← Back to Skills Marketplace
Sora Ai Video Maker
by
susan4731-wilfordf
· GitHub ↗
· v1.0.0
· MIT-0
97
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install sora-ai-video-maker
Description
content creators generate text prompts into AI generated videos using this skill. Accepts MP4, MOV, WebM, GIF up to 500MB, renders on cloud GPUs at 1080p, an...
Usage Guidance
This skill appears to do what it says, but before installing: (1) understand that your uploaded media will be sent to https://mega-api-prod.nemovideo.ai for processing — ensure you are comfortable with that external upload and any privacy/billing implications; (2) the skill will use or create a NEMO_TOKEN (it can auto-generate an anonymous token valid 7 days) and may cache session/token data in a local config path (~/.config/nemovideo/) — confirm whether you want tokens stored locally; (3) registry metadata and the SKILL.md disagree about config path requirements — ask the publisher which local paths will be used and for what purpose; (4) if you prefer, provide your own NEMO_TOKEN rather than allowing the skill to auto-generate one; (5) no installers or other credentials are requested, which reduces risk, but always review the provider domain and privacy policy before uploading sensitive content.
Capability Analysis
Type: OpenClaw Skill
Name: sora-ai-video-maker
Version: 1.0.0
The skill provides instructions for an AI agent to interface with a video generation service hosted at `mega-api-prod.nemovideo.ai`. It includes logic for automated session management, anonymous token generation, and mapping user prompts to specific API endpoints. While it instructs the agent to perform environment checks (e.g., verifying installation paths like `~/.cursor/skills/` for platform attribution), these actions are aligned with the stated purpose of the tool and do not exhibit signs of malicious intent, data exfiltration, or unauthorized execution.
Capability Assessment
Purpose & Capability
Name/description, declared credential (NEMO_TOKEN), and the SKILL.md API endpoints all align with a cloud video render service. The skill requires only a service token and performs uploads, SSE, and render requests consistent with the stated goal.
Instruction Scope
Instructions tell the agent to (a) obtain or use NEMO_TOKEN, (b) create sessions, (c) upload user media, (d) stream/poll SSE endpoints and return download URLs. These are appropriate for the stated function. The skill also instructs the agent to read the skill's frontmatter and detect install path to populate attribution headers; that requires reading skill metadata / runtime install path (reasonable but broader than purely 'generate video'). No instructions request unrelated files, system secrets, or arbitrary local data.
Install Mechanism
There is no install spec and no code files — this is an instruction-only skill. That is the lowest-risk install profile (nothing is written to disk by an installer).
Credentials
Only one credential (NEMO_TOKEN) is required and is the primaryEnv; this is proportionate for a cloud API. The skill can also request/generate an anonymous token itself via the provider's anonymous-token endpoint (so it can operate without a pre-set token). One minor inconsistency: the SKILL.md frontmatter includes a configPaths entry (~/.config/nemovideo/) while the registry metadata shown earlier listed no required config paths — the skill may expect to read/write a local config directory for token/session caching, which is plausible but worth verifying.
Persistence & Privilege
always:false and normal model invocation are used (no forced global inclusion). The skill instructs storing session_id and may cache tokens/sessions locally (consistent with services that resume jobs), but it does not request elevated or cross-skill persistence beyond its own config area.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install sora-ai-video-maker - After installation, invoke the skill by name or use
/sora-ai-video-maker - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Sora AI Video Maker skill initial release:
- Generate high-quality 1080p MP4 videos from text prompts via cloud GPU rendering.
- Supports uploading media files (mp4, mov, webm, gif, jpg, png, mp3, etc.) up to 500MB per file.
- Anonymous users receive free credits for AI video generation after simple token registration.
- Provides workflows for uploading, editing, previewing, exporting, and checking credits/status.
- Designed for concise, prompt-driven AI video creation; typical render time 1–3 minutes per clip.
- Robust error handling and guided interactions help users handle authentication, credits, and export issues smoothly.
Metadata
Frequently Asked Questions
What is Sora Ai Video Maker?
content creators generate text prompts into AI generated videos using this skill. Accepts MP4, MOV, WebM, GIF up to 500MB, renders on cloud GPUs at 1080p, an... It is an AI Agent Skill for Claude Code / OpenClaw, with 97 downloads so far.
How do I install Sora Ai Video Maker?
Run "/install sora-ai-video-maker" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Sora Ai Video Maker free?
Yes, Sora Ai Video Maker is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Sora Ai Video Maker support?
Sora Ai Video Maker is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Sora Ai Video Maker?
It is built and maintained by susan4731-wilfordf (@susan4731-wilfordf); the current version is v1.0.0.
More Skills