← 返回 Skills 市场
Text To Video Benchmark
作者
whitejohnk-26
· GitHub ↗
· v1.0.0
· MIT-0
64
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install text-to-video-benchmark
功能描述
Get benchmark video clips ready to post, without touching a single slider. Upload your text prompts (TXT, DOCX, CSV, JSON, up to 500MB), say something like "...
安全使用建议
This skill appears to do what it claims (upload prompts/files to a nemo backend and return generated videos), but review the following before installing: 1) If you don't want the agent to contact an external service on your behalf, do not allow the skill to fetch an anonymous token — provide your own NEMO_TOKEN or avoid installing. 2) Uploaded files (up to 500MB) and prompts will be sent to mega-api-prod.nemovideo.ai; avoid uploading sensitive content unless you accept their handling/retention. 3) Ask the publisher to explain the configPaths discrepancy (~/.config/nemovideo/ is present in SKILL.md but absent in the registry metadata) and whether the skill will read or write that directory. 4) If you need stronger guarantees, request a privacy/data-retention statement and verify the API hostname is the official service you expect. If you want me to, I can draft questions to ask the publisher or highlight the exact lines in SKILL.md that cause these concerns.
功能分析
Type: OpenClaw Skill
Name: text-to-video-benchmark
Version: 1.0.0
The skill provides a functional interface for a text-to-video generation service hosted at mega-api-prod.nemovideo.ai. It correctly manages authentication via the NEMO_TOKEN environment variable or an anonymous token acquisition flow and uses standard REST and SSE patterns for media processing. The instructions in SKILL.md are well-aligned with the stated purpose of benchmarking AI video models and include security-conscious directives to avoid exposing tokens to the user.
能力评估
Purpose & Capability
Name and description match the runtime instructions: the skill uploads prompts/files and calls a nemo backend to render video. The declared primary credential (NEMO_TOKEN) is appropriate. However, SKILL.md frontmatter lists a configPath (~/.config/nemovideo/) while the registry metadata above reports no required config paths — an inconsistency worth clarifying.
Instruction Scope
Instructions explicitly send user files (up to 500MB) and prompt text to https://mega-api-prod.nemovideo.ai and describe obtaining a token via an anonymous auth endpoint if NEMO_TOKEN is not present. That behavior is coherent with the stated purpose, but it means user data will be transmitted to a third-party service; the doc does not surface a privacy/retention policy or warn about sensitive content. The skill also asks callers to add attribution headers and to auto-detect install path/platform, which implies some filesystem/environment probing.
Install Mechanism
No install spec or code files are provided (instruction-only). There is no binary install, URL download, or archive extraction — minimal install risk.
Credentials
Only NEMO_TOKEN is declared as required, which is proportionate to a cloud-rendering integration. But the SKILL.md instructs that if the env var is absent the agent should call an anonymous-token endpoint and treat the returned value as NEMO_TOKEN — this means the skill will create/consume credentials on the user's behalf. Also the frontmatter's configPaths (~/ .config/nemovideo/) suggest the skill may read/write a local config; that was not listed in the registry summary and should be clarified.
Persistence & Privilege
always:false and normal autonomous invocation are set. The skill does not request permanent system-wide privileges or modification of other skills. Potentially it maintains session_id state for job management, which is expected for this service.
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 text-to-video-benchmark - 安装完成后，直接呼叫该 Skill 的名称或使用
/text-to-video-benchmark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 Text to Video Benchmark.
- Generate AI videos from text prompts, with upload support for TXT, DOCX, CSV, and JSON (up to 500MB).
- Automatic cloud setup: handles NEMO_TOKEN authentication and cloud session creation.
- Supports 1080p MP4 exports and batch processing of multiple prompts.
- Credits balance, session state, and export functions accessible via simple commands.
- Accurate error messages for token, credits, file size/type, and session issues.
- Timeline viewer for previewing video, audio, and text tracks.
元数据
常见问题
Text To Video Benchmark 是什么？
Get benchmark video clips ready to post, without touching a single slider. Upload your text prompts (TXT, DOCX, CSV, JSON, up to 500MB), say something like "... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 64 次。
如何安装 Text To Video Benchmark？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install text-to-video-benchmark」即可一键安装，无需额外配置。
Text To Video Benchmark 是免费的吗？
是的，Text To Video Benchmark 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Text To Video Benchmark 支持哪些平台？
Text To Video Benchmark 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 Text To Video Benchmark？
由 whitejohnk-26（@whitejohnk-26）开发并维护，当前版本 v1.0.0。
推荐 Skills