Aliyun Wan Video

What it does

When your agent uses it

• Generating videos with Model Studio DashScope SDK using Wan video generation models (wan2.6-t2v
• Wan2.6-i2v-flash
• Wan2.6-i2v and regional variants)
• Documenting video.generate requests/responses

Example prompts

• “/aliyun-wan-video”

Requirements

• Python 3
• A credential in DASHSCOPE_API_KEY

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
2. 2Run one minimal read-only query first to verify connectivity and permissions.
3. 3Execute the target operation with explicit parameters and bounded scope.
4. 4Verify results and save output/evidence files.

What it can do on your machine

Read from SKILL.md and the folder at commit 1818263. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 2 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python
  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • DASHSCOPE_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Aliyun Wan Video loads about 1.4k tokens when it runs, and up to ~1.9k if it reads all its reference files. Until then it costs about 99 tokens; SKILL.md has 384 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~99

When it runs · the whole SKILL.md, loaded when a task matches

~1.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from cinience/alicloud-skills at commit 1818263, republished under its MIT licence (© cinience). 384 words, ~1,398 tokens.

name

aliyun-wan-video

description

Use when generating videos with Model Studio DashScope SDK using Wan video generation models (wan2.6-t2v, wan2.6-i2v-flash, wan2.6-i2v and regional variants). Use when implementing or documenting video.generate requests/responses, mapping prompt/negative_prompt/duration/fps/size/seed/reference_image/motion_strength, or integrating video generation into the video-agent pipeline.

version

1.0.0

mkdir -p output/aliyun-wan-video
python -m py_compile skills/ai/video/aliyun-wan-video/scripts/generate_video.py && echo "py_compile_ok" > output/aliyun-wan-video/validate.txt

python3 -m venv .venv
. .venv/bin/activate
python -m pip install dashscope

import os
from dashscope import VideoSynthesis

# Prefer env var for auth: export DASHSCOPE_API_KEY=...
# Or use ~/.alibabacloud/credentials with dashscope_api_key under [default].

def generate_video(req: dict) -> dict:
    payload = {
        "model": req.get("model", "wan2.6-i2v-flash"),
        "prompt": req["prompt"],
        "negative_prompt": req.get("negative_prompt"),
        "duration": req.get("duration", 4),
        "fps": req.get("fps", 24),
        "size": req.get("size", "1280*720"),
        "seed": req.get("seed"),
        "motion_strength": req.get("motion_strength"),
        "api_key": os.getenv("DASHSCOPE_API_KEY"),
    }

    if req.get("reference_image"):
        # DashScope expects img_url for i2v models; local files are auto-uploaded.
        payload["img_url"] = req["reference_image"]

    response = VideoSynthesis.call(**payload)

    # Some SDK versions require polling for the final result.
    # If a task_id is returned, poll until status is SUCCEEDED.
    result = response.output.get("results", [None])[0]

    return {
        "video_url": None if not result else result.get("url"),
        "duration": response.output.get("duration"),
        "fps": response.output.get("fps"),
        "seed": response.output.get("seed"),
    }

import os
from dashscope import VideoSynthesis

task = VideoSynthesis.async_call(
    model=req.get("model", "wan2.6-i2v-flash"),
    prompt=req["prompt"],
    img_url=req["reference_image"],
    duration=req.get("duration", 4),
    fps=req.get("fps", 24),
    size=req.get("size", "1280*720"),
    api_key=os.getenv("DASHSCOPE_API_KEY"),
)

final = VideoSynthesis.wait(task)
video_url = final.output.get("video_url")

© cinience, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts, references) in skills/ai/video/aliyun-wan-video of cinience/alicloud-skills.

• SKILL.md
• agents/openai.yaml
• references/api_reference.md
• references/sources.md
• scripts/generate_dancing_video.py
• scripts/generate_video.py

Open the folder on GitHubat commit 1818263