Alicloud Ai Video Wan R2v

Generate reference-based videos with Alibaba Cloud Model Studio Wan R2V models (wan2.6-r2v-flash, wan2.6-r2v). Use when creating multi-shot videos from refer...

Security Scan

The skill appears to implement Alibaba Cloud Wan R2V workflows, but there are multiple mismatches between its metadata and runtime instructions (undeclared credential requirement, inconsistent file paths/outputs), so proceed with caution.

Purpose & Capability

The stated purpose (Alibaba Cloud Wan R2V reference-to-video generation) matches the included helper script and references to Alibaba docs; requesting an SDK/API key is coherent with that purpose. However, the registry metadata declares no required environment variables or primary credential while the SKILL.md explicitly requires a DASHSCOPE_API_KEY or credentials in ~/.alibabacloud/credentials — an inconsistency that should be resolved.

Instruction Scope

The SKILL.md instructs to install dashscope, set DASHSCOPE_API_KEY, prepare requests, and save outputs — which is within the claimed scope. However, there are multiple practical inconsistencies: the validation command references a path (skills/ai/video/alicloud-ai-video-wan-r2v/scripts/prepare_r2v_request.py) that does not match the provided script path, the expected validation/output directories differ (SKILL.md uses output/alicloud-ai-video-wan-r2v but the script writes to output/ai-video-wan-r2v), and the validation step expects a validate.txt file that the script will not produce. These make the runtime behavior unclear and may cause accidental data placement or failure.

Install Mechanism

There is no formal install spec (instruction-only), which is low-risk for packaging. SKILL.md tells users to create a venv and pip install dashscope — a reasonable, standard approach. The package source (dashscope) should be verified (official PyPI/project) before installation. No remote download/extract behavior is present in the skill itself.

Credentials

The skill's instructions require a DASHSCOPE_API_KEY or entries in ~/.alibabacloud/credentials, which is proportional to calling Alibaba APIs, but the skill metadata does not declare these environment/credential requirements. Requiring an API key without declaring it in metadata is an incoherence that could lead to unexpected secret exposure. The skill does not request unrelated credentials, but the omission in metadata reduces transparency.

Persistence & Privilege

The skill is instruction-only with no install spec and always:false. It does not request persistent system-wide configuration changes or special agent privileges. Autonomous invocation is allowed (platform default) but not combined with other high-risk factors here.

What to consider before installing

This skill mostly does what it says (prepare R2V requests for Alibaba Model Studio) but has practical inconsistencies you should resolve before trusting it with real credentials or production data. Specifically: - Do not assume metadata: SKILL.md requires DASHSCOPE_API_KEY or ~/.alibabacloud/credentials, but the registry metadata lists no required env vars — verify and provide credentials only after confirming the source. - Validate paths: the SKILL.md validation command references different paths and output directories than the included script; test the script in an isolated environment to confirm where files will be written and adjust the SKILL.md or script accordingly. - Inspect dashscope: verify the dashscope package origin (official docs or PyPI project) before pip installing and prefer creating a disposable virtual environment. - Sensitive-data caution: only provide API keys or credentials in a controlled environment (not shared terminals), and consider using a least-privilege key if possible. If you cannot confirm the author's identity or fix the path/metadata mismatches, run this skill in an isolated VM/container or avoid installing it. If you plan to use it, ask the publisher to correct the declared requirements and file paths so the behavior is transparent.

Category: provider

Model Studio Wan R2V

Validation

mkdir -p output/alicloud-ai-video-wan-r2v
python -m py_compile skills/ai/video/alicloud-ai-video-wan-r2v/scripts/prepare_r2v_request.py && echo "py_compile_ok" > output/alicloud-ai-video-wan-r2v/validate.txt

Pass criteria: command exits 0 and output/alicloud-ai-video-wan-r2v/validate.txt is generated.

Output And Evidence

• Save reference input metadata, request payloads, and task outputs in output/alicloud-ai-video-wan-r2v/.
• Keep at least one polling result snapshot.

Use Wan R2V for reference-to-video generation. This is different from i2v (single image to video).

Critical model names

Use one of these exact model strings:

• wan2.6-r2v-flash
• wan2.6-r2v

Prerequisites

• Install SDK in a virtual environment:

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

• Set DASHSCOPE_API_KEY in your environment, or add dashscope_api_key to ~/.alibabacloud/credentials.

Normalized interface (video.generate_reference)

Request

• prompt (string, required)
• reference_video (string | bytes, required)
• reference_image (string | bytes, optional)
• duration (number, optional)
• fps (number, optional)
• size (string, optional)
• seed (int, optional)

Response

• video_url (string)
• task_id (string, when async)
• request_id (string)

Async handling

• Prefer async submission for production traffic.
• Poll task result with 15-20s intervals.
• Stop polling when SUCCEEDED or terminal failure status is returned.

Local helper script

Prepare a normalized request JSON and validate response schema:

.venv/bin/python skills/ai/video/alicloud-ai-video-wan-r2v/scripts/prepare_r2v_request.py \
  --prompt "Generate a short montage with consistent character style" \
  --reference-video "https://example.com/reference.mp4"

Output location

• Default output: output/alicloud-ai-video-wan-r2v/videos/
• Override base dir with OUTPUT_DIR.

Workflow

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

References

• references/sources.md