← 返回 Skills 市场
Rtk Compressor Online
作者
vynbosserman65
· GitHub ↗
· v1.0.0
· MIT-0
106
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install rtk-compressor-online
功能描述
Turn a 500MB MP4 recording from a dashcam or drone into 1080p compressed MP4 files just by typing what you need. Whether it's reducing large RTK or drone vid...
安全使用建议
This skill appears to do what it says (upload a video to nemovideo.ai, request a render, and return a download link), but review these points before installing or using it:
- Privacy: uploaded videos are sent to mega-api-prod.nemovideo.ai. Only upload content you are comfortable sharing with that service.
- Token behavior: the skill expects a NEMO_TOKEN; if none is present it will call the anonymous-token endpoint to obtain a token for you. That implies the backend will receive an agent-scoped token (100 free credits / 7-day expiry). If you prefer control, provide your own token instead of relying on auto-generation.
- Filesystem checks: the runtime instructions say to detect install paths (~/.clawhub, ~/.cursor) and reference a config directory (~/.config/nemovideo/). If you are concerned about revealing which tools or config exist on your machine, avoid giving the agent access to your home directory or run in an isolated environment.
- Inconsistency: registry metadata and the SKILL.md frontmatter disagree about required config paths. That could be an oversight, but you may want to ask the publisher to clarify.
If you proceed, only share files you control, consider supplying your own NEMO_TOKEN, and use an isolated environment (or limit the agent's filesystem access) if you have privacy concerns.
功能分析
Type: OpenClaw Skill
Name: rtk-compressor-online
Version: 1.0.0
The skill is a functional integration for the NemoVideo AI cloud service, designed to compress and edit video files. It manages authentication via the NEMO_TOKEN environment variable or an automated anonymous token generation process through mega-api-prod.nemovideo.ai. The instructions in SKILL.md guide the agent to handle file uploads, session state, and video rendering tasks as described. While it includes minor telemetry (detecting the installation platform) and sends user prompts to a remote backend for processing, these behaviors are transparently documented and aligned with the tool's stated purpose.
能力评估
Purpose & Capability
Name/description align with a cloud video-compression service and the skill only asks for a single service credential (NEMO_TOKEN) used to call nemovideo.ai endpoints — that is proportionate. However, the SKILL.md frontmatter declares a config path (~/.config/nemovideo/) while the registry metadata listed no required config paths, which is an inconsistency.
Instruction Scope
Instructions direct the agent to upload local video files (multipart file POSTs), create sessions, stream SSEs, poll renders, and include attribution headers. Uploading files is expected for this purpose, but the skill also instructs the agent to detect install paths (~/.clawhub/, ~/.cursor/skills/) and to read this file's YAML frontmatter at runtime — actions that touch user filesystem metadata and could reveal presence of other tools. The skill will also generate an anonymous token by POSTing to the backend if NEMO_TOKEN is absent; this automatically grants the backend a token tied to the agent. These behaviors are plausible for the stated purpose but increase privacy/telemetry surface and should be understood.
Install Mechanism
Instruction-only skill with no install spec and no code files — low risk from install artifacts. Nothing is downloaded or written by an installer step.
Credentials
Only NEMO_TOKEN is requested as a primary credential, which is appropriate for a hosted compression service. But the SKILL.md also describes creating and using an anonymous token when NEMO_TOKEN is missing (calling an external endpoint to obtain a token), and the frontmatter mentions a config path not declared elsewhere — these are mismatches the user should be aware of. No unrelated credentials are requested.
Persistence & Privilege
always:false and no install steps — the skill does not request permanent presence or system-level changes. It does ask the agent to remember session_id during a run, which is normal for session-based APIs.
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 rtk-compressor-online - 安装完成后，直接呼叫该 Skill 的名称或使用
/rtk-compressor-online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
RTK Compressor Online 1.0.0 — Initial Release
- Launches a cloud-based AI video compression tool for MP4, MOV, AVI, and MKV dashcam/drone recordings (up to 500MB).
- Simple workflow: upload video, describe compression or export needs, and receive 1080p MP4 in 30-90 seconds.
- Automated token management and session setup with free trial (100 credits, 7 days).
- Supports user instructions for compression, export, track edits, and text/audio overlays via natural language or file upload.
- Clear error handling and actionable feedback for upload size, file type, credits, and session state.
- Includes multilingual keyword-based command routing, session/timeline tracking, and periodic progress reporting.
元数据
常见问题
Rtk Compressor Online 是什么？
Turn a 500MB MP4 recording from a dashcam or drone into 1080p compressed MP4 files just by typing what you need. Whether it's reducing large RTK or drone vid... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 106 次。
如何安装 Rtk Compressor Online？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install rtk-compressor-online」即可一键安装，无需额外配置。
Rtk Compressor Online 是免费的吗？
是的，Rtk Compressor Online 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Rtk Compressor Online 支持哪些平台？
Rtk Compressor Online 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 Rtk Compressor Online？
由 vynbosserman65（@vynbosserman65）开发并维护，当前版本 v1.0.0。
推荐 Skills