← Back to Skills Marketplace
Video Cut
by
dsewell-583h0
· GitHub ↗
· v1.0.0
· MIT-0
69
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install video-cut
Description
Turn a 10-minute unedited interview recording into 1080p trimmed video clips just by typing what you need. Whether it's trimming and splitting long videos in...
Usage Guidance
This skill appears to be a frontend for a cloud video-rendering API and will upload your raw video files to https://mega-api-prod.nemovideo.ai. Before installing or invoking it: 1) Confirm you trust the remote service (no homepage or source code is provided here). 2) Be aware the skill will read NEMO_TOKEN from the environment (or obtain an anonymous token if none exists) and may inspect paths in your home directory to set an attribution header or read config (~/.config/nemovideo/). If you don't want any local filesystem reads, do not provide the skill with elevated file access. 3) Ask the publisher for a source or homepage and what data is retained or logged by the backend (retention, who can access uploaded videos). 4) If you must proceed, run it in an environment where exposing NEMO_TOKEN and uploading sensitive footage is acceptable (e.g., test account or isolated VM).
Capability Analysis
Type: OpenClaw Skill
Name: video-cut
Version: 1.0.0
The video-cut skill is a functional integration for an AI video editing service hosted at nemovideo.ai. It provides detailed instructions for the agent to manage sessions, upload media, and poll for render status via a remote API. While it includes logic to detect the host platform (e.g., checking for ~/.cursor/skills/) for attribution headers and automates anonymous token acquisition, these behaviors are consistent with the stated purpose of providing a cloud-based video processing service and do not show evidence of malicious intent or unauthorized data exfiltration.
Capability Assessment
Purpose & Capability
The name/description (remote video trimming and exports) aligns with the declared primary credential (NEMO_TOKEN) and the SKILL.md which calls a remote rendering API. Requiring a token to call the service is proportionate. However, the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while registry metadata shows no required config paths — that mismatch is unexplained.
Instruction Scope
Instructions tell the agent to: read NEMO_TOKEN from env (expected); if missing, generate a UUID and obtain an anonymous token by POSTing to the service (expected fallback); create sessions, upload user video files (multipart or via URL), stream SSE, poll render status, and return remote download URLs. These are appropriate for a cloud render service, but the skill also instructs deriving an attribution header (X-Skill-Platform) by inspecting install paths (e.g., ~/.clawhub/ or ~/.cursor/skills/) which implies filesystem inspection beyond just reading the declared env var. The SKILL.md also references a config directory in its metadata. Those filesystem-access expectations are not declared in the registry and broaden the scope of what the agent may read from the host.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing will be written to disk by an installer. This is the lowest-risk install mechanism.
Credentials
Only NEMO_TOKEN is declared as required and is the primary credential; that is coherent with a remote video API. The SKILL.md does not request additional unrelated secrets. It will, however, attempt to fetch an anonymous token if NEMO_TOKEN is absent (by contacting the service), which is reasonable but means the agent will still talk to the remote backend even without explicit credentials.
Persistence & Privilege
always is false and the skill does not request special persistent privileges or modify other skills. The only small privilege-like behavior is that it wants to detect install path and optionally read a config dir (~/.config/nemovideo/) per its frontmatter — this implies read access to parts of the user home directory but not system-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install video-cut - After installation, invoke the skill by name or use
/video-cut - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of video-cut — fast, AI-powered video trimming and splitting.
- Upload raw video footage and describe edits in plain language to quickly generate trimmed, export-ready clips.
- No manual timeline editing — cloud GPU processing handles everything server-side within 30–90 seconds.
- Supports quick exports to multiple formats (MP4, MOV, AVI, WEBM, and more), with no install required.
- Built-in onboarding: automatic anonymous token and session creation, with clear connection and status feedback.
- User prompts are matched to upload, edit, credits, export, and session status actions via keyword detection.
- Handles errors gracefully, guides users on limits (500MB/file), and offers tips for fastest results.
Metadata
Frequently Asked Questions
What is Video Cut?
Turn a 10-minute unedited interview recording into 1080p trimmed video clips just by typing what you need. Whether it's trimming and splitting long videos in... It is an AI Agent Skill for Claude Code / OpenClaw, with 69 downloads so far.
How do I install Video Cut?
Run "/install video-cut" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Video Cut free?
Yes, Video Cut is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Video Cut support?
Video Cut is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Video Cut?
It is built and maintained by dsewell-583h0 (@dsewell-583h0); the current version is v1.0.0.
More Skills