Individual skill

huashu-mac-use

操控没有API的macOS原生app并留下可复现取证：截指定窗口（后台被遮挡也能截）、点击输入、探测某个app能不能自动化、内嵌Chromium的app走CDP零焦点操控、做产品实测与多模型跑批。浏览器里的事走huashu-chrome，翻旧截图走disk-keeper。

SKILL.md

Read pinned source

Source commit 95892a0d5df7547ccc6b53a6074287a49acfcfb6

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: No
Observed behavior: Not checked yet
Last checked: Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 340
Repository last updated: Nov 7, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skills Repository topic
automation Repository topic
claude-code Repository topic
claude-code-skills Repository topic
claude-skills Repository topic
codex Repository topic
computer-use Repository topic
cursor Repository topic
huashu-skills Repository topic
macos Repository topic
engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

.gitignoreasset · 51 bytes
LICENSEasset · 1,072 bytes
README.mddoc · 16,939 bytes
SKILL.mdcore · 12,787 bytes
SKILL.mdcore · 12,787 bytes
assets/banner.svgasset · 5,929 bytes
assets/case-blender-gui.jpgasset · 363,558 bytes
assets/case-cruise-compare.jpgasset · 786,968 bytes
assets/case-donut.jpgasset · 298,691 bytes
assets/hero-cruise.gifasset · 8,918,770 bytes
assets/hero-donut.gifasset · 9,485,521 bytes
assets/how-it-works-gen.pyruns · 12,617 bytes
assets/how-it-works.htmlasset · 16,114 bytes
assets/how-it-works.pngasset · 553,727 bytes
assets/wechat-qrcode.jpgasset · 50,292 bytes
references/about-author.mddoc · 9,941 bytes
references/app档案.mddoc · 34,790 bytes
references/取证规范.mddoc · 10,895 bytes
references/控制面详解.mddoc · 13,612 bytes
references/权限与故障.mddoc · 17,881 bytes
references/踩坑实录.mddoc · 37,841 bytes
scripts/build.shruns · 459 bytes
scripts/cdp.jsruns · 24,327 bytes
scripts/mac.swiftasset · 71,712 bytes
scripts/probe.shruns · 12,315 bytes

Read excerpt


# huashu-mac-use · 操控没有 API 的原生 app

你是 macOS 自动化工程师兼取证员。你的独特价值不是「能截图」，是**操控一个既没有 CLI 也没有 API 的 GUI-only 原生 app，并把每一步都留成可复现的证据**——桌面 AI 客户端这类东西，命令行进不去、网页工具够不着，只有你能一边操作一边把窗口拍下来。你交付的标准是：用户在另一个窗口打字时完全感觉不到你在干活，而你交出的每一张图都能说出它是怎么来的。

`$SKILL_DIR` 指本文件所在目录。脚本一律写全路径调用（agent 的 cwd 是用户项目目录）。首次用先 `bash $SKILL_DIR/scripts/build.sh` 编译内核（约 20 秒）。

## 一、第一步该不该是它

| 任务信号 | 走哪 |
|---|---|
| 操控 Mac 原生 app：点菜单、填输入框、读界面、切窗口；系统层动作（打开退出 app、系统设置） | 本 skill |
| 给某个 app 的窗口截图取证（配图、汇报、复现 bug） | 本 skill，窗口级截图别的 skill 都够不着 |
| 探测陌生 app 能不能自动化 | `probe.sh` |
| 多模型同题跑批，目标是**桌面客户端本身** | 本 skill（只关心模型能力 → multi-model 走 API） |