Productivity

xiaohongshu-cover-generator

freestylefly/xiaohongshu-skills · updated Apr 8, 2026

$npx skills add https://github.com/freestylefly/xiaohongshu-skills --skill xiaohongshu-cover-generator
summary

Generate Xiaohongshu-style cover images from user topics with automatic formatting.

  • Accepts a topic as input and produces vertically-oriented 3:4 cover images optimized for mobile viewing
  • Requires API key from https://api.canghe.ai/ (via CANGHE_API_KEY environment variable or direct argument)
  • Saves generated images to the current working directory with timestamped filenames ( xiaohongshu-cover-{timestamp}.png )
  • Applies clean, youthful aesthetic with automatic watermark removal and
skill.md

Xiaohongshu Cover Generator

This skill generates Xiaohongshu-style cover images based on user-provided topics.

Usage

When a user requests a Xiaohongshu cover image:

  1. Confirm the topic with the user if not clear
  2. Check for API key (CANGHE_API_KEY environment variable or ask user to provide it)
  3. Run the generation script with the topic
  4. The image will be saved to the current working directory with filename format: xiaohongshu-cover-{timestamp}.png

Running the Script

The script is located at scripts/handler.ts and requires:

  • Topic (required): The subject for the cover image
  • API Key (required): Either via environment variable CANGHE_API_KEY or passed as argument

Execute with:

cd ~/.codebuddy/skills/xiaohongshu-cover-generator
npx tsx scripts/handler.ts "<topic>" "<api-key-optional>"

Or with environment variable:

cd ~/.codebuddy/skills/xiaohongshu-cover-generator
CANGHE_API_KEY="your-api-key" npx tsx scripts/handler.ts "<topic>"

API Key

Users need a valid API key from https://api.canghe.ai/

If the API key is missing or invalid, provide the user with clear instructions to obtain one.

Output

The generated image will be saved to the directory where the skill was invoked (current working directory), not the skill's directory. The filename format is xiaohongshu-cover-{timestamp}.png where timestamp is in milliseconds.

Style Specifications

The generated images follow these specifications:

  • Aspect ratio: 3:4 (vertical, mobile-friendly)
  • Style: Clean, refined, youthful aesthetic
  • Automatic removal of watermarks and logos
  • High-quality output suitable for mobile viewing
  • Text should be clear and readable with appropriate sizing
general reviews

Ratings

4.460 reviews
  • Isabella Verma· Dec 20, 2024

    Solid pick for teams standardizing on skills: xiaohongshu-cover-generator is focused, and the summary matches what you get after install.

  • Shikha Mishra· Dec 12, 2024

    xiaohongshu-cover-generator has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Isabella Khanna· Dec 12, 2024

    Keeps context tight: xiaohongshu-cover-generator is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Yusuf Abebe· Dec 8, 2024

    We added xiaohongshu-cover-generator from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

  • Sofia Brown· Dec 8, 2024

    I recommend xiaohongshu-cover-generator for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Ishan Ramirez· Dec 8, 2024

    Useful defaults in xiaohongshu-cover-generator — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Fatima Menon· Nov 27, 2024

    xiaohongshu-cover-generator fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • Kwame Dixit· Nov 27, 2024

    Registry listing for xiaohongshu-cover-generator matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Yusuf Diallo· Nov 27, 2024

    Solid pick for teams standardizing on skills: xiaohongshu-cover-generator is focused, and the summary matches what you get after install.

  • Noor Wang· Nov 11, 2024

    I recommend xiaohongshu-cover-generator for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

showing 1-10 of 60

1 / 6