← 返回 Skills 市场
Text To Video Long
作者
francemichaell-15
· GitHub ↗
· v1.0.0
· MIT-0
70
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install text-to-video-long
功能描述
Get long-form videos ready to post, without touching a single slider. Upload your text script (TXT, DOCX, PDF, MD, up to 500MB), say something like "turn thi...
安全使用建议
Things to consider before installing:
- The skill will call external endpoints at mega-api-prod.nemovideo.ai and needs a bearer token (NEMO_TOKEN). If you don't provide one, it will request an anonymous token for you — decide whether you trust that domain to handle your uploads and metadata.
- The SKILL.md asks the agent to read the skill file's YAML frontmatter and probe common install paths to set attribution headers; ask the developer to confirm exactly what local paths/files will be read and why. If you prefer, run the skill in an isolated/sandboxed environment.
- There is a minor metadata inconsistency: the SKILL.md mentions a config path (~/.config/nemovideo/) while the registry metadata did not list required config paths. Request clarification from the publisher about whether the skill will access that directory.
- If you plan to provide a persistent NEMO_TOKEN tied to an account, be aware the skill will include it in every request; confirm how tokens and session_ids are stored and for how long.
- If you want greater assurance, ask the maintainer for a privacy/security statement (what files/uploads are retained, where are files stored, data retention, who can access rendered outputs) and for a signed domain or official homepage. Without those, treat the skill as functional but exercise caution with sensitive content.
Additional data that would increase confidence: explicit confirmation of config-path usage, a homepage/source repo, and clarity on where tokens/session IDs are stored and how long the vendor retains uploaded media.
功能分析
Type: OpenClaw Skill
Name: text-to-video-long
Version: 1.0.0
The skill 'text-to-video-long' is a legitimate integration for a video generation service hosted at nemovideo.ai. The SKILL.md file provides detailed, task-aligned instructions for the AI agent to manage API authentication, session handling, and video rendering workflows. It includes standard error handling and telemetry (platform detection via install path) without any evidence of data exfiltration, unauthorized access, or malicious code execution.
能力评估
Purpose & Capability
Name/description (text→long-form video) aligns with endpoints and actions in SKILL.md: upload script, create session, submit render jobs, poll export status. Requesting a service token (NEMO_TOKEN) is appropriate for a cloud-rendering integration.
Instruction Scope
Instructions tell the agent to call external API endpoints, upload user files, stream SSE responses, and include attribution headers derived from local install paths/YAML frontmatter. Reading the skill file's frontmatter and probing common install paths (~/.clawhub/, ~/.cursor/skills/) is outside pure video-processing logic and increases local-file access scope; this is plausible for attribution but should be explicit. The SKILL.md also instructs automatic anonymous-token creation if NEMO_TOKEN is not present, which contradicts the manifest's 'required env var' implication.
Install Mechanism
This is an instruction-only skill with no install spec and no code files — low install-risk. All runtime actions are network calls; nothing is written to disk by an installer.
Credentials
Only one credential (NEMO_TOKEN) is declared, which is reasonable. However, the SKILL.md will autonomously POST to an external auth endpoint to obtain an anonymous NEMO_TOKEN if none is set — meaning the 'required' env var is effectively optional. The SKILL.md also references a config path (~/.config/nemovideo/) in its frontmatter, but the registry metadata reported earlier did not list required config paths; this mismatch should be clarified.
Persistence & Privilege
The skill is not always-enabled and is user-invocable. It asks to store session_id and use tokens for subsequent requests, which is expected for session-based cloud APIs. It does not request system-wide privileges or to modify other skills' configs.
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-long - 安装完成后，直接呼叫该 Skill 的名称或使用
/text-to-video-long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 the text-to-video-long skill.
- Generate long-form 1080p videos from text scripts (TXT, DOCX, PDF, MD, up to 500MB) with narration, visuals, and audio tracks.
- Supports instant file uploads, easy prompt-based instructions, and automated cloud rendering on GPUs.
- Automatic authentication and session management, with 100 free credits on first-time use.
- Clear export, status, and credits checking options; robust error handling included.
- Designed for fast, camera-free video production for YouTubers, educators, and marketers.
元数据
常见问题
Text To Video Long 是什么？
Get long-form videos ready to post, without touching a single slider. Upload your text script (TXT, DOCX, PDF, MD, up to 500MB), say something like "turn thi... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 70 次。
如何安装 Text To Video Long？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install text-to-video-long」即可一键安装，无需额外配置。
Text To Video Long 是免费的吗？
是的，Text To Video Long 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Text To Video Long 支持哪些平台？
Text To Video Long 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 Long？
由 francemichaell-15（@francemichaell-15）开发并维护，当前版本 v1.0.0。
推荐 Skills