Cover Anchor System logo

Cover Anchor System

Community
ponyodong2026
cover-anchor-system

波妞小红书强钩子爆款封面。小红书/公众号封面「信息密度 × 视觉锚点」设计系统。Use when the user wants Xiaohongshu covers, WeChat article covers, social-media title images, cover diagnosis, cover redesign, click-through-rate improvement, visual-anchor planning, cover color/type hierarchy, doodle-outline fresh covers, sunlit scrapbook cutout photo-collage covers, or ChatGPT Image 2 prompts for complete finished covers. Outputs template choice, anchor layout, color and type hierarchy, finished-cover generation prompts, and critique/checklist guidance.

Overview

Publisherponyodong2026
Repositoryponyo-cover-anchor-system
Skill namecover-anchor-system
Stars
217
Forks
30
Bundled files
7
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 7 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ponyodong2026 on GitHub. Read the source before you install it.

Installation

Install the Cover Anchor System AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ponyodong2026/ponyo-cover-anchor-system/tree/main/cover-anchor-system
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ponyodong2026/ponyo-cover-anchor-system.git /tmp/ponyo-cover-anchor-system
mkdir -p .claude/skills
cp -r /tmp/ponyo-cover-anchor-system/cover-anchor-system .claude/skills/cover-anchor-system
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cover Anchor System in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cover Anchor System on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cover Anchor System is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

波妞小红书强钩子爆款封面

核心逻辑

封面要解决的从来不是「好看」,是3秒内让人决定要不要点进来。

决定点击率的只有两个变量:

  • 信息密度:利益点在缩略图里清不清楚
  • 视觉锚点:有没有一个位置让眼睛「停住」

Default Behavior

Unless the user explicitly asks for a text-free background, design a complete finished cover: title text, tag, visual anchor, color blocks, subject, and layout should all be generated in one image prompt.

Do not default to HTML/CSS mockups or background-only assets for social covers.

Do not hard-code the author's watermark, logo, 波妞, PONYO, or any @ handle into generated covers. If the user provides their own account mark, include only that user-provided mark; otherwise generate a clean cover with no watermark. The skill's attribution belongs in the repository/README, not inside default output images.

Operating Flow

  1. Identify the content type, audience, platform, and existing title.
  2. Pick one template from the matrix below.
  3. Read the relevant reference file:
    • New complete cover: references/finished-cover-prompts.md
    • Doodle-outline fresh cover: references/doodle-outline-fresh-style.md
    • Sunlit scrapbook cutout cover: references/sunlit-scrapbook-cutout-style.md
    • Existing cover critique/redesign: references/cover-diagnosis-checklist.md
    • Template measurements/colors: references/template-formulas.md
    • Text-free background assets only: references/image-prompts.md
  4. Output a concise cover plan plus a ready-to-use image prompt.
  5. If the user provided an existing cover, score it and give a replacement prompt.

模板选择矩阵

内容类型推荐模板核心锚点
知识/观点/方法论冲突型人脸 + 标题撞色区
干货/教程/步骤数字型大号数字本身
案例/结果/对比截图型截图内容 + 标注箭头
情感/生活/故事情绪型人脸(天然最强锚点)
品牌/产品/工具冲突型 or 截图型视情况选
旅行/家居/Vlog/Citywalk涂鸦描边小清新真实照片主体 + 白色描边 + 手帐贴纸标题
旅行/穿搭/护肤/居家运动/生活方式阳光胶片拼贴白描边顶部胶片条 + 人物白描边 + 手写刷字标题

模板与风格一览

🔴 冲突型

反直觉标题 × 强对比色 × 人物遮罩 → 适合:知识类、观点类、AI工具介绍

🟡 数字型

大号数字锚点 × 色块分割 × 悬念副标题 → 适合:干货类、教程类、成果展示

🟢 截图型

真实截图遮罩 × 手写感标注 × 低饱和底色 → 适合:案例类、前后对比、工具测评

🔵 情绪型

全出血人物图 × 单行大字 × 撞色条 → 适合:情感类、生活类、vlog封面

🟣 涂鸦描边小清新

真实照片 × 白色描边 × 手帐贴纸标题 → 适合:旅行、家居、日常Vlog、Citywalk、咖啡探店

🟤 阳光胶片拼贴白描边

阳光实拍 × 顶部胶片拼贴 × 人物白描边 × 手写刷字标题 → 适合:旅行 Vlog、穿搭、护肤、居家运动、生活方式教程


输出规范

每次给出封面方案,必须包含:

  1. 模板类型 + 选择理由
  2. 锚点位置 — 精确描述(上1/3 / 中心 / 左下角等)
  3. 配色方案 — 主色 + 撞色 + 底色(附 HEX 色值)
  4. 字重层级 — 主标题 / 副标题 / 角标的视觉权重比
  5. ChatGPT Image 2 生图提示词 — 默认是完整成品封面提示词,包含准确中文文字

When diagnosing an existing cover, additionally include:

  • information density score
  • visual anchor score
  • thumbnail readability score
  • top 3 fixes
  • replacement finished-cover prompt

参考文件

  • references/template-formulas.md — 基础模板参数表(锚点规则、配色阈值、字重比)
  • references/finished-cover-prompts.md — 多种完整成品封面 ChatGPT Image 2 提示词
  • references/doodle-outline-fresh-style.md — 涂鸦描边小清新封面风格包(旅行/家居/Vlog/Citywalk)
  • references/sunlit-scrapbook-cutout-style.md — 阳光胶片拼贴白描边封面风格包(旅行/穿搭/护肤/运动/生活方式)
  • references/cover-diagnosis-checklist.md — 旧封面诊断、打分、改版规则
  • references/image-prompts.md — 旧版 text-free 背景素材提示词,仅在用户明确要后期叠字时使用

平台尺寸规范

平台封面比例推荐尺寸
小红书封面3:41080 × 1440px
小红书正方1:11080 × 1080px
公众号头图3:1900 × 383px
公众号次图1:1500 × 500px

ChatGPT Image 2 / DALL-E 生图时在提示词里明确写比例和中文文字。小红书默认 3:4,公众号头图默认 3:1。

Quality Bar

Every cover must pass these checks:

  • Main headline remains readable when viewed as an 80px-wide thumbnail.
  • The viewer sees one dominant anchor before any secondary detail.
  • The cover headline is shorter than the article title and benefit-led.
  • There are no dense explanatory paragraphs.
  • Chinese text is large, crisp, and not garbled.
  • No fake logos, fake QR codes, or invented revenue/data claims unless the user provides them.
  • No hard-coded 波妞, PONYO, logo, creator signature, or @ handle unless the user explicitly provides their own account mark.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Cover Anchor System AI skill do?

波妞小红书强钩子爆款封面。小红书/公众号封面「信息密度 × 视觉锚点」设计系统。Use when the user wants Xiaohongshu covers, WeChat article covers, social-media title images, cover diagnosis, cover redesign, click-through-rate improvement, visual-anchor planning, cover color/type hierarchy, doodle-outline fresh covers, sunlit scrapbook cutout photo-collage covers, or ChatGPT Image 2 prompts for complete finished covers. Outputs template choice, anchor layout, color and type hierarchy, finished-cover generation prompts, and critique/checklist guidance.

Why use Cover Anchor System on TypingMind?

Because you install it once and use it with any model. Cover Anchor System is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cover Anchor System in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ponyodong2026/ponyo-cover-anchor-system/tree/main/cover-anchor-system. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cover Anchor System?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cover Anchor System?

As many as you like. As long as a model supports skills, you can use Cover Anchor System with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cover Anchor System AI skill free?

It is published on GitHub by ponyodong2026. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇