Seedance Dreamina 即梦 CLI 视频生成下载工作流

Use when an agent needs Dreamina（即梦） image or video generation through the dreamina CLI.

Security Scan

The skill's instructions and requirements are consistent with a CLI wrapper for Dreamina (即梦); the main risk is that it instructs running a remote install script (curl | bash) and encourages reuse of local login state, which you should review before proceeding.

Purpose & Capability

Name, description, and runtime instructions all align: the skill is an instruction-only wrapper for the Dreamina CLI and focuses on submitting/querying image/video generation tasks and checking account state. It does not request unrelated credentials or capabilities.

Instruction Scope

SKILL.md instructs the agent to run dreamina commands, check help, reuse existing login state, run login when needed, and warn about credit consumption. Reusing login state implies the agent may read local CLI session data or configuration, though no explicit paths are named. The instructions do not direct data to external endpoints other than expected Dreamina operations, but you should be aware the agent may access local session files or tokens to operate the CLI.

Install Mechanism

There is no formal install spec, but the instructions recommend running a remote installer via `curl -fsSL https://jimeng.jianying.com/cli | bash`. Piping an external script to bash is inherently risky because it executes remote code without inspection. The hostname appears related to the product, but the skill does not provide a checksum or alternative verified distribution. This is a practical risk to review before following the instruction.

Credentials

The skill declares no required environment variables, credentials, or config paths. This is proportionate to an instruction-only CLI helper. It does instruct reuse of local login state (which is reasonable for a CLI tool) but does not request unrelated secrets.

Persistence & Privilege

The skill is not always-enabled, and it is user-invocable. It does not request to modify other skills or system-wide settings. Autonomous invocation is allowed (platform default) but not accompanied by broad or unexplained privileges.

Assessment

This skill appears to be a straightforward instruction-only helper for the Dreamina CLI and is internally consistent. Before installing or running it: (1) verify the installer URL (https://jimeng.jianying.com/cli) is official and, when possible, inspect the install script instead of piping it directly to bash; (2) be aware that reusing a login state means the agent/CLI will access local session files or tokens—only proceed if you trust the environment and tool; (3) warn users before running commands that will consume paid credits; (4) if you are uncomfortable, manually install the CLI, inspect its documentation, and run commands interactively rather than allowing an agent to run them autonomously.

Dreamina CLI

Use this skill when you need Dreamina（即梦） image or video generation through dreamina.

Requirements

1. 高级会员 此 CLI 工具仅限即梦高级会员使用。

2. 安装方式（官方）

curl -fsSL https://jimeng.jianying.com/cli | bash

安装完成后，运行 dreamina -h 查看所有功能，并执行 dreamina login 完成登录授权。

即梦 is the Chinese product name of Dreamina. If the user says 即梦, treat it as Dreamina and use this skill.

This skill is intentionally short. Detailed flags and supported values belong to the CLI itself, so always treat dreamina -h and dreamina <subcommand> -h as the primary reference.

What this tool is for

dreamina is the local CLI entrypoint for all currently exposed Dreamina（即梦） image and video generation workflows, plus the account/session operations around them.

Use it for:

• checking or reusing an existing Dreamina login session
• checking account credit
• submitting image generation tasks
• submitting video generation tasks
• querying async task results
• reviewing saved task history

Default workflow

When using this CLI as an agent:

1. Start with dreamina -h.
2. Before using any command for real, run dreamina <subcommand> -h.
3. Reuse the current login state unless the user explicitly asks you to login, relogin, or logout.
4. Be explicit about whether you are only reading help, submitting a real task, or querying an existing task.
5. Warn the user before running commands that may consume credits.

Choosing the right command

At a high level:

• Use user_credit to check budget.
• Use query_result when you already have a submit_id.
• Use list_task to review recent saved tasks.
• Use image commands when the input or output is image-first.
• Use video commands when the output is a video.
• Use image2video when one main image is enough; if the user has multiple images for a coherent story, prefer multiframe2video.
• Use multiframe2video for Dreamina's intelligent multi-frame flow: multiple images in, one coherent story video out.
• Use multimodal2video for Dreamina's flagship video mode when the task needs all-around references across images, video, and audio; it supports the seedance2.0 family.

For the exact flags and supported combinations, rely on each subcommand's -h.

Model selection rule

Do not hardcode model support from this skill.

If the user specifies a model, always check the relevant subcommand help before running it:

dreamina <subcommand> -h

Use the subcommand help to confirm:

• whether that command exposes model selection
• whether the requested model is supported on that command
• what other constraints apply to that model, such as duration, ratio, or resolution

Additional guidance:

• some commands do not expose model selection at all
• some models, especially the seedance2.0 family, can be capacity-constrained
• if the user cares more about speed than maximum quality, do not default to seedance2.0 unless they explicitly ask for it

How to judge submit success

Do not rely on shell exit code alone.

For async generation commands, treat a submit as successful only when:

• submit_id is present
• gen_status is querying or success

If gen_status is fail, inspect fail_reason and tell the user the concrete reason.

Follow-up pattern for async tasks

After a submit returns querying:

1. Save the submit_id.
2. Use query_result --submit_id=<id> for follow-up.
3. Use list_task when you want to review saved tasks in bulk.

If you are running a test sweep, keep results in a machine-readable format so you can query the returned submit_id values later.

Important user-facing rules

• Some generation commands are asynchronous; submit and query are separate steps.
• Some models may require a one-time authorization on Dreamina Web. If the CLI returns AigcComplianceConfirmationRequired, tell the user to complete that web-side confirmation first, then retry.
• Do not assume that different commands support the same models, ratios, durations, or resolutions. Check each subcommand's -h before use.

Good agent behavior

• Prefer small, reviewable batches when running real generation tasks.
• Keep a record of the command, arguments, submit_id, and final status for every paid test you run.
• When the user cares about generation speed, do not default to the seedance2.0 family unless they explicitly ask for it or clearly prioritize output quality.
• If you are preparing a report, separate:
  • help-only inspection
  • submit-stage validation
  • later async result follow-up