← 返回 Skills 市场

Aliyun Animate Anyone

Name: Aliyun Animate Anyone
Author: cinience

作者 cinience · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

总下载

当前安装

版本数

在 OpenClaw 中安装

/install aliyun-animate-anyone

功能描述

Use when generating dance or motion-transfer videos with Alibaba Cloud Model Studio AnimateAnyone (`animate-anyone-gen2`) using a detected character image an...

使用说明 (SKILL.md)

Category: provider

Model Studio AnimateAnyone

Validation

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

Pass criteria: command exits 0 and output/aliyun-animate-anyone/validate.txt is generated.

Output And Evidence

Save normalized request payloads, detection outputs, template IDs, and task polling snapshots under output/aliyun-animate-anyone/.
Record whether the result should keep the reference image background or the source video background.

Use AnimateAnyone when the task needs motion transfer from a template video rather than plain talking-head animation.

Critical model names

Use these exact model strings:

animate-anyone-detect-gen2
animate-anyone-template-gen2
animate-anyone-gen2

Selection guidance:

Run image detection first.
Run template generation on the source motion video.
Use animate-anyone-gen2 for the final video job.

Prerequisites

China mainland (Beijing) only.
Set DASHSCOPE_API_KEY in your environment, or add dashscope_api_key to ~/.alibabacloud/credentials.
Input files must be public HTTP/HTTPS URLs.

Normalized interface (video.animate_anyone)

Detect Request

model (string, optional): default animate-anyone-detect-gen2
image_url (string, required)

Template Request

model (string, optional): default animate-anyone-template-gen2
video_url (string, required)

Generate Request

model (string, optional): default animate-anyone-gen2
image_url (string, required)
template_id (string, required)
use_ref_img_bg (bool, optional): whether to keep the input image background

Response

task_id (string)
task_status (string)
video_url (string, when finished)

Quick start

python skills/ai/video/aliyun-animate-anyone/scripts/prepare_animate_anyone_request.py \
  --image-url "https://example.com/dancer.png" \
  --template-id "tmpl_xxx" \
  --use-ref-img-bg

Operational guidance

The action template must come from the official template-generation API.
Full-body images work best when use_ref_img_bg=false; half-body images are not recommended in that mode.
This skill is best for dancing or large body motion transfer, not generic talking-head tasks.

Output location

Default output: output/aliyun-animate-anyone/request.json
Override base dir with OUTPUT_DIR.

References

references/sources.md

安全使用建议

This skill appears to be a simple request-preparer for Alibaba Cloud AnimateAnyone, but the SKILL.md expects an API key (DASHSCOPE_API_KEY) or an entry in ~/.alibabacloud/credentials while the manifest lists no required credentials — that's an inconsistency. Before installing or using it: 1) confirm with the skill author why credentials weren't declared and whether the agent will actually call Alibaba APIs (the script alone does not). 2) If you must provide credentials, create a minimal-scope API key limited to only the necessary AnimateAnyone actions and region (Beijing) rather than reusing broad account credentials. 3) Avoid putting sensitive keys into shared global credential files unless you understand the scope; prefer dedicated env vars if possible. 4) Ensure input files truly need to be public URLs (the skill requires that) and that exposing those URLs is acceptable. If the author cannot justify the missing manifest fields, treat the skill as untrusted until fixed.

功能分析

Type: OpenClaw Skill Name: aliyun-animate-anyone Version: 1.0.0 The skill bundle is a legitimate integration for Alibaba Cloud's AnimateAnyone video generation service. The script `scripts/prepare_animate_anyone_request.py` is a simple utility that formats JSON payloads for API requests, and the `SKILL.md` provides standard operational guidance and validation steps aligned with official Alibaba Cloud documentation (referenced in `references/sources.md`). No evidence of data exfiltration, malicious execution, or prompt injection was found.

能力评估

ℹ Purpose & Capability

The name, description, model names, and included helper script all align with an Alibaba Cloud AnimateAnyone integration. However, the SKILL.md lists a required API key (DASHSCOPE_API_KEY) and an Alibaba Cloud credentials file path that are not declared in the skill's top-level requirements, which is an inconsistency between claimed needs and declared requirements.

⚠ Instruction Scope

Runtime instructions ask the agent to set an environment variable or add a key to ~/.alibabacloud/credentials and to use public HTTP/HTTPS input URLs; the included script itself only writes a JSON request and does not perform network calls. The instructions therefore expect access to credentials/config files and to call external Alibaba APIs, but those accesses are not reflected in the declared requirements. The skill's instructions do not explicitly restrict what agent context may be read beyond that credentials path.

✓ Install Mechanism

No install spec is present and the only code writes request JSON locally; there is no download-from-URL or package installation. This is low-risk from an install/execution perspective.

⚠ Credentials

The SKILL.md requires DASHSCOPE_API_KEY or a dashscope_api_key entry in ~/.alibabacloud/credentials, but the skill manifest declares no required environment variables or primary credential. This mismatch is disproportionate to the manifest and should be corrected. Also note that placing keys in ~/.alibabacloud/credentials may grant access to other Alibaba Cloud APIs unless a scoped/minimal key is used.

✓ Persistence & Privilege

The skill does not request always:true, does not modify other skills, and does not install persistent components. It is not requesting elevated or permanent presence.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install aliyun-animate-anyone
安装完成后，直接呼叫该 Skill 的名称或使用 /aliyun-animate-anyone 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release of aliyun-animate-anyone skill: - Enables dance and motion-transfer video generation using Alibaba Cloud Model Studio AnimateAnyone (Gen2). - Supports input normalization for image detection, action template extraction, and final video generation. - Saves outputs including request payloads, detection results, template IDs, and task logs. - Requires public URLs for inputs and is restricted to the China mainland (Beijing) region. - Offers operational guidance for best visual quality based on input type.

元数据

Slug aliyun-animate-anyone

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题