creator

Generates platform-ready content packages combining articles, images, and narration audio.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Turning a topic, URL, or raw material into publish-ready content for WeChat, Xiaohongshu, or narration scripts normally requires juggling writing, image generation, TTS, and formatting across multiple tools. This Skill orchestrates that entire multi-step pipeline into one guided workflow with quality review. ## Core Features & Use Cases - Multi-Platform Templates: Produces WeChat long-form articles with illustrations, Xiaohongshu image cards plus long text, and spoken narration scripts with optional TTS audio. - Writing Engine with Quality Review: Applies forbidden-word scanning, style consistency checks, prototype-specific review, and an L1-L4 self-review loop to keep output human-sounding. - Style Learning and Presets: Extracts style directives from reference articles, persists user style preferences, and offers visual presets (flat, watercolor, cute, bold, etc.) for generated images. - Use Case: Paste a URL and say "turn this into a Xiaohongshu post" — the Skill extracts the content, confirms a template and visual preset, writes the copy, generates card images via the listenhub CLI, and saves a complete output folder with meta.json. ## Quick Start Ask the assistant to create a WeChat article, Xiaohongshu post, or narration script from your topic, text, or URL, then confirm the proposed template and preset when prompted.

Frequently Asked Questions about creator

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

FAQPage Schema
How do I generate a Xiaohongshu post with AI image cards?▼

Provide a topic, text, or URL and specify Xiaohongshu as the platform. The Skill asks you to pick a visual preset, writes the card copy and long text, then generates 3:4 card images sequentially via the listenhub image create command into an output folder.

How do I turn a URL into a WeChat article?▼

Paste the article URL and request a WeChat article. The Skill calls the content-parser API with your LISTENHUB_API_KEY to extract the content, writes the article following style rules, generates illustrations, and saves everything with a meta.json file.

What authentication is required for content generation?▼

Image generation and TTS require listenhub CLI authentication via listenhub auth login. URL content extraction requires the LISTENHUB_API_KEY environment variable. Pure text-only pipelines like narration scripts without audio need no authentication.

Can I teach the writing style from a reference article?▼

Yes. Provide a reference article with keywords like "参考" or "style" and the Skill extracts 3-5 style directives for your confirmation. You can apply them once or persist them to a per-platform style file for future generations.

What are the limitations of the TTS narration audio?▼

TTS input is limited to roughly 10,000 characters, which comfortably covers typical narration scripts of 300-2000 characters. If TTS generation fails, the Skill still delivers the script and notes the failure in the output summary.