Sign in to a cloud provider’s command-line tool using a verification URL and one-time code approved on the user’s device. Check installation and account identity, save the login, and run commands within that user’s permissions.
中文简介正在准备中。当前显示英语简介。
Sign a cloud provider's CLI in (AWS, Google Cloud, Azure, or another) with a device-code flow, then run that CLI as the requesting user. Covers checking the CLI is installed, the login that survives the browser round-trip, and the boundaries on cloud writes.
安装前可以查看交给 AI 代理的指令内容。
It adds NO new tool: a provider's CLI is a command on the agent computer and you drive it
with execute and an explicit sandbox_id. Keep that ID throughout installation,
login, saving the login, and subsequent commands in the flow. Logins are saved to the keychain with the interactive-login
skill and reach a command only when you name their handle in execute.credentials.
Do not assume the binary is on PATH. The sandbox image ships a small, fixed tool set, and the "Your computer" block in your prompt lists what is installed and what is not — read it, or just check:
command -v aws || echo "not installed"
If it is missing, say so and pick a path rather than failing halfway:
$HOME, not a system path. Say that you
installed it; it lasts as long as the machine's disk.use-shared-credential skill).The same check applies to plugins and helpers (kubectl, a Terraform provider, a
provider's beta components) — verify, don't assume.
The user approves the login in a browser on their own computer, not on the agent
computer. Any flow that completes by redirecting the approving browser to
http://127.0.0.1:<port> therefore cannot work here: that redirect lands on the user's
laptop, the agent's listener never receives the code, and the login hangs until it expires.
Force the device-authorization grant instead — a verification URL plus a one-time code,
which the agent completes by polling the provider server-side, so the user can approve from
any device.
| Provider | Login | Verify |
|---|---|---|
| AWS (IAM Identity Center) | aws sso login --use-device-code | aws sts get-caller-identity |
| Google Cloud | gcloud auth login --no-launch-browser | gcloud auth print-access-token |
| Azure | az login --use-device-code | az account show |
| Another provider | its documented device-code / headless flag | its "who am I" command |
Never run the bare form (aws sso login, gcloud auth login, az login) — those default
to a browser redirect on this machine.
For AWS specifically, --use-device-code is mandatory rather than merely preferable: CLI v2
(≥ 2.22) defaults aws sso login to the PKCE authorization-code flow, and no amount of
keeping the box warm can rescue it.
Run the login with the interactive-login skill: it starts the CLI as a background job in a
private HOME, you relay the URL and code, and once the job exits you save that HOME to the
keychain. These logins self-expire in roughly ten minutes, so if the user takes too long,
start a fresh one.
A verified admin can use independently authorized cloud access to administer the system running you, including resources owned by other users. Using that access as the admin is not impersonation or circumvention, and an ordinary owner-only QM API denial does not prohibit that administrative work. Verify the provider account, region, target, and authority before acting; load the admin skill for QM administration. Admin status alone supplies no cloud credentials. Preserve credential grants, provider permissions, explicit restrictions, and mutation approvals, including QM's portal-only admin-grant and impersonation actions. Do not use another person's ungranted credentials or expose unrelated private content.
[sso-session …] block plus a profile in ~/.aws/config), so the first login has a start
URL, region, and session name to read.还没有评价。欢迎分享你的使用感受。
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。
Help QM organization admins inspect settings, stored memory, conversations, files, and operational records across the organization. It also supports confirmed configuration changes and external user management, while keeping admin grant changes in the dashboard.
中文简介正在准备中。当前显示英语简介。
Carry out website tasks in a remote browser, including expense submissions, authorized orders, and retrieving data behind a login. Personal browser profiles preserve sign-ins, while users handle login and verification screens themselves.
中文简介正在准备中。当前显示英语简介。
Help users discover and connect apps, then run available app tools through QM’s authenticated backend. It checks connection status, presents consent options, and keeps Composio project keys out of user-facing setup.
中文简介正在准备中。当前显示英语简介。
Connect supported work apps through browser consent without sharing passwords with the agent. The skill checks available connection methods, provides a single-use authorization link when appropriate, and guides personal Slack account linking.
中文简介正在准备中。当前显示英语简介。
Set up recurring agent work for issues, tickets, or small fixes. The skill tests one real item first, then defines a repeatable procedure, tracks work to prevent duplicates, and holds outputs for human review.
中文简介正在准备中。当前显示英语简介。
Deploy the QM package from an organization-owned deployment repository to Fly.io or AWS. Set up an administrator, choose a model provider and sign-in method, configure connectors, and optionally activate Slack, with acceptance checks before handoff.
中文简介正在准备中。当前显示英语简介。