← Back to Skills Marketplace
64
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install video-caption-maker
Description
add video files into captioned video files with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators use it for adding subtitles to...
Usage Guidance
This skill appears to do what it says: it uploads videos to mega-api-prod.nemovideo.ai, asks for (or generates) a NEMO_TOKEN, and returns rendered captioned videos. Before installing: 1) Confirm you trust the remote service (mega-api-prod.nemovideo.ai) because your videos and metadata will leave your machine. 2) Decide whether you are comfortable providing/storing NEMO_TOKEN and session IDs — ask where the agent will persist them (local config file vs in-memory). 3) Clarify the metadata mismatch: SKILL.md frontmatter lists ~/.config/nemovideo/ but registry metadata showed no required config paths. 4) If you need privacy, do not install or ensure you can revoke tokens and delete persisted session/config files. 5) If you want extra assurance, ask the skill author (or registry owner) for a provenance/source URL and for details about token lifecycle, data retention, and how uploaded videos are handled on the backend.
Capability Analysis
Type: OpenClaw Skill
Name: video-caption-maker
Version: 1.0.0
The video-caption-maker skill is a functional integration for a cloud-based video processing service (nemovideo.ai). It provides clear instructions for the AI agent to handle video uploads, session management, and caption generation via a documented API. The skill includes security-conscious instructions (e.g., not printing raw tokens) and follows standard patterns for third-party service integrations, such as using environment variables for authentication and providing an anonymous trial flow. No evidence of data exfiltration, malicious code execution, or harmful prompt injection was found.
Capability Assessment
Purpose & Capability
The skill's name and description match what the SKILL.md actually instructs: uploading videos to a remote API, generating captions, and returning rendered MP4s. The declared primary credential (NEMO_TOKEN) is used by the API. One inconsistency: the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata above stated no required config paths — this should be clarified (see guidance).
Instruction Scope
The instructions explicitly direct the agent to POST files and messages to https://mega-api-prod.nemovideo.ai, create anonymous tokens if needed, and save session_id and tokens. All of that is in-scope for a cloud captioning service. There are no instructions to read unrelated local system files. Note: the skill will upload user-provided videos (potentially sensitive) to a third-party endpoint — an expected functional need but a privacy risk.
Install Mechanism
Instruction-only skill with no install spec or code files — lowest install risk. No downloads, packages, or binaries are requested.
Credentials
Only one environment variable is required (NEMO_TOKEN), which the SKILL.md uses directly. That is proportionate to the stated purpose. However, the skill will (a) generate anonymous tokens via the external API if no token is present, and (b) expects to persist session/token state — confirm where these are stored on your agent. Also confirm that you are comfortable sending video content and metadata to the external service.
Persistence & Privilege
always:false and model-invocation allowed (default) — normal. The skill instructs the agent to save session_id and token state; review where those credentials are written (in-memory vs. disk) and whether the declared config path (~/.config/nemovideo/) will be used. No indication the skill attempts 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-caption-maker - After installation, invoke the skill by name or use
/video-caption-maker - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of Video Caption Maker.
- Upload MP4, MOV, AVI, or WebM files (up to 500MB) for automatic AI subtitle generation and burned-in captions.
- Supports quick, cloud-based processing (usually 30–60 seconds) to deliver 1080p MP4 files for YouTube and social media.
- Multi-language captions (e.g., English, Spanish) and auto-sync supported.
- Handles common workflows: quick edits, batch processing, and iterative timeline refinements.
- Built-in session, credit, and export management with clear prompts and robust error handling.
- Anonymous users automatically receive temporary free credits for testing.
Metadata
Frequently Asked Questions
What is Video Caption Maker?
add video files into captioned video files with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators use it for adding subtitles to... It is an AI Agent Skill for Claude Code / OpenClaw, with 64 downloads so far.
How do I install Video Caption Maker?
Run "/install video-caption-maker" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Video Caption Maker free?
Yes, Video Caption Maker is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Video Caption Maker support?
Video Caption Maker is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Video Caption Maker?
It is built and maintained by tk8544-b (@tk8544-b); the current version is v1.0.0.
More Skills