← 返回 Skills 市场
Trimmer Js
作者
linmillsd7
· GitHub ↗
· v1.0.0
· MIT-0
99
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install trimmer-js
功能描述
trim video clips into trimmed video clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators use it for cutting and trimming...
安全使用建议
This skill will upload any videos you give it to an external service (mega-api-prod.nemovideo.ai) and will use a NEMO_TOKEN for authorization. The SKILL.md will create an anonymous token for you if one isn't set and may read or write ~/.config/nemovideo/ or check typical install paths to derive a platform header. Before installing or using: (1) confirm the service/domain and owner (there's no homepage and source is unknown); (2) decide whether you are comfortable uploading the specific video content to an external cloud service; (3) ask the publisher where and how tokens are stored (are tokens persisted locally? for how long?); (4) verify privacy/retention and terms for uploaded media; and (5) be cautious about using this with sensitive or private footage. The mismatches between the registry metadata and the SKILL.md (config paths and token-handling behavior) are not definitive proof of maliciousness but are enough to request clarification from the author before trusting the skill.
功能分析
Type: OpenClaw Skill
Name: trimmer-js
Version: 1.0.0
The trimmer-js skill is a well-documented integration for a cloud-based video editing service (nemovideo.ai). It provides the AI agent with specific instructions for managing authentication via anonymous tokens, handling session states, and interacting with a REST API for video processing. The skill's behavior is strictly aligned with its stated purpose of trimming videos, and it includes security-conscious instructions for the agent to avoid exposing tokens or raw API data. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found.
能力评估
Purpose & Capability
The name/description (trim videos via cloud) matches the SKILL.md actions (upload, render, export). Requesting a single service token (NEMO_TOKEN) and calling an external video render API is consistent with the stated purpose. However, the registry metadata reported no required config paths while the SKILL.md frontmatter declares ~/.config/nemovideo/ (incoherence between manifest and runtime instructions).
Instruction Scope
The instructions explicitly tell the agent to POST to https://mega-api-prod.nemovideo.ai, create sessions, upload files (multipart or by URL), stream SSE events, and poll render status. Those operations are expected for a cloud-based trimming service. The instructions also ask the agent to derive headers from the YAML frontmatter and detect install path (~/.clawhub/, ~/.cursor/skills/) which requires inspecting local paths — this is plausible but broader than a purely API-only skill. The SKILL.md also specifies generating an anonymous token if NEMO_TOKEN is absent, which conflicts with declaring NEMO_TOKEN as required (the skill both requires and knows how to obtain the token).
Install Mechanism
No install spec and no code files (instruction-only) — lowest install risk. Nothing is downloaded or written by an installer step in the registry metadata.
Credentials
Only one credential is declared (NEMO_TOKEN), which is appropriate for a single-cloud-backend service. However, SKILL.md instructs the agent to automatically obtain an anonymous token via the API when the env var is missing — that dual behavior (declared required env var but runtime will create one) is inconsistent and worth calling out. The skill's frontmatter also references a config path (~/.config/nemovideo/) that could be used to read or persist credentials; the top-level registry metadata did not list any required config paths, which is a mismatch.
Persistence & Privilege
always:false and no special persistent installation are requested. The skill discusses session tokens and session lifecycle but does not demand always-on or system-wide privileges in the manifest. The potential for the skill to write a token to a config path is implied in the SKILL.md/frontmatter but not explicitly declared as a persistent install action.
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-js - 安装完成后，直接呼叫该 Skill 的名称或使用
/trimmer-js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-js 1.0.0 — Initial Release
- Launches Trimmer JS: trims and exports MP4, MOV, AVI, and WebM video clips up to 500MB.
- Cloud GPU processing with automatic session/token setup; handles everything via chat.
- Supports exporting in high-quality 1080p MP4 by default.
- Provides clear instructions for uploads, exports, checking credits, and session management.
- Includes detailed error handling and automatic retry logic for setup and exports.
- Designed for content creators needing fast, precise cloud video trims with no local install required.
元数据
常见问题
Trimmer Js 是什么？
trim video clips into trimmed video clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators use it for cutting and trimming... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 99 次。
如何安装 Trimmer Js？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install trimmer-js」即可一键安装，无需额外配置。
Trimmer Js 是免费的吗？
是的，Trimmer Js 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Trimmer Js 支持哪些平台？
Trimmer Js 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 Js？
由 linmillsd7（@linmillsd7）开发并维护，当前版本 v1.0.0。
推荐 Skills