agentleFS
ArchAIHarnessArchAIHarness/agent-workflows/skills/engineering/doubao-video/SKILL.md

doubao-video

Skill1 starsChanged 5 months agoMITView on GitHub

Use when needing to generate videos with Doubao (豆包) Seedance / Seedream models via Volcengine Ark (火山方舟). Supports text-to-video and image-to-video: create generation tasks, query task status, list tasks, and cancel/delete tasks. Models: doubao-seedance-2.0, doubao-seedance-2.0-fast, doubao-seedance-1.5-pro, doubao-seedream-5.0-lite. Configure API_KEY in .doubao-video/.env before use.

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use doubao_video_list to review recent tasks, and doubao_video_cancel to abort or delete a task.

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

doubao-video

Goal

Provide video generation capabilities using Doubao Seedance/Seedream models on Volcengine Ark. Users configure API credentials once, then the AI creates and tracks asynchronous video generation tasks.

Configuration

API key must be set before first use:

# In project's .doubao-video/.env or ~/.doubao-video/.env
API_KEY=your_ark_api_key_here

Get the API Key from the Volcengine Ark console: https://console.volcengine.com/ark

The config file is auto-created on first tool call if missing.

Models

Specify the target model via the model argument when creating a task.

ModelDescription
doubao-seedance-2.0Seedance 2.0 video generation (default)
doubao-seedance-2.0-fastSeedance 2.0 fast variant, lower latency
doubao-seedance-1.5-proSeedance 1.5 pro video generation
doubao-seedream-5.0-liteSeedream 5.0 lite generation

API Endpoints (Volcengine Ark, Agent/Coding Plan)

ActionMethodEndpoint
Create video taskPOSThttps://ark.cn-beijing.volces.com/api/plan/v3/contents/generations/tasks
Query video taskGEThttps://ark.cn-beijing.volces.com/api/plan/v3/contents/generations/tasks/{id}
List video tasksGET.../tasks?page_num={page_num}&page_size={page_size}&filter.status={status}&filter.task_ids={ids}&filter.model={model}
Cancel/delete video taskDELETEhttps://ark.cn-beijing.volces.com/api/plan/v3/contents/generations/tasks/{id}

Authentication: Authorization: Bearer <API_KEY> header on every request.

Default Tools

  • doubao_video_create — create a text-to-video or image-to-video generation task
  • doubao_video_query — query a task's status and result video URL by task ID
  • doubao_video_list — list tasks with pagination and status/model/task-id filters
  • doubao_video_cancel — cancel or delete a task by task ID

Workflow

  1. User provides a prompt (text-to-video) and/or a first-frame image URL (image-to-video), plus an optional model.
  2. AI reads API_KEY from .doubao-video/.env (auto-created with a clear message if missing).
  3. AI calls doubao_video_create, which returns a task ID.
  4. Video generation is asynchronous — AI polls doubao_video_query with the task ID until status is succeeded (then a video URL is returned) or failed.
  5. Use doubao_video_list to review recent tasks, and doubao_video_cancel to abort or delete a task.

Safety Rules

  • API keys are read from .doubao-video/.env only, never hardcoded and never printed in full.
  • Tools return the raw API response so the AI can surface accurate status with evidence; do not fabricate task status or URLs.
  • The AI must report the actual task ID and status returned by the API. If a request fails, report the HTTP status and error body.
  • User must have a valid API_KEY configured; tools fail with a clear, actionable message if it is missing.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.