← Back to Skills Marketplace
Youtube Photo Video
by
peandrover adam
· GitHub ↗
· v1.0.0
· MIT-0
133
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install youtube-photo-video
Description
Skip the learning curve of professional editing software. Describe what you want — turn these photos into a YouTube slideshow video with transitions and musi...
Usage Guidance
This skill uploads your images and session data to a third-party service (nemovideo.ai). Before installing or using it: 1) Decide whether you are comfortable sending photos (especially sensitive ones) to an external renderer. 2) Note the inconsistency: the registry declares NEMO_TOKEN as required, but the skill can obtain an anonymous token itself — set an environment token only if you trust the service. 3) Ask the publisher for source code or a privacy policy / terms of service for mega-api-prod.nemovideo.ai and confirm data retention and access controls. 4) If you must use it, avoid uploading private or sensitive images and consider creating a throwaway account or using the anonymous flow rather than supplying long-lived credentials.
Capability Analysis
Type: OpenClaw Skill
Name: youtube-photo-video
Version: 1.0.0
The skill is a legitimate integration for the 'nemovideo.ai' cloud service, designed to convert images into videos. It handles authentication via environment variables or anonymous token generation, manages file uploads, and processes video rendering through documented API endpoints. While it performs environment checks (e.g., searching for config paths like ~/.config/nemovideo/ and detecting the installation platform), these actions are consistent with its stated purpose of session management and attribution, with no evidence of data exfiltration or malicious intent.
Capability Assessment
Purpose & Capability
The skill's stated purpose (turn photos into YouTube-ready videos) aligns with the runtime actions (uploading images, starting render jobs, polling for results). Requiring a NEMO_TOKEN is reasonable for a cloud service, but the SKILL.md provides an anonymous-token flow if NEMO_TOKEN is missing, so declaring NEMO_TOKEN as a required primary credential is inconsistent with the instructions.
Instruction Scope
Instructions explicitly direct the agent to upload user files and send them to a third-party API (https://mega-api-prod.nemovideo.ai). They also instruct generating a UUID, requesting anonymous tokens, creating sessions, uploading files (multipart or URLs), using SSE for interactive edits, and polling render endpoints. These actions are within the advertised purpose, but the SKILL.md also describes deriving X-Skill-Platform from the agent's install path and references a config path (~/.config/nemovideo/), which implies the agent may inspect local file paths and home-directory locations — this expands scope beyond pure upload/render and may read local environment/install location.
Install Mechanism
Instruction-only skill with no install spec or code to write to disk. This is low-risk from install mechanism perspective.
Credentials
Registry metadata lists NEMO_TOKEN as a required primary credential, but SKILL.md provides a fallback anonymous-token acquisition flow (POST to /api/auth/anonymous-token) and thus NEMO_TOKEN may not actually be strictly required. The SKILL.md frontmatter also references a config path (~/.config/nemovideo/) even though the registry summary lists no required config paths — a mismatch. Aside from NEMO_TOKEN, no unrelated credentials are requested. The real risk is that user images and generated session tokens will be sent to the external service; sensitive content could be exposed.
Persistence & Privilege
The skill is not marked always:true and does not request persistent installation or to modify other skills. It does create and use session IDs for render jobs, but that is limited to its own workflow. Autonomous invocation is allowed (default) but not combined with other high-risk factors here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install youtube-photo-video - After installation, invoke the skill by name or use
/youtube-photo-video - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of YouTube Photo Video skill.
- Instantly turns your uploaded photos into YouTube-ready slideshow videos with music and transitions—no editing software needed.
- Supports JPG, PNG, WEBP, HEIC files up to 200MB; export as 1080p MP4 in 30–60 seconds.
- Automatic setup: handles token generation and secure connection for cloud video processing.
- Easily check credits, upload files, edit, preview timeline, and export via simple chat commands.
- Clear error handling for unsupported files, token/session issues, and export limits.
Metadata
Frequently Asked Questions
What is Youtube Photo Video?
Skip the learning curve of professional editing software. Describe what you want — turn these photos into a YouTube slideshow video with transitions and musi... It is an AI Agent Skill for Claude Code / OpenClaw, with 133 downloads so far.
How do I install Youtube Photo Video?
Run "/install youtube-photo-video" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Youtube Photo Video free?
Yes, Youtube Photo Video is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Youtube Photo Video support?
Youtube Photo Video is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Youtube Photo Video?
It is built and maintained by peandrover adam (@peand-rover); the current version is v1.0.0.
More Skills