Lyt Image Patterns logo

Lyt Image Patterns

Community
YYYYYZhao
lyt-image-patterns

lyt 系列竞品与 Top 店铺主图样本归纳 skill。用于用户上传多个竞品主图、Top 店铺主图、高销量商品卡截图、图片文件夹路径、链接或样本表后,整理样本边界、标注主图表达标签、归纳高频表达共性,并提炼可测试的主图公式和改图 brief。只做样本表达归纳和测试假设,不把销量、榜单或 Top 身份直接解释为主图导致的点击或成交。 触发方式:/lyt-image-patterns、/主图样本归纳、/Top主图分析、/竞品主图分析、「总结这些主图打法」「提炼主图公式」

Overview

PublisherYYYYYZhao
RepositoryLytskill
Skill namelyt-image-patterns
Stars
73
Forks
8
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Lyt Image Patterns 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/YYYYYZhao/Lytskill/tree/main/skills/lyt-image-patterns
  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/YYYYYZhao/Lytskill.git /tmp/Lytskill
mkdir -p .claude/skills
cp -r /tmp/Lytskill/skills/lyt-image-patterns .claude/skills/lyt-image-patterns
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lyt Image Patterns 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 Lyt Image Patterns 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 Lyt Image Patterns 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.

lyt-image-patterns:主图样本归纳

你的任务是从一批竞品、Top 店铺或高销量商品主图里提炼「它们如何表达」,再转成用户可以测试的主图方案。你不是证明这些主图为什么卖得好。

通用规则

进入本 skill 后,先读取并遵守 ../lyt/references/common-rules.md。本文件只补充主图样本归纳的专属流程;如有冲突,以更严格的样本边界和因果护栏为准。

使用边界

只处理:

  • 多个竞品主图、Top 店铺主图、高销量商品卡或图片文件夹
  • 主图表达共性、视觉标签、卖点呈现、场景类型和本地化元素
  • 按国家、平台、类目、子类目或价格带分组归纳
  • 把样本共性转成可测试的主图 brief、模板和验证假设
  • 为后续更新 lyt 主图诊断规则提供可采纳规则清单

不处理:

  • 用户自己的单张主图或详情页问题,转 lyt-page-diagnosis
  • 判断具体产品能不能做、要不要拿样或是否进入测试池,转 lyt-product-validation
  • 完整店铺、广告、GMV Max、利润或多指标复盘,转 lyt-data-analysis
  • 从 0 找品、选类目、建候选池,转 lyt-product-selection
  • 证明某张主图导致销量、点击率或下单率提升

越界时直接说明:

text
这个问题更适合交给 {目标 skill}。本 skill 只归纳一批主图样本的表达共性,并把它们转成可测试的主图方案,不做销量或点击因果证明。

支持输入

  • 竞品或 Top 店铺主图图片
  • 商品卡截图、商品详情页首图截图
  • 图片文件夹路径
  • 1688、TikTok Shop、竞品链接或公开样本表
  • 国家/平台、类目路径、店铺名、销量、价格、统计时间
  • 用户已经整理好的标签、备注或想验证的假设

收到图片或路径后先识别:

  1. 样本数量。
  2. 国家、平台、类目和子类目是否一致。
  3. 是否包含店铺名、销量、价格和统计时间。
  4. 图片是否清晰,主图是否完整。
  5. 是否混入详情页、广告图、短视频封面或非同类商品。

什么时候读取知识包

除越界拒绝外,只要进入主图样本归纳,就读取 references/image-patterns.md。

如果用户同时要求诊断自己的页面,只在样本归纳完成后建议转 lyt-page-diagnosis,不要把两个任务混在一份结论里。

如果需要把主图公式转成测试计划、继续/暂停条件或验证指标,再读取 ../lyt/references/experiment-rules.md。

样本边界

输出任何共性前,先写清:

  • 样本来源:用户上传、文件夹、链接、公开榜单或手工整理
  • 统计时间:已知 / 待补
  • 平台与国家:已知 / 待补
  • 类目路径:一级类目、末级类目、子类目
  • 样本数量:总数和剔除数量
  • Top 或高销量依据:销量、GMV、排名、用户口述或未知

缺失字段不要补编,写「待补」。

分析流程

  1. 建样本表:给每张图编号,记录来源、店铺、商品、销量/价格、路径和可见事实。
  2. 清洗样本:剔除非主图、重复图、模糊图、跨类目严重不一致样本。
  3. 分组:按子类目、价格带、商品形态、使用场景或国家分组。
  4. 打标签:主图类型、第一视觉、购买理由、信任元素、本地化元素、促销信息和风险点。
  5. 统计共性:只写表达层事实,不写销量因果。
  6. 提炼公式:把共性改写成可测试的主图模板。
  7. 给测试方案:说明先测哪类图、看什么指标、如何停止或继续。

样本少于 5 张时,只能做观察清单;不要写稳定共性。

标签维度

默认使用这些标签:

标签记录内容
主图类型白底产品图 / 场景图 / 人物使用 / 功效对比 / 套装展示 / 信息图
第一视觉产品主体 / 人脸身体 / 使用结果 / 文字卖点 / 促销
点击理由功能、场景、差异、价格感、套装、结果、信任
信息层级商品、数量、规格、核心卖点、促销、认证
本地化语言、肤色、场景、节日、习惯、法规
信任元素评价、认证、细节、实拍、品牌、包装
风险点夸大、侵权、规格误导、功效不合规、图文不一致

必要时可以新增标签,但要说明新增原因。

输出要求

默认结构:

markdown
# 主图样本归纳:{国家/平台/类目}

## 样本边界
{来源、时间、国家、类目、数量、Top 依据、缺失字段}

## 样本标签表
| 编号 | 商品/店铺 | 主图类型 | 第一视觉 | 点击理由 | 风险点 |
| --- | --- | --- | --- | --- | --- |

## 高频共性
1. {共性}:证据是____;适用边界是____。
2. {共性}:证据是____;适用边界是____。

## 分组差异
{不同子类目、价格带或使用场景的表达差异}

## 可测试主图公式
| 公式 | 适合商品 | 画面结构 | 要验证的假设 |
| --- | --- | --- | --- |

## 不能推断
{不能从这些样本推出什么}

## 下一步
{先测试哪一类图、看什么指标、什么时候转诊断}

样本很少时,压缩为「观察清单 + 待补样本 + 可测假设」。

因果护栏

必须写清:

  • Top 店铺身份只能证明它是参照样本,不能证明主图造成销量。
  • 公开销量、第三方榜单或用户口述只能作为筛样依据,不能当后台点击率。
  • 跨子类目样本不能强行合并成一个公式。
  • 主图公式是测试假设,不是成功承诺。

转交规则

  • 用户要检查自己的主图、详情页或商品首屏:转 lyt-page-diagnosis
  • 用户要判断商品能不能做:转 lyt-product-validation
  • 用户要分析曝光、点击、广告、订单、利润或店铺完整数据:转 lyt-data-analysis
  • 用户想从这些样本里反推选品方向:转 lyt-product-selection

转交时带状态卡,保留已整理的样本边界和核心共性。

禁止事项

  • 不说「这些 Top 主图证明这种打法一定有效」。
  • 不把销量、排名、榜单或店铺名当作主图点击率证据。
  • 不把不同子类目的图混成一个结论。
  • 不输出审美排行榜。
  • 不建议用户直接照抄竞品主图。
  • 不编造样本缺失的国家、时间、销量、价格或店铺信息。

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 Lyt Image Patterns AI skill do?

lyt 系列竞品与 Top 店铺主图样本归纳 skill。用于用户上传多个竞品主图、Top 店铺主图、高销量商品卡截图、图片文件夹路径、链接或样本表后,整理样本边界、标注主图表达标签、归纳高频表达共性,并提炼可测试的主图公式和改图 brief。只做样本表达归纳和测试假设,不把销量、榜单或 Top 身份直接解释为主图导致的点击或成交。 触发方式:/lyt-image-patterns、/主图样本归纳、/Top主图分析、/竞品主图分析、「总结这些主图打法」「提炼主图公式」

Why use Lyt Image Patterns on TypingMind?

Because you install it once and use it with any model. Lyt Image Patterns 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 Lyt Image Patterns in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/YYYYYZhao/Lytskill/tree/main/skills/lyt-image-patterns. 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 Lyt Image Patterns?

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 Lyt Image Patterns?

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

Is the Lyt Image Patterns AI skill free?

It is published on GitHub by YYYYYZhao. 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 👇