← 返回 Skills 市场
Trimmer In
作者
mhogan2013-9
· GitHub ↗
· v1.0.0
· MIT-0
58
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install trimmer-in
功能描述
Turn a 3-minute interview recording with long pauses into 1080p trimmed video clips just by typing what you need. Whether it's cutting unwanted sections from...
安全使用建议
This skill uploads your raw video/audio to an external service (mega-api-prod.nemovideo.ai). Before installing or using it: (1) confirm the service owner and read a privacy/security policy — there is no homepage or source link provided; (2) decide whether you trust a third party with your footage (sensitive content should not be uploaded until you verify policies); (3) ask the publisher to explain the configPath discrepancy (~/.config/nemovideo/ present in SKILL.md but not in registry metadata) and why the skill probes install paths; (4) if you require transparency, request the skill's source code or a known release host for the backend. If you proceed, prefer supplying your own NEMO_TOKEN (vs. allowing anonymous-token issuance) and avoid uploading highly sensitive materials until the backend identity and policies are confirmed.
能力评估
Purpose & Capability
The skill claims to send user video to a cloud rendering backend (nemovideo.ai) and the SKILL.md contains the exact endpoints and flows to do that, so required env var NEMO_TOKEN is appropriate. However the SKILL.md frontmatter lists a required config path (~/.config/nemovideo/) while the registry metadata lists no required config paths — this mismatch is unexplained.
Instruction Scope
Instructions are explicit about token acquisition, session creation, SSE streaming, uploads and polls — all consistent with a cloud trimming service. They also instruct reading the skill's YAML frontmatter and detecting the agent install path (e.g., ~/.clawhub/, ~/.cursor/skills/) to create attribution headers. Probing install paths and reading frontmatter are out-of-band filesystem accesses relative to the stated task and should be validated.
Install Mechanism
This is an instruction-only skill with no install spec or code to write to disk, which is the lowest install risk.
Credentials
Requesting a single NEMO_TOKEN is proportionate for a cloud service. The skill also implements an anonymous-token flow (POST to mega-api-prod.nemovideo.ai) if NEMO_TOKEN isn't present; that behavior is reasonable but means the skill can obtain a token itself. The earlier configPath inconsistency is a minor concern.
Persistence & Privilege
The skill does not request always:true, does not modify other skills, and only maintains an ephemeral session token for render jobs. Autonomous invocation is allowed by default (normal) but does increase blast radius if the backend or skill were malicious.
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 trimmer-in - 安装完成后，直接呼叫该 Skill 的名称或使用
/trimmer-in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
trimmer-in v1.0.0
- Initial release offering AI-powered video trimming and export via cloud processing.
- Supports natural language instructions to trim, cut, or edit uploaded video files—no timeline dragging required.
- Fast processing (20–40 seconds for short clips); outputs 1080p MP4 by default.
- Integrated session-based workflow with automatic authentication and credits management.
- Handles a wide range of common video/audio/image formats; up to 500MB per file.
- User-friendly error handling and feedback throughout the upload, edit, and export process.
元数据
常见问题
Trimmer In 是什么？
Turn a 3-minute interview recording with long pauses into 1080p trimmed video clips just by typing what you need. Whether it's cutting unwanted sections from... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 58 次。
如何安装 Trimmer In？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install trimmer-in」即可一键安装，无需额外配置。
Trimmer In 是免费的吗？
是的，Trimmer In 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Trimmer In 支持哪些平台？
Trimmer In 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 Trimmer In？
由 mhogan2013-9（@mhogan2013-9）开发并维护，当前版本 v1.0.0。
推荐 Skills