explainer

Generate narrated explainer videos with AI visuals via the ListenHub CLI.

335|37|Updated Jul 18, 2026
One-click install
npx skills add https://github.com/joeseesun/qiaomu-cut-skill --skill explainer-joeseesun
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: explainer
Source: https://github.com/joeseesun/qiaomu-cut-skill/tree/main/vendor/marswaveai-skills/explainer
Command: npx skills add https://github.com/joeseesun/qiaomu-cut-skill --skill explainer-joeseesun

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Creating an explainer video normally requires writing a script, recording narration, sourcing visuals, and editing everything together. This Skill turns a single topic into a narrated explainer video with AI-generated visuals through the ListenHub CLI, handling authentication, speaker selection, and artifact saving. ## Core Features & Use Cases - Guided parameter collection: Walks the user through topic, language (zh/en/ja), style (Info or Story), speaker, and output type with confirmation before any generation runs. - Text-only or full video output: Generate just a narration script, or a complete video with AI-generated visuals, selectable aspect ratio, and image resolution. - Persistent config and artifact management: Saves defaults in a local config file and downloads scripts and audio into topic-named folders in the working directory. - Use Case: Ask for an explainer introducing a product; the Skill collects your preferences, submits the job to ListenHub, and returns the video URL, audio URL, and credit usage. ## Quick Start Ask the agent to create an explainer video introducing your chosen topic, then answer the prompts for language, style, and output type.

Frequently Asked Questions about explainer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an explainer video with AI-generated visuals?▼

Provide a topic and answer the guided prompts for language, style, speaker, and output type. The Skill runs the ListenHub CLI storybook or explainer command in the background and returns the video URL, audio URL, and credit usage when generation completes.

How to generate only a narration script without video?▼

Choose the text script only output option during the interaction flow. The Skill adds the skip-audio flag to the CLI command, and the script is presented inline or saved as a markdown file in the current working directory.

What languages and styles does AI explainer video generation support?▼

Supported languages are Chinese (zh), English (en), and Japanese (ja). Styles are Info for factual, structured presentations and Story for narrative, storytelling content; slides mode is not supported by this Skill.

Can I change the narrator voice for an explainer video?▼

Yes. The Skill uses a saved default speaker per language from the config file, but you can ask to change the voice and it will fetch the available speaker list from the ListenHub speakers CLI. Speaker IDs are never hardcoded.

Why does explainer video generation fail with an authentication error?▼

The ListenHub CLI must be installed and logged in before generation. The Skill checks auth first and auto-installs or auto-logs in; it also detects whether to use the OpenAPI route (listenhub openapi storybook) or the OAuth route (listenhub explainer).

How long does AI explainer video generation take?▼

Text-only script generation takes about 2-3 minutes, while full text plus video output takes about 5-10 minutes. The CLI command runs in the background with a 600-second generation timeout.