← 返回 Skills 市场
Tomoviee Tail to Video
作者
wondershare-boop
· GitHub ↗
· v1.0.3
· MIT-0
317
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install tomoviee-tail-to-video
功能描述
Generate videos from first and last frame images using Tomoviee First-Last Frame API (`tm_tail2video_b`) via Wondershare OpenAPI gateway (`https://openapi.wo...
安全使用建议
This package is internally consistent with its stated purpose: it builds Basic auth from app_key/app_secret and posts to openapi.wondershare.cc to create and poll tasks. Before installing or using it, consider: 1) supply credentials only for a verified Tomoviee/Wondershare account and avoid pasting production keys into third-party or unknown code until you confirm the provider and owner; the registry metadata omits declared credential requirements even though the SKILL.md/code require app_key/app_secret. 2) The optional callback parameter can forward results to any URL you provide — do not use untrusted callback endpoints if your inputs (images, prompts) are sensitive. 3) The skill owner and homepage are unknown; verify the vendor docs (links provided in SKILL.md) and test with limited or expendable credentials first. 4) The code does not persist secrets to disk, but you should still avoid committing keys to source control. If you want stronger assurance, ask the publisher to update registry metadata to declare required credentials and provide a verified homepage or publisher identity.
功能分析
Type: OpenClaw Skill
Name: tomoviee-tail-to-video
Version: 1.0.3
The skill bundle provides a legitimate integration for the Tomoviee AI service to generate videos from first and last frame images. The Python client in `scripts/tomoviee_firstlast2video_client.py` and the authentication helper in `scripts/generate_auth_token.py` correctly implement the documented API workflow using the Wondershare gateway (openapi.wondershare.cc) without any evidence of malicious intent, data exfiltration, or unauthorized execution.
能力评估
Purpose & Capability
The skill's name and description match the included client code and SKILL.md: it implements tm_tail2video_b via the Wondershare gateway. One minor inconsistency: the registry metadata lists no required env vars/credentials, but the SKILL.md and code clearly require an app_key and app_secret (passed to the client). This is a documentation/metadata mismatch rather than a functional mismatch.
Instruction Scope
SKILL.md and the code only instruct creating tasks, polling for results, and returning the video URL. The code does not read unrelated files or environment variables, does not write secrets to disk, and only contacts the documented endpoints on openapi.wondershare.cc. The optional callback parameter can cause the provider to contact an external URL (expected for callback usage).
Install Mechanism
This is instruction-plus-source (no automated install spec). The only runtime dependency is requests (requirements.txt). No remote downloads, no archive extraction, and nothing is written to disk by the skill beyond normal runtime state.
Credentials
The functionality legitimately requires an app_key and app_secret (used to form a Basic auth header). However, the skill metadata in the registry did not declare required env vars or a primary credential; SKILL.md expects credentials passed to the client. Also note the optional 'callback' parameter — if set to a user-controlled external URL, the provider may send results there (expected behavior but a potential data-forwarding vector).
Persistence & Privilege
always is false; the skill does not request persistent system privileges or modify other skills or global agent settings. It does not enable itself or store auth tokens to disk.
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 tomoviee-tail-to-video - 安装完成后，直接呼叫该 Skill 的名称或使用
/tomoviee-tail-to-video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
v1.0.3
- Skill renamed from "tomoviee-firstlast2video" to "tomoviee-tail-to-video".
- Description updated to clarify credential requirements and usage scope.
- Added "Scope" and "Required Inputs" sections to make limitations and required parameters clear.
- Dependency information made explicit (only supports requests 2.x).
- Emphasized the skill covers only the "first-last frame to video" endpoint and does not support other video generation features.
v1.0.2
- Added requirements.txt and _meta.json for packaging and dependency management.
- Updated documentation for credential handling, endpoint provenance, and provider details.
- Clarified API usage, parameters, and image constraints in the README.
- Improved async workflow and resource references for clarity.
v1.0.1
- Updated external resource links from tomoviee.cn to tomoviee.ai for the Developer Portal and API Documentation.
- No functional or feature changes.
v1.0.0
Initial release of tomoviee-firstlast2video
- Generate 5-second videos from two images (first and last frame) with AI-interpolated motion.
- Supports 720p/1080p output and various aspect ratios (16:9, 9:16, 4:3, 3:4, 1:1, original).
- Includes 46 cinematic camera movement options and physics-based motion simulation.
- Accepts detailed text prompts to control subject, motion, and background.
- Python client and async API workflow provided for easy integration.
元数据
常见问题
Tomoviee Tail to Video 是什么？
Generate videos from first and last frame images using Tomoviee First-Last Frame API (`tm_tail2video_b`) via Wondershare OpenAPI gateway (`https://openapi.wo... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 317 次。
如何安装 Tomoviee Tail to Video？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install tomoviee-tail-to-video」即可一键安装，无需额外配置。
Tomoviee Tail to Video 是免费的吗？
是的，Tomoviee Tail to Video 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Tomoviee Tail to Video 支持哪些平台？
Tomoviee Tail to Video 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Tomoviee Tail to Video？
由 wondershare-boop（@wondershare-boop）开发并维护，当前版本 v1.0.3。
推荐 Skills