← 返回 Skills 市场
51
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install text-to-video-examples
功能描述
Turn a 3-sentence product description into 1080p generated video clips just by typing what you need. Whether it's generating videos from written scripts or p...
安全使用建议
This skill plausibly implements a text→video API and only asks for a single service token, but exercise caution because: (1) the source and homepage are missing — you can't easily verify the provider; (2) the SKILL.md and registry metadata disagree about config paths (registry says none; the skill references ~/.config/nemovideo/), which is unexplained; (3) the runtime instructions allow uploading arbitrary files and instruct probing install paths, which could expose sensitive data if the agent is granted broad filesystem access. Before installing: verify the skill's provenance (official docs or vendor), confirm what NEMO_TOKEN can do and how long it lasts, avoid uploading sensitive files, prefer using an ephemeral or least-privilege token (revoke when done), and ask the skill author to explain the configPath discrepancy and precisely how/where tokens/sessions are stored.
功能分析
Type: OpenClaw Skill
Name: text-to-video-examples
Version: 1.0.0
The skill is a legitimate integration for a text-to-video service hosted at nemovideo.ai. It defines standard API workflows for authentication, session management, file uploads, and video rendering. While it includes logic to detect the host platform (e.g., Cursor or OpenClaw) for attribution headers and manages a NEMO_TOKEN environment variable, these actions are transparently documented in SKILL.md and align with the stated purpose of the tool. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
能力评估
Purpose & Capability
Name/description match the runtime instructions: the SKILL.md describes a remote video-rendering API and the skill requests a single service token (NEMO_TOKEN). However the package has no homepage, unknown source/owner, and the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata claimed no required config paths — this mismatch is unexplained.
Instruction Scope
The instructions direct the agent to call external API endpoints (session creation, SSE streaming, uploads, rendering) and to upload files via multipart (files=@/path). Upload operations necessarily require reading file paths the user supplies; that is expected for a video upload feature, but it also creates an exfiltration vector if the agent is allowed to read arbitrary files. The skill also instructs detecting install paths (~/.clawhub/, ~/.cursor/skills/) and reading this file's YAML frontmatter for attribution headers, which implies filesystem probing beyond the service's API. These behaviors are within a video service's plausible needs, but they increase risk and should be justified/limited.
Install Mechanism
This is an instruction-only skill with no install spec and no code files — nothing will be downloaded or written by an installer. That is lower risk compared to skills that fetch and extract remote archives.
Credentials
Only one env var is declared (NEMO_TOKEN), which is appropriate for a hosted video API. However, the SKILL.md describes generating an anonymous token via an API and treating the returned token as NEMO_TOKEN (100 credits, 7-day expiry), and the frontmatter references a config path (~/.config/nemovideo/) that the registry did not declare. The discrepancy between declared config paths and the SKILL.md metadata is a red flag. Also, because the skill accepts uploads, the token grants the service ability to act on uploaded data — ensure you understand what that token permits and how long it remains valid.
Persistence & Privilege
The skill is not always-included and uses normal autonomous invocation defaults. It will create and use session IDs and tokens for the remote API, which is expected. There is no claim it will modify other skills or system-wide settings. Monitor where it persists the anonymous token/session if it does so.
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-examples - 安装完成后，直接呼叫该 Skill 的名称或使用
/text-to-video-examples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 Examples" skill — quickly convert short product descriptions or text prompts into AI-generated 1080p video clips.
- Simple workflow: upload text, specify video requirements, receive downloadable MP4 in 1–2 minutes.
- Automatic setup connects to the video processing API and handles session management.
- Supports quick edits, batch processing, and iterative refinement; tracks timeline state for smooth user experience.
- Handles user prompts for export, credits, status, and uploads via intent-based routing.
- Comprehensive error handling and helpful feedback for format support, token issues, and export permissions.
元数据
常见问题
Text To Video Examples 是什么？
Turn a 3-sentence product description into 1080p generated video clips just by typing what you need. Whether it's generating videos from written scripts or p... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 51 次。
如何安装 Text To Video Examples？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install text-to-video-examples」即可一键安装，无需额外配置。
Text To Video Examples 是免费的吗？
是的，Text To Video Examples 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Text To Video Examples 支持哪些平台？
Text To Video Examples 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 Examples？
由 tk8544-b（@tk8544-b）开发并维护，当前版本 v1.0.0。
推荐 Skills