← 返回 Skills 市场
140
总下载
0
收藏
0
当前安装
5
版本数
在 OpenClaw 中安装
/install tibetan-cinematic-video
功能描述
Generates authentic Tibetan cinematic videos (9:16) via Google Veo from user image + exactly 3 Chinese theme words. STRICT output: ~/.openclaw/workspace/tibe...
安全使用建议
This skill is internally consistent for its stated task, but before installing: (1) verify your OpenClaw/agent environment includes a trusted google/veo tool integration (so Veo calls are authenticated by the platform and not by this skill), and confirm how credentials/endpoints are managed; (2) confirm the platform will not copy or retain input images or outputs outside ~/.openclaw/workspace/tibetanProc/ if you require stricter storage controls; (3) if you have privacy or compliance concerns about sending images to an external video API, do not enable the skill until you confirm where data is sent and how it's stored/retained; (4) note the skill enforces cultural guardrails—review outputs for accuracy and sensitivity. If the platform cannot demonstrate trusted Veo integration, treat the missing credential declaration as a blocker.
功能分析
Type: OpenClaw Skill
Name: tibetan-cinematic-video
Version: 1.1.0
The skill bundle is designed to generate Tibetan-themed cinematic videos using the Google Veo API. It contains well-defined instructions for the AI agent, including strict directory enforcement to ensure all output files are saved exclusively within a specific subdirectory (~/.openclaw/workspace/tibetanProc/). There are no indicators of malicious intent, data exfiltration, or unauthorized command execution in SKILL.md or _meta.json.
能力评估
Purpose & Capability
Name/description (Tibetan cinematic video via Google Veo) matches the SKILL.md: it specifies building prompts, sending the input image and prompt to Veo, and saving the generated clip. No unrelated capabilities or unrelated env vars/binaries are requested.
Instruction Scope
Runtime instructions are narrowly scoped: require an image and exactly three Chinese words, build a Veo prompt, call Veo, poll, download the resulting clip, and save to the declared directory. The skill does not instruct reading other files or arbitrary environment variables. It enforces a strict output path and rejects creation outside the tibetanProc subdir.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is written to disk at install time. Low install risk.
Credentials
No environment variables or credentials are declared, which is coherent if the platform provides a google/veo tool integration that already handles auth. The SKILL.md references Veo and an 'internal Veo endpoint' — confirm how Veo credentials/endpoints are supplied by the platform and that no hidden credential requests will be made at runtime.
Persistence & Privilege
The skill is not always-enabled and is user-invocable. It does not request persistent system-wide changes or access to other skills' configurations. It only writes output under its dedicated tibetanProc directory per its own file-spec.
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 tibetan-cinematic-video - 安装完成后，直接呼叫该 Skill 的名称或使用
/tibetan-cinematic-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
v1.1.0
- Switched backend from Leonardo.ai to Google Veo for video generation.
- Updated prompt guidance and structure to be compatible with Google Veo (veo-3.1-generate-preview).
- Clarified API parameters and outlined expected single-clip (8 seconds) output per call.
- Adjusted language to reflect new platform (tools, platform, and prompt style).
- Expanded cultural and style guardrails to reinforce Tibetan authenticity and avoid anime/western fantasy depictions.
v1.0.5
- Enforced strict directory management: now all files must be created only in ~/.openclaw/workspace/tibetanProc/, never in the parent directory.
- Added global rule and explicit error messaging for any path violations outside tibetanProc/ subfolder.
- Clarified file creation flow: ensures tibetanProc/ subdir exists and aborts if output is elsewhere.
- Updated documentation to reflect directory constraints and enhanced error handling for invalid paths.
v1.0.3
Version 1.0.3
- Clarified and streamlined input requirements: image mandatory, exactly 3 Chinese theme words required in a strict "word1,word2,word3" format.
- Expanded and formalized error handling for missing images, word count, or incorrect input format.
- Made file output specification stricter: 10-digit UTC timestamped filename and explicit output directory.
- Refined cultural guardrails to avoid fantasy, anime, or non-authentic Tibetan elements.
- Updated and tightened prompt format and execution flow for improved consistency.
- Enhanced documentation for user guidance and output validation.
v1.0.1
**Integration with Leonardo.ai video generation and clarified workflow**
- Added Leonardo.ai as the primary video generation model and specified output path/filename convention.
- Defined stricter input requirements (user must provide image and exactly 3 Chinese words).
- New required elements section: always include specific camera motions, atmosphere, and aspect ratio in every prompt.
- Updated workflow for prompt assembly based on the image’s dominant subject and mapped themes.
- Introduced a reusable prompt template and clarified output process for automated video file generation.
- Reinforced guardrails to ensure cultural authenticity and prevent stereotypes.
v1.0.0
- Initial release of "tibetan-cinematic-video" skill.
- Transforms a user-provided image and 3-word theme into a Tibetan-style cinematic video prompt for short vertical clips.
- Produces a prompt structured as 3 sequential video clips, each based on one of the user’s theme words.
- Ensures cultural authenticity, keeps user image essence, and applies cinematic motions and lighting.
- Outputs a single prompt designed for easy video generation (9:16 vertical, soft cinematic lighting, ethereal mood).
元数据
常见问题
tibetan-cinematic-video 是什么？
Generates authentic Tibetan cinematic videos (9:16) via Google Veo from user image + exactly 3 Chinese theme words. STRICT output: ~/.openclaw/workspace/tibe... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 140 次。
如何安装 tibetan-cinematic-video？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install tibetan-cinematic-video」即可一键安装，无需额外配置。
tibetan-cinematic-video 是免费的吗？
是的，tibetan-cinematic-video 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
tibetan-cinematic-video 支持哪些平台？
tibetan-cinematic-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 tibetan-cinematic-video？
由 Jeff Yang（@j3ffyang）开发并维护，当前版本 v1.1.0。
推荐 Skills