← 返回 Skills 市场
vynbosserman65

Video Editor Ai Nano Banana

作者 vynbosserman65 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
67
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-editor-ai-nano-banana
功能描述
Turn a 30-second raw clip filmed on a smartphone into 1080p edited video clips just by typing what you need. Whether it's making fast lightweight edits to sh...
安全使用建议
This skill appears to implement a cloud video-editing workflow, but before installing or providing credentials consider: (1) The skill will upload your video files to https://mega-api-prod.nemovideo.ai — don't send sensitive or private videos unless you trust the service and its privacy policy. (2) It asks for NEMO_TOKEN; treat that token like a password: use a least-privilege or ephemeral token if possible and avoid giving a long-lived account token. (3) The SKILL.md instructs the agent to read local config/install paths (e.g., ~/.config/nemovideo/, ~/.clawhub/, ~/.cursor/skills/) — confirm whether you are comfortable with the skill accessing those locations, and ask the publisher why that is needed. (4) Registry metadata and the SKILL.md frontmatter disagree about config path requirements — request clarification from the publisher or maintainer, verify the domain (nemovideo.ai) is legitimate, and consider running the skill in a sandboxed account or environment first. (5) If you need stronger assurance, ask the publisher for a homepage, privacy policy, or source code so you can audit what data is sent and where. If you can't verify those, treat the skill with caution.
能力评估
Purpose & Capability
The declared purpose (cloud video editing) is consistent with the single required credential (NEMO_TOKEN) and with the API endpoints in SKILL.md. However, the SKILL.md frontmatter requests reading a config path (~/.config/nemovideo/) and install-path detection for header attribution; the registry metadata at the top explicitly listed no config paths. This mismatch is an incoherence: either the skill needs to read local config files (reasonable if it tries to locate stored tokens) or the registry metadata is inaccurate.
Instruction Scope
Runtime instructions tell the agent to (a) read NEMO_TOKEN from the environment or generate an anonymous token via POST to an external API, (b) create sessions, (c) upload user files via multipart form (files=@/path) or by URL, and (d) read this SKILL.md frontmatter and detect install paths (~/.clawhub/, ~/.cursor/skills/) to set X-Skill-Platform. Uploading user-specified video files is expected, but detecting install paths and reading local config directories is broader than strictly necessary for editing and could expose local metadata or other skill-related tokens. The instructions also implicitly allow the agent to access arbitrary local paths when the user supplies files — that is expected for a video upload tool but increases risk of accidental exfiltration if the agent is given a path that contains sensitive files.
Install Mechanism
No install spec and no code files — the skill is instruction-only. This reduces risk from downloaded code or opaque installers.
Credentials
Only one credential is declared (NEMO_TOKEN), which is proportionate for a cloud editing service. But SKILL.md also mentions reading config paths (~/.config/nemovideo/) and scanning install paths to form headers; those filesystem accesses are not declared in the registry 'Required config paths' field (which lists none). That inconsistency should be clarified because it expands what the skill may read from the user's environment.
Persistence & Privilege
The skill is not always-on and is user-invocable; autonomous invocation is allowed (the platform default) but there are no flags requesting permanent presence or modifications to other skills. No elevated persistence privileges were requested.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install video-editor-ai-nano-banana
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /video-editor-ai-nano-banana 触发
  4. 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
Video Editor AI Nano Banana 1.0.0 — Fast AI editing for short clips - Instantly edit and export 30-second smartphone video clips to 1080p by describing your desired changes—no timeline, no export settings. - Easy onboarding: automatically connects to backend, acquires or uses existing API tokens, and guides you in simple language. - Supports fast lightweight edits (trim, silence removal, text overlays, BGM) with AI-driven cloud rendering in 20–40 seconds. - Flexible file uploads (raw clips, URLs); exports in multiple formats including mp4, mov, avi, and more. - Clear workflows for credits, session state, export, and error handling—no technical details exposed to the user. - Designed for speed, simplicity, and minimal user effort; optimized for quick social content and batch processing.
元数据
Slug video-editor-ai-nano-banana
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Video Editor Ai Nano Banana 是什么?

Turn a 30-second raw clip filmed on a smartphone into 1080p edited video clips just by typing what you need. Whether it's making fast lightweight edits to sh... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 67 次。

如何安装 Video Editor Ai Nano Banana?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-editor-ai-nano-banana」即可一键安装,无需额外配置。

Video Editor Ai Nano Banana 是免费的吗?

是的,Video Editor Ai Nano Banana 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Video Editor Ai Nano Banana 支持哪些平台?

Video Editor Ai Nano Banana 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 Editor Ai Nano Banana?

由 vynbosserman65(@vynbosserman65)开发并维护,当前版本 v1.0.0。

💬 留言讨论