← 返回 Skills 市场
71
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install text-to-video-json
功能描述
Skip the learning curve of professional editing software. Describe what you want — convert this text into a 30-second video with visuals and voiceover — and...
安全使用建议
This skill appears to implement a cloud text→video workflow and only asks for a single service token (NEMO_TOKEN), which is reasonable — but take these precautions before installing:
- Verify the backend domain (mega-api-prod.nemovideo.ai) and the service's reputation before sending any sensitive content. Uploaded files are sent to that external service.
- Understand token handling: the skill will accept a user-provided NEMO_TOKEN or create an anonymous token by calling the API itself. Either token/session may be persisted (SKILL.md frontmatter references ~/.config/nemovideo/). Ask where tokens/session_ids are stored and how to revoke/delete them.
- Avoid uploading sensitive or private files unless you trust the service and its privacy policy. The instructions explicitly allow multipart uploads from local paths; ensure the agent only uploads files you intentionally provide.
- If you must test, prefer ephemeral or least-privilege tokens and delete any stored session/token after use.
- Clarify the metadata inconsistency: registry metadata lists no config paths while the SKILL.md frontmatter references a config directory. Ask the publisher to confirm exactly what (if anything) will be written to disk.
If you cannot confirm these points or don't trust the external service, do not install or use the skill with sensitive data.
功能分析
Type: OpenClaw Skill
Name: text-to-video-json
Version: 1.0.0
The skill bundle provides instructions for an AI agent to interface with the nemovideo.ai API for text-to-video conversion. It includes standard workflows for authentication (anonymous token generation via UUID), session management, file uploads, and video rendering. While it requests platform attribution headers and environment variable access (NEMO_TOKEN), these actions are consistent with the stated functionality of a cloud-based media processing service. The instructions in SKILL.md are focused on API orchestration and user experience, with no evidence of data exfiltration, malicious execution, or harmful prompt injection.
能力评估
Purpose & Capability
Name/description map to a cloud text→video service and the single required credential (NEMO_TOKEN) is appropriate for that purpose. However, the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) while registry metadata lists no required config paths — an internal inconsistency. The skill also elects to auto-provision an anonymous token if NEMO_TOKEN is absent, which is explainable for usability but differs from a model that requires only user-supplied credentials.
Instruction Scope
Runtime instructions direct the agent to: contact an external API to create an anonymous token, store a session_id for subsequent requests, and upload files (multipart form with file paths or URL-based uploads). Uploading user-specified files is expected, but the instructions allow sending file paths (e.g., '-F "files=@/path"'), which — if misused — could exfiltrate arbitrary local files. The guidance to 'Don't display raw API responses or token values' indicates secrets are handled, but where/how session/token are persisted is unspecified. Overall, the instruction set grants the agent discretion to create tokens, persist them, and read local files — all normal for this skill but high-impact if abused.
Install Mechanism
No install steps or code are included (instruction-only), so nothing is written to disk by an installer and there is no package download risk.
Credentials
Only NEMO_TOKEN is declared as required and is relevant to the stated service. The skill's ability to auto-request an anonymous token means it can operate without a pre-provisioned secret. The metadata's mention of a config path suggests the skill may persist tokens or session data on disk (proportional for convenience but a privacy consideration). There are no unrelated credentials requested.
Persistence & Privilege
always:false and autonomous invocation are normal. The SKILL.md instructs storing session_id (and possibly token) for subsequent calls and the frontmatter references ~/.config/nemovideo/, implying it may persist state to disk. That persistence is plausible for a long-running cloud render session, but the registry metadata vs SKILL.md mismatch is ambiguous and should be clarified.
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-json - 安装完成后，直接呼叫该 Skill 的名称或使用
/text-to-video-json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
Text-to-video-json v1.0.0 — Initial Release
- Converts text prompts (plain text, JSON, DOCX, CSV) into 30-second videos with AI visuals and voiceover in 1–2 minutes.
- Supports file uploads up to 500MB and multiple video export formats (MP4, MOV, AVI, etc.).
- Streamlined onboarding with automatic session/token setup and 100 free credits for new users.
- Handles video export, balance checks, status updates, and uploads via natural language prompts.
- Includes robust error handling and clear guidance for credits, unsupported files, and export limitations.
元数据
常见问题
Text To Video Json 是什么？
Skip the learning curve of professional editing software. Describe what you want — convert this text into a 30-second video with visuals and voiceover — and... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 71 次。
如何安装 Text To Video Json？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install text-to-video-json」即可一键安装，无需额外配置。
Text To Video Json 是免费的吗？
是的，Text To Video Json 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Text To Video Json 支持哪些平台？
Text To Video Json 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 Json？
由 tk8544-b（@tk8544-b）开发并维护，当前版本 v1.0.0。
推荐 Skills