← Back to Skills Marketplace
54
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install video-writer
Description
Turn a 2-minute raw product demo recording into 1080p scripted video content just by typing what you need. Whether it's generating written scripts and narrat...
Usage Guidance
This skill appears to do what it says: it sends user video clips and requests rendering/script generation from a Nemovideo cloud API and needs a NEMO_TOKEN to authenticate. Before installing/using it: (1) Confirm you trust mega-api-prod.nemovideo.ai — your video files and any metadata you send will be uploaded to that external service. (2) If you don't already have a NEMO_TOKEN, the skill will generate an anonymous token (100 credits, 7-day expiry) by posting a UUID to the service — be aware this creates a server-side account tied to that identifier. (3) Ask the publisher to clarify the configPaths discrepancy in the SKILL.md frontmatter (~/.config/nemovideo/) vs the registry listing (none). (4) Do not use this skill with sensitive or private footage unless you have verified the provider's privacy/retention policy. If you want higher assurance, request a published homepage/privacy policy or vendor identity before providing tokens or private media.
Capability Analysis
Type: OpenClaw Skill
Name: video-writer
Version: 1.0.0
The 'video-writer' skill is a legitimate integration for a cloud-based video processing service (nemovideo.ai). It provides instructions for the AI agent to manage authentication, session state, and video rendering workflows. While it performs environment fingerprinting (checking install paths like ~/.cursor/skills/ for attribution) and handles API tokens, these actions are directly aligned with its stated purpose of providing a video editing interface. There is no evidence of data exfiltration, unauthorized command execution, or malicious prompt injection; in fact, it explicitly instructs the agent not to print sensitive tokens or raw JSON to the user.
Capability Assessment
Purpose & Capability
The skill is described as a cloud video/script generation tool and only requests a single service token (NEMO_TOKEN) and access to a Nemovideo config path in its frontmatter — both are coherent with calling a remote API that performs rendering and script generation. No unrelated credentials or binaries are requested.
Instruction Scope
The SKILL.md directs the agent to obtain/use NEMO_TOKEN, create sessions, upload user video files (multipart uploads or by URL), stream SSE messages, and poll for render results at mega-api-prod.nemovideo.ai. This is expected for the described functionality, but it means user-supplied media and metadata will be sent to an external service; the instructions also tell the agent to generate a UUID for anonymous auth and to include attribution headers on every request. There are no instructions to read or exfiltrate unrelated local files or other environment variables.
Install Mechanism
No install spec or code is present (instruction-only). Nothing will be downloaded or written to disk by an installer step. This is lower risk and matches the listed metadata.
Credentials
The skill requires only NEMO_TOKEN as the primary credential, which is proportional to a remote API client. However, the YAML frontmatter in SKILL.md includes a configPaths requirement (~/.config/nemovideo/), while the registry metadata at the top of the evaluation listed 'Required config paths: none' — this mismatch is inconsistent and should be clarified. The skill also instructs detecting the agent install path to set an X-Skill-Platform header, which requires reading path information (minor scope).
Persistence & Privilege
always:false and user-invocable:true. The skill does not request persistent platform privileges or to modify other skills' configurations. It is an instruction-only skill that relies on runtime API calls.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install video-writer - After installation, invoke the skill by name or use
/video-writer - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of Video Writer: turn raw product demos into 1080p scripted videos in under a minute by uploading clips and describing the result you want.
- Automatic session setup and free anonymous access (100-credits, 7-day token); handles token/session management transparently.
- Supports generating scripts, narration, text overlays, and audio tracks from uploaded video or user description.
- Cloud-based rendering (MP4 default, up to 1080p), with export/download ready in 30–90 seconds.
- Streamlined commands: upload, export, check credits, view project state, and batch processing—all via natural language.
- Clear error messages and workflow guidance; supports multiple file formats and iterative editing in session.
Metadata
Frequently Asked Questions
What is Video Writer?
Turn a 2-minute raw product demo recording into 1080p scripted video content just by typing what you need. Whether it's generating written scripts and narrat... It is an AI Agent Skill for Claude Code / OpenClaw, with 54 downloads so far.
How do I install Video Writer?
Run "/install video-writer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Video Writer free?
Yes, Video Writer is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Video Writer support?
Video Writer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Video Writer?
It is built and maintained by tk8544-b (@tk8544-b); the current version is v1.0.0.
More Skills