← Back to Skills Marketplace
think-x-actually-y-video-gen
by
parallel world
· GitHub ↗
· v1.0.1
· MIT-0
138
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install think-x-actually-y-video-gen
Description
Create vertical three-beat debunks: you think X, actually Y, but Z—timed English captions on three segments (WeryAI). Use for mindset ladders, hot-take templ...
Usage Guidance
This bundle appears to be what it says: a Node script that talks to WeryAI and requires a WERYAI_API_KEY. Before you use it: (1) Prefer supplying public https image URLs to avoid the script reading local files. (2) If you do provide local image paths, review scripts/video_gen.js and explicitly confirm the upload — the script will read that file and POST it (with your WERYAI_API_KEY) to api-growth-agent.weryai.com to create a public URL. (3) Use a limited/short-lived API key or an account with minimal credits for testing to limit exposure from accidental paid submissions. (4) Follow the SKILL.md pre-submit gate: do not allow any automated submits without explicit user confirmation of the full expanded prompt and parameters. (5) If you need higher assurance, run the script in an isolated environment, audit network requests, and revoke/regenerate the key after testing.
Capability Analysis
Type: OpenClaw Skill
Name: think-x-actually-y-video-gen
Version: 1.0.1
The skill bundle provides a tool for generating videos via the WeryAI API, but it includes a script (scripts/video_gen.js) that can read arbitrary local files and upload them to a remote server (api-growth-agent.weryai.com). While this is documented as a feature for handling local images and SKILL.md mandates a 'Pre-submit gate' for user confirmation, the capability to exfiltrate local data via the upload endpoint is a high-risk behavior. No evidence of intentional malice, obfuscation, or unauthorized persistence was found.
Capability Assessment
Purpose & Capability
Name/description ask for video generation via WeryAI; required binary (node) and required env var (WERYAI_API_KEY) are exactly what a Node-based WeryAI client needs. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md keeps runtime scope focused: it requires explicit pre-submit confirmation of full prompts/parameters and prefers public https image URLs. The packaged script supports reading local image files and uploading them to WeryAI (turning local paths into public URLs). SKILL.md documents and gates this behavior (requests review and explicit user consent before local read-and-upload), so scope creep is acknowledged and controlled — but local-file uploads remain the main area where extra data can leave the system if a user supplies a path without understanding the implications.
Install Mechanism
No external install / download step; script is bundled with the skill and there are no arbitrary remote installers or third‑party package pulls. Risk from installation is low.
Credentials
Only WERYAI_API_KEY is required and is appropriate for the described API interactions (generation, model registry, and upload). The SKILL.md explicitly marks it as secret and warns not to commit it.
Persistence & Privilege
Skill does not request permanent/always-on privileges (always:false). It does not attempt to modify other skills or system-wide configuration. Autonomous invocation is allowed by default but not combined with other concerning privileges here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install think-x-actually-y-video-gen - After installation, invoke the skill by name or use
/think-x-actually-y-video-gen - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- No changes detected in this version; documentation and workflow remain the same.
- Version number and functionality are unchanged.
v1.0.0
think-x-actually-y-video-gen 1.0.1 — Improved clarity, user consent workflow, and prompt structure
- Expanded documentation for three-beat video debunk structure and timing (X, Y, Z beats).
- Enforced explicit user confirmation before any paid video generation task begins.
- Detailed pre-submit parameter table and user workflow to ensure clarity and consent for all parameters and prompts.
- Added security, environment, and local image handling guidelines for sensitive API key and file access.
- Provided step-by-step user workflow for submitting, tracking, and retrieving generated videos.
- Updated tags and descriptions for improved discoverability and use case coverage.
Metadata
Frequently Asked Questions
What is think-x-actually-y-video-gen?
Create vertical three-beat debunks: you think X, actually Y, but Z—timed English captions on three segments (WeryAI). Use for mindset ladders, hot-take templ... It is an AI Agent Skill for Claude Code / OpenClaw, with 138 downloads so far.
How do I install think-x-actually-y-video-gen?
Run "/install think-x-actually-y-video-gen" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is think-x-actually-y-video-gen free?
Yes, think-x-actually-y-video-gen is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does think-x-actually-y-video-gen support?
think-x-actually-y-video-gen is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created think-x-actually-y-video-gen?
It is built and maintained by parallel world (@zoucdr); the current version is v1.0.1.
More Skills