← Back to Skills Marketplace
82
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install video-screen
Description
Skip the learning curve of professional editing software. Describe what you want — crop the screen recording to 16:9, highlight the cursor clicks, and add a...
Usage Guidance
This skill behaves like a thin client for a hosted service (nemovideo.ai) and will upload any video you give it to that backend for processing. Before installing or invoking it: (1) Do not provide a personal NEMO_TOKEN unless you trust the nemovideo service — a bearer token equals API access to your account; prefer letting the skill obtain an anonymous token if possible. (2) Confirm the privacy/retention policy for uploaded videos and whether returned download URLs are public. (3) Note the minor inconsistencies (claimed config path in the SKILL.md vs registry metadata) and the instruction to auto-detect platform from install path — ask the publisher to clarify whether the skill will inspect local paths or files. (4) Because this is instruction-only, there is no code to audit; only proceed if you trust the external domain (https://mega-api-prod.nemovideo.ai) and are comfortable with remote processing of your media. If you need higher confidence, request the publisher to reconcile the metadata and to document exactly what local files/paths (if any) the agent will read.
Capability Analysis
Type: OpenClaw Skill
Name: video-screen
Version: 1.0.0
The video-screen skill is a legitimate integration for a cloud-based video editing service hosted at mega-api-prod.nemovideo.ai. It provides instructions for an AI agent to manage authentication, upload video files, and poll for rendering status. The skill uses standard API patterns (REST and SSE) and does not exhibit signs of data exfiltration, malicious execution, or unauthorized access to sensitive local files.
Capability Assessment
Purpose & Capability
Name/description align with the runtime actions: the SKILL.md instructs the agent to upload videos and call a nemovideo backend. Requesting a single NEMO_TOKEN credential is proportionate for a hosted video-editing service. However, the skill frontmatter metadata names a config path (~/.config/nemovideo/) while the registry summary said no required config paths — this discrepancy is unresolved.
Instruction Scope
The SKILL.md gives detailed, stepwise instructions to: use NEMO_TOKEN (or obtain an anonymous token via POST), create sessions, upload files, stream SSE responses, poll render status, and return download URLs. Those actions are consistent with the described service. Concerns: it instructs the agent to 'auto-detect' X-Skill-Platform from the install path (implies inspecting install/agent paths) and requires strict attribution headers matching frontmatter values — both could lead the agent to inspect local environment/paths or otherwise leak metadata. The doc also instructs hiding technical details from the user, which is fine operationally but worth noting.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest install risk. There is no remote code download or package install to review.
Credentials
Only one credential is declared (NEMO_TOKEN), which is appropriate for a hosted video-editing API. The SKILL.md will fallback to requesting an anonymous token from the nemovideo API if no token is present. Important: any real account NEMO_TOKEN you supply would grant the skill full bearer access to that account's API operations, so supplying a personal token has real privilege implications.
Persistence & Privilege
always:false and normal autonomous invocation are used (expected). The skill references a config path in its frontmatter and requests platform auto-detection from install paths — this implies potential local filesystem inspection for metadata, which is disproportionate for a pure runtime instruction set unless used solely to set a header. It does not request to modify other skills or system-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install video-screen - After installation, invoke the skill by name or use
/video-screen - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of video-screen skill for screen recording editing:
- Edit and export screen recordings by describing desired changes—no complex software required.
- Supports uploading MP4, MOV, AVI, and WebM files up to 500MB.
- Automatically crops, highlights cursor clicks, and adds voiceovers in seconds.
- Handles all editing and rendering via secure cloud GPU; nothing to install locally.
- Includes workflows for quick edits, batch processing, and iterative refinements.
- Built-in token/session management and support for credits, export, and state updates.
Metadata
Frequently Asked Questions
What is Video Screen?
Skip the learning curve of professional editing software. Describe what you want — crop the screen recording to 16:9, highlight the cursor clicks, and add a... It is an AI Agent Skill for Claude Code / OpenClaw, with 82 downloads so far.
How do I install Video Screen?
Run "/install video-screen" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Video Screen free?
Yes, Video Screen is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Video Screen support?
Video Screen is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Video Screen?
It is built and maintained by mory128 (@mory128); the current version is v1.0.0.
More Skills