Agent skill

Xiaohongshu Cover Generator

by Vivixiao980 in Vivixiao980/xhs-cover-skill

Creates and edits Xiaohongshu (RedNote) cover images from a portrait photo and text, using GPT Image 2 first and a Gemini CLI script as fallback.

No licenceAuto-check passedMedia & Creative

SKILL.md written in Chinese; this summary is our English description.

Install Xiaohongshu Cover Generator

skills CLI
$ npx skills add Vivixiao980/xhs-cover-skill --skill xhs-cover -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Vivixiao980/xhs-cover-skill xhs-cover --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
xhs-cover
GitHub stars
204
Token cost
~2.9k tokens
SKILL.md length
572 words
Files
48 (incl. scripts, assets)
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

Creates and edits Xiaohongshu (RedNote) cover images from a portrait photo and text, using GPT Image 2 first and a Gemini CLI script as fallback.

  • Works in 10 steps: :优先使用 GPT Image 2 → :检查配置(首次使用 Onboarding) → :收集生成参数 → …
  • Making a Xiaohongshu cover from a portrait photo and a headline
  • SKILL.md covers 路径约定, 工作流入口, 执行流程 and 配置管理, plus 2 more sections
  • Calls git and node; reaches xhscover.vivi.wiki and generativelanguage.googleapis.com; needs XHS_COVER_API_KEY

What it does

Written in Chinese, the skill generates or modifies Xiaohongshu covers from a portrait photo, a main title, optional subtitle lines, a chosen style and the default 3:4 ratio. When Codex image generation is available it uses GPT Image 2 by default and falls back to a Gemini command-line script only if that is unavailable or you ask for command-line or API generation. It includes 18 preset styles, and you can learn a custom style from a reference image.

Three flows are supported: generating a new cover, editing the last cover so only the parts you name change while the original style and composition are kept, and learning a style from an uploaded image into a JSON file in a `styles` folder. The Gemini path has a first-run onboarding that stores an API key and base URL in `~/.config/xhs-cover/config.json`, choosing between Google AI Studio and an OpenAI-compatible third-party proxy. The skill installs under a Codex, Claude Code or OpenClaw skills folder.

When your agent uses it

  • Making a Xiaohongshu cover from a portrait photo and a headline
  • Adjusting the layout, text or colors of a cover you already generated
  • Learning a new cover style from a reference image

Example prompts

  • “Generate a Xiaohongshu cover with my photo and the title 'Morning routine for busy people' in the dark-glow style.”
  • “Edit the last cover so the title text is larger but keep everything else.”
  • “Learn the style of this reference image and save it as a custom cover style.”

Requirements

  • GPT Image 2 or Codex image generation, or an API key for the Gemini fallback
  • A portrait photo to use on the cover

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. :优先使用 GPT Image 2
  2. :检查配置(首次使用 Onboarding)
  3. :收集生成参数
  4. :风格选择
  5. :运行生成
  6. :展示结果
  7. :上传与分析
  8. :确认与生成 Prompt
  9. :测试生成
  10. :贡献到社区(可选)

What it can do on your machine

Read from SKILL.md and the folder at commit 25a7279. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • git
    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • xhscover.vivi.wiki
    • generativelanguage.googleapis.com
    • ai.google.dev
    • aistudio.google.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • XHS_COVER_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Xiaohongshu Cover Generator loads about 2.9k tokens when it runs. Until then it costs about 155 tokens; SKILL.md has 572 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~155
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 572 words (~2,916 tokens).

“直接生成或修改小红书封面,优先使用 GPT Image 2 / Codex 图片生成能力。”

— opening of SKILL.md by Vivixiao980
name
xhs-cover

Read the full SKILL.md on GitHub

Files

SKILL.md and 47 other files (scripts, assets) in the repository root of Vivixiao980/xhs-cover-skill.

  • SKILL.md
  • .gitignore
  • README.md
  • assets/screenshot-website.png
  • assets/styles/background-big-text.jpg
  • assets/styles/cozy-home.jpg
  • assets/styles/dark-glow.jpg
  • assets/styles/dashed-decoration.jpg
  • assets/styles/hand-drawn-border.jpg
  • assets/styles/home-motivation.jpg
  • assets/styles/multi-layer-layout.jpg
  • assets/styles/neon-contrast.jpg
  • assets/styles/outdoor-handwriting.jpg
  • assets/styles/pink-yellow-playful.jpg
  • assets/styles/professional-clean.jpg
  • assets/styles/professional-woman.jpg
  • assets/styles/split-screen-tags.jpg
  • assets/styles/sticker-energy.jpg
  • assets/styles/study-room-intellectual.jpg
  • … and 29 more

Open the folder on GitHubat commit 25a7279

Compare with similar skills

Xiaohongshu Cover Generator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Xiaohongshu Cover Generator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Xiaohongshu Cover Generator this skillVivixiao980/xhs-cover-skill204—~2.9kAutomated safety check: PassNone
Cover Anchor Systemponyodong2026/ponyo-cover-anchor-system190—~1.1kAutomated safety check: PassNone
ImageNexus-JPF/note-companion8703 repos~3.9kAutomated safety check: PassMIT
AI Image Generation and Editingzhayujie/CowAgent47k—~1.3kAutomated safety check: PassMIT
SEO Image GeneratorAgriciDaniel/claude-seo19k2 repos~2.1kAutomated safety check: PassMIT
BlockRun Image GenerationBlockRunAI/ClawRouter6.6k—~2.1kAutomated safety check: PassMIT

Similar skills

  • Cover Anchor System

    ponyodong2026/ponyo-cover-anchor-system

    Designs Xiaohongshu and WeChat article covers around information density and a visual anchor, then writes a complete image prompt, color plan and critique.

    190 GitHub stars~1.1k tokensUpdated 3 mo ago
    Media & CreativeAuto-check passed
  • Image

    Nexus-JPF/note-companion

    When the user wants to create, generate, edit, or optimize images for marketing — blog heroes, social graphics, product mockups, profile banners, listing visuals, or brand assets.

    870 GitHub starsUsed in 3 repos~3.9k tokens
    Media & CreativeAuto-check passed
  • Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.

    47k GitHub stars~1.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • SEO Image Generator

    AgriciDaniel/claude-seo

    Generates Open Graph previews, blog hero images, product photos and infographics for SEO use through Gemini image tools and the banana extension.

    19k GitHub starsUsed in 2 repos~2.1k tokens
    Media & CreativeAuto-check passed
  • BlockRun Image Generation

    BlockRunAI/ClawRouter

    Generates or edits images through ClawRouter's local image API, with a choice of models and sizes and payment handled automatically through x402.

    6.6k GitHub stars~2.1k tokensUpdated 5 days ago
    Media & CreativeAuto-check passed
  • Youtube Thumbnail

    hassancs91/claude-youtube-editor

    Dedicated YouTube thumbnail generator — interviews you for exactly the style elements you want (environment, text budget, extras, accent color), then renders high-contrast, vibrant, face-consistent…

    328 GitHub stars~2.1k tokensUpdated 1 mo ago
    Media & CreativeAuto-check: notes

Questions about Xiaohongshu Cover Generator

What does Xiaohongshu Cover Generator do?

Creates and edits Xiaohongshu (RedNote) cover images from a portrait photo and text, using GPT Image 2 first and a Gemini CLI script as fallback. Written in Chinese, the skill generates or modifies Xiaohongshu covers from a portrait photo, a main title, optional subtitle lines, a chosen style and the default 3:4 ratio. When Codex image generation is available it uses GPT Image 2 by default and falls back to a Gemini command-line script only if that is unavailable or you ask for command-line or API generation.

When should I use Xiaohongshu Cover Generator?

Xiaohongshu Cover Generator fits situations like: making a Xiaohongshu cover from a portrait photo and a headline; adjusting the layout, text or colors of a cover you already generated; learning a new cover style from a reference image.

How do I install Xiaohongshu Cover Generator in Claude Code?

Run `npx skills add Vivixiao980/xhs-cover-skill --skill xhs-cover -a claude-code`. Or copy the skill folder (the Vivixiao980/xhs-cover-skill repository) into .claude/skills/xhs-cover in your project. Claude Code loads it when a task matches its description.

How do I install Xiaohongshu Cover Generator in Codex?

Run `npx skills add Vivixiao980/xhs-cover-skill --skill xhs-cover -a codex`. Or copy the skill folder (the Vivixiao980/xhs-cover-skill repository) into .agents/skills/xhs-cover in your project. Codex loads it when a task matches its description.

Can I use Xiaohongshu Cover Generator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Vivixiao980/xhs-cover-skill --skill xhs-cover -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xhs-cover, .gemini/skills/xhs-cover, .github/skills/xhs-cover and .opencode/skills/xhs-cover in your project.

What does Xiaohongshu Cover Generator need to run?

Going by SKILL.md and its folder, Xiaohongshu Cover Generator needs the command-line tools its instructions call (git and node) and credentials named XHS_COVER_API_KEY. Our summary lists: GPT Image 2 or Codex image generation, or an API key for the Gemini fallback; A portrait photo to use on the cover.

Does Xiaohongshu Cover Generator access the network?

SKILL.md names 4 domains. In commands or code: xhscover.vivi.wiki, generativelanguage.googleapis.com, ai.google.dev and aistudio.google.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Xiaohongshu Cover Generator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Xiaohongshu Cover Generator use?

No licence was found for Xiaohongshu Cover Generator or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Xiaohongshu Cover Generator use?

About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Xiaohongshu Cover Generator?

Skills that share tags, products or a category with Xiaohongshu Cover Generator: Cover Anchor System (ponyodong2026/ponyo-cover-anchor-system, 190 stars), Image (Nexus-JPF/note-companion, 870 stars), AI Image Generation and Editing (zhayujie/CowAgent, 47k stars) and SEO Image Generator (AgriciDaniel/claude-seo, 19k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Xiaohongshu Cover Generator?

Vivixiao980 (a GitHub user) maintains it in Vivixiao980/xhs-cover-skill, which has 204 GitHub stars. The repository was last updated on May 26, 2026.

Source: Vivixiao980/xhs-cover-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.