email-draft
Use when the user asks to draft, polish, translate, or reply to an email. Produces a clean draft with subject line, greeting, body, and sign-off, plus a…
Hope Agent native macOS desktop control — the standard `mac_control` status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog
$ npx -y skills add shiwenwen/hope-agent --skill ha-mac-control --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ha-mac-controlContext preview
The summary Claude sees to decide when to auto-load this skill.
Hope Agent native macOS desktop control — the standard `mac_control` status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog
name: ha-mac-control description: "Hope Agent native macOS desktop control — the standard `mac_control` status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog state. Load whenever using `mac_control`, or when the user asks to control local Mac apps, Dock, Spaces, click/type/menu/window/dialog/clipboard, automate Finder/TextEdit/System Settings, visually locate UI, or says 控制 Mac, macOS 自动化, 点按钮, 打开应用, Dock, Space, 关闭窗口, 菜单点击, 视觉定位." version: 1.0.0 author: Hope Agent license: MIT allowed-tools: [mac_control, ask_user_question] status: active
`mac_control` operates the user's macOS desktop from the authorized Hope Agent app process. macOS UI state is volatile: apps steal focus, AX IDs expire, sheets attach to windows, and multiple windows often share similar titles. Use a fresh observation before every meaningful action.
Use this loop unless the user explicitly asks for a single read-only query:
1. mac_control(action="status") 2. mac_control(action="apps", op="frontmost" | "search" | "installed") 3. observe: snapshot / visual.observe / elements.find / windows.list / dock.list / spaces.list / menu.list / menu.popover / dialog.inspect 4. act: apps.activate/launch, dock.launch, spaces.switch, windows.*, act.*, menu.click, dialog.* 5. verify: wait, snapshot, windows.list, or dialog.inspect
For a concrete app workflow:
apps.launch bundleId=... apps.frontmost # verify focus if the next step depends on menus/input snapshot, elements.find, or windows.list # get fresh window/element ids act/menu/windows/clipboard/dialog # one action burst wait or snapshot # verify the expected change
🦭 会记忆、能持续推进目标、会动态编排多 Agent 的跨端桌面 AI 助手,也可服务化常驻 NAS / 云端 | A cross-device desktop AI agent with memory, autonomous goals, dynamic workflows, and headless deployment
Repo: shiwenwen/hope-agent
Use when the user asks to draft, polish, translate, or reply to an email. Produces a clean draft with subject line, greeting, body, and sign-off, plus a…
Use when the user mentions 飞书 / Feishu / Lark workspace operations: docx (云文档) read/write, bitable (多维表格) records / views / dashboards, drive (云盘)…
Hope Agent browser automation — the standard `status → tabs → snapshot → act` loop, stale-ref recovery rules, and what to do when login / 2FA / captcha /…
Hope-native review of uncommitted, staged, commit, branch, or PR changes: discover concrete regressions, independently verify candidates, and report actionable…
Hope-native baseline for implementing, fixing, refactoring, and maintaining code: inspect the repository first, protect user changes, keep scope narrow, and…
Hope-native implementation planning for non-trivial code changes: ground the plan in repository evidence, order dependencies, name critical files and risks,…