local-access
Skill9 starsChanged 8 months agoMITView on GitHub
macOS 本地计算机操作 — 日历、通讯录、邮件、提醒、Finder、剪贴板、浏览器、应用控制
In this repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- chart-creationSkill
- code-rulesSkill
- conditional-formattingSkill
- data-analysisSkill
- data-cleaningSkill
- equity-valuationSkill
- financial-modelingSkill
- formula-operationsSkill
- sandbox-executorSkill
- template-generationSkill
- wps-core-apiSkill
- connector-managerSkill
- financial-dataSkill
- knowledge-baseSkill
- sensortowerSkill
- similarwebSkill
- web-searchSkill
- equity-valuation-frameworkSkill
- agent-modeSkill
- ask-modeSkill
- plan-modeSkill
- memory-managerSkill
- onboardingSkill
- soul-engineSkill
- monthly-reportSkill
The file
Files
本地计算机操作
你可以通过 local.* 操作访问用户的 macOS 系统应用。
使用方式
输出 JSON 指令，格式：
{"_action": "local.calendar.list", "_args": [{"days": 7}]}注意：_args 传入数组，第一个元素是参数对象。
可用操作速查
日历：local.calendar.list 查看事件、local.calendar.create 创建事件 通讯录：local.contacts.search 搜索联系人 邮件：local.mail.send 发送邮件、local.mail.unread 查看未读 提醒：local.reminders.list 查看、local.reminders.create 创建 文件：local.finder.open 打开目录、local.finder.selection 获取选中文件 剪贴板：local.clipboard.get 读取、local.clipboard.set 写入 浏览器：local.browser.tabs 查看标签页、local.browser.open 打开网址 应用：local.apps.list 列表、local.apps.launch 启动、local.apps.quit 退出 系统：local.system.info 获取主机名、用户、电池、磁盘信息
Reasoning
当用户请求涉及本地系统应用时：
- 识别需要哪个 local.* 操作
- 输出对应 JSON 指令
- 如果权限不足，系统会返回引导信息，转告用户需要在系统设置中授权
- 操作成功后，用自然语言总结结果
常见场景
- 查查我本地日历 -> local.calendar.list
- 帮我发一封邮件 -> local.mail.send
- 搜索联系人张三 -> local.contacts.search
- 帮我创建一个提醒 -> local.reminders.create
- 打开 Downloads 文件夹 -> local.finder.open
- 我剪贴板里有什么 -> local.clipboard.get
- 查看浏览器标签页 -> local.browser.tabs
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.