊断、改页面对象或假模型 | `references/driver.md` |
| 找纸墨外壳某一页的现成场景(流程脊、运行侧页、书房、设置、架构、角色、蓝图、正文、作品资料页) | `references/rd-stage-scenarios.md` |
| 键盘、英文界面、宽度、对比度、标签菜单这类横跨页面的场景 | `references/rd-review-scenarios.md` |
| 某个已修 issue 的回归场景(#382 起) | `references/issue-scenarios.md` |
| 截图可重复性、启动耗时、空闲内存、页面内计时 | `references/measurement.md` |
| RD-10 之前的旧外壳基线场景,只对 trunk 跑 | `references/baseline-scenarios.md` |
参考里没写到的场景,以 `scripts/redesign/*-scenarios.mjs` 的源码为准。新加场景时,在对应参考文件里补一行。
## 提交本 skill 的改动
`.claude/` 在 `.gitignore` 里,提交要用 `git add -f .claude/skills/verify`。
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.