跳到正文
cccskills
免费在 GitHub 公开

cua-volume

Save agent memory and outputs in Cua Volume, shared storage that persists beyond a Space, the working environment. Hand files to the user, read shared references, and check synchronization, version history, and conflicting edits.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Use Cua Volume, the one volume every Space and agent of this user shares. Inside a Space it is mounted as a folder (/volume on Linux, ~/Cua Volume on macOS), so any program reads and writes it directly. Use it for anything that must outlive this Space - your memory and outputs in your agent home, shared reference in public/ - and to hand files to the user or to other agents. Use when the user mentions the volume, Cua Volume, shared files, your home or memory, or saving results.

查看安装方法

适用场景

  • Keep outputs after a working environment ends
  • Save agent memory for later work
  • Deliver files to the user
  • Check file sync status and conflicting edits

包含的文件(1)

  • SKILL.md3.8 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Cua Volume

One versioned volume per user. Every write is a new version; deletes keep history. The same files appear on the user's Mac (Finder) and in every Space, within seconds.

Where it is

Where you runPath
A Linux Space/volume (or ~/Cua Volume when /volume is absent)
A macOS Space~/Cua Volume
No mount (Windows for now, or the Space has none)use the volume_* tools below

Check that it is mounted, not just present: mountpoint -q /volume on Linux, ls ~/"Cua Volume" on macOS. A /volume holding only CUA-VOLUME-UNAVAILABLE.txt (read-only) is not the volume: the file says why (for example, a container without /dev/fuse). If it is not mounted, use the tools; nothing written to an unmounted folder is saved.

Layout and what you may do

FolderYou (an agent in a Space)
public/read only: shared reference from the user
agents/<you>/read and write: your home (memory, outputs/, inbox/)
spaces/<this space>/read and write: this Space's scratch and outputs
another agent's home, another Spacenot visible; ask with volume_request_access

Put results the user should see in agents/<you>/outputs/ (or this Space's folder) and tell them the path. A refused write means the folder is not yours: do not retry elsewhere to get around it, ask.

Tools (the cua MCP server)

ToolUse
volume_ls, volume_read, volume_writeThe same files without the mount; each file's sync state
volume_delete, volume_history, volume_restoreWhere offered: delete, old versions, restore one
volume_request_accessAsk the user for more (a folder, r or rw, and why); they approve in Cua
volume_sync_statusSync health, each device's last sync, your files still uploading, conflicts

Inside a Space these tools answer from the user's machine, so they show its view of sync, not only this Space's.

Sync and conflicts

  • A file another device just wrote can take a few seconds to arrive. Before relying on one, check volume_sync_status: feed is live (syncing), off (storage on this machine only: nothing to wait for) or offline (the bucket is unreachable, see last_error: say so rather than trust a stale file). devices shows when each device last synced.
  • volume_ls and volume_read mark a file with sync when it matters: pending_upload (not yet stored, other devices cannot see it yet), conflict (a write lost to a later one; kept at conflict_path), conflict_copy, and written_by when another device wrote it last.
  • Your own writes through the mount upload when you close the file (or after a moment without writes). Close files before telling the user they are ready.
  • When two devices change the same file, the later write wins and the other is kept next to it as name (conflict from <device> <date>).ext. Nothing is lost. Do not delete a conflict copy yourself: tell the user, or merge the two into the current file if the task asks for it.

Never put secrets in the volume

API keys, tokens, passwords and private keys belong in the user's Keyvault. Writes to agent homes are scanned; a write with a secret is refused (secret_detected) and logged. Do not work around the refusal: remove the secret.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Operate native apps on macOS, Windows, and Linux using identified controls, menu paths, or screen coordinates. Target a specific window, verify the result after each action, and consult available recent activity when resuming work.

中文简介正在准备中。当前显示英语简介。

  • Operate a specific app window
  • Click controls and enter text
  • Adjust window positions and sizes
trycua/cua3万2026年10月18日 更新

Create disposable Linux or macOS computers for running code, testing apps, operating desktop interfaces, and browsing websites. Use isolated environments locally or in the Cua cloud, then delete them when the work is complete.

中文简介正在准备中。当前显示英语简介。

  • Run code in an isolated environment
  • Test an app or reproduce an issue
  • Fill web forms and capture page screenshots
trycua/cua3万2026年10月18日 更新

Work in a local or remote computer environment whose screen you can watch. Run commands, transfer files, launch coding agents, move signed-in app sessions, and share the host computer’s network when needed.

中文简介正在准备中。当前显示英语简介。

  • Run tasks in an isolated environment you can watch
  • Transfer files into and out of a Space
  • Launch and monitor coding agents
trycua/cua3万2026年10月18日 更新

Operate apps and websites by inspecting screenshots, clicking controls, typing, and dragging. Use it to fill forms, check layouts, and test complete user flows, with recorded actions available for replay and review.

中文简介正在准备中。当前显示英语简介。

  • Fill forms and use file upload dialogs
  • Test buttons and complete user flows
  • Check layouts and capture screenshots
trycua/cua3万2026年10月18日 更新

jev-use

免费

Build a computer-control loop where Cua Driver observes and acts, while TypeSafe Jev chooses from predefined actions. Validate each choice, execute one action at a time, and verify the result before continuing.

中文简介正在准备中。当前显示英语简介。

  • Build a Jev integration for browser automation
  • Create action candidates for native desktop apps
  • Reject stale or unknown action choices
trycua/cua3万2026年10月18日 更新

Review open GitHub issues, proposals, and pull requests to identify useful maintainer work. Get ranked candidates with evidence, dependencies, and validation needs, then begin work only on an item you explicitly select.

中文简介正在准备中。当前显示英语简介。

  • Choose the next maintenance task
  • Prioritize a backlog for the available work window
  • Find pull requests that need review
trycua/cua3万2026年10月18日 更新

查看 trycua 的全部技能

报告此技能的问题