← 返回 Skills 市场
Video Text Generator
作者
linmillsd7
· GitHub ↗
· v1.0.0
· MIT-0
71
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-text-generator
功能描述
Skip the learning curve of professional editing software. Describe what you want — add on-screen text captions and title cards to my video — and get text-ove...
安全使用建议
This skill acts as a client for a cloud rendering service (mega-api-prod.nemovideo.ai). Before installing: (1) Understand that your video files will be uploaded to that third-party service and rendered there — do not send confidential or restricted videos. (2) The skill will use or obtain a NEMO_TOKEN (it can auto-create an anonymous token if you don't provide one) and will store session state; consider providing your own token if you want control and know how to revoke it. (3) There is a minor metadata mismatch (SKILL.md references ~/.config/nemovideo/ while the registry did not) — ask the publisher where tokens/sessions are stored and how they are protected. (4) If you are comfortable with those network calls and storage behaviors and trust the external service, the skill appears coherent for its stated purpose; otherwise decline or sandbox it and verify where tokens/files are kept.
功能分析
Type: OpenClaw Skill
Name: video-text-generator
Version: 1.0.0
The skill is a functional wrapper for a cloud-based video editing service (nemovideo.ai). It provides instructions for the AI agent to manage authentication, session creation, and file uploads to a specific backend API (mega-api-prod.nemovideo.ai). While it includes automated token generation and environment probing for platform attribution (X-Skill-Platform), these behaviors are consistent with the stated purpose of providing a seamless server-side video rendering experience and do not show evidence of malicious intent or unauthorized data exfiltration.
能力评估
Purpose & Capability
The skill is an instruction-only front-end for a remote video rendering API and only requests a single service token (NEMO_TOKEN), which matches the described purpose. Minor inconsistency: registry metadata listed no required config paths, but the SKILL.md frontmatter lists a config path (~/.config/nemovideo/), which is plausible for storing session/token data but is not declared in the registry entry.
Instruction Scope
SKILL.md instructs the agent to upload user video files, create sessions, post SSE messages, poll renders, and optionally auto-create an anonymous token by POSTing to an external API. These actions are necessary for the described cloud rendering; however, the skill also directs the agent to automatically obtain and persist tokens/session IDs and explicitly instructs not to display raw tokens to users, which is a behavior you should be aware of (it involves network calls and storing credentials/session state).
Install Mechanism
No install spec or code files; instruction-only skill. This is the lowest-risk install mechanism because nothing is written to disk by an installer. Runtime network calls still occur per the instructions.
Credentials
Only one environment variable (NEMO_TOKEN) is required, which is proportional for a remote API. The SKILL.md will create an anonymous token if NEMO_TOKEN is absent — reasonable but means the agent will call an external auth endpoint automatically. Also note the frontmatter references a config path (~/.config/nemovideo/) that could be used to persist tokens/sessions; the registry did not list this path, creating a minor mismatch to verify.
Persistence & Privilege
always:false and no requests to modify other skills or global agent settings. The only persistence behavior described is storing a session_id / token for subsequent requests (expected for this use-case). Autonomous invocation is allowed by default but not elevated here.
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 video-text-generator - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-text-generator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 Video Text Generator skill.
- Instantly add text overlays, captions, and title cards to videos using AI — just upload and describe your edits.
- Supports MP4, MOV, AVI, and WebM files up to 500MB; export videos in 1080p MP4 format.
- Automatic onboarding with easy token generation and session setup; no editing software or manual steps required.
- Cloud-based GPU rendering ensures quick turnarounds (30–60 seconds for short clips).
- Designed for content creators and marketers needing rapid, high-quality video text overlays without complex tools.
元数据
常见问题
Video Text Generator 是什么？
Skip the learning curve of professional editing software. Describe what you want — add on-screen text captions and title cards to my video — and get text-ove... 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 Video Text Generator？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-text-generator」即可一键安装，无需额外配置。
Video Text Generator 是免费的吗？
是的，Video Text Generator 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Text Generator 支持哪些平台？
Video Text Generator 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 Video Text Generator？
由 linmillsd7（@linmillsd7）开发并维护，当前版本 v1.0.0。
推荐 Skills