TypingMindTypingMindThe best frontend for AI
Wan Cover Plus logo

Wan Cover Plus

Community
wwwzhouhui
wan-cover-plus

使用 Wan2.7-image 生成公众号封面图、小红书封面图、种草图和海报改版视觉稿，并支持文生视频、静态图转丝滑动态视频、参考图 / 参考视频转视频，以及为视频自动补 Edge TTS 配音与字幕烧录。视频任务兼容 Wan 2.6 与 Wan 2.7 模型，可通过 config.yaml 默认配置或输入 JSON 的 model 字段覆盖。用于把标题、副标题、卖点、品牌色、结构化 JSON、参考图或参考视频转成真实图片或视频输出；当用户提到封面图、头图、配图、种草图、视觉稿、海报重排版、横版改竖版、文生视频、图片转视频、静态图转动态视频、参考图转视频、参考视频转视频、丝滑动态视频、视频配音、字幕烧录、Edge TTS 配音时，必须优先考虑这个技能。支持 Prompt 构建、场景选择、真实 Wan API 调用、PNG / MP4 文件输出与 prompt sidecar 保存。

Overview

Publisherwwwzhouhui
Repositoryskills_collection
Skill namewan-cover-plus
Stars
285
Forks
57
Bundled files
23
Links
Skill sourceRepository
  • 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.

  • 23 bundled files

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

  • Open source

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

Installation

Install the Wan Cover Plus 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/wwwzhouhui/skills_collection/tree/main/wan-cover-plus
  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/wwwzhouhui/skills_collection.git /tmp/skills_collection
mkdir -p .claude/skills
cp -r /tmp/skills_collection/wan-cover-plus .claude/skills/wan-cover-plus
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wan Cover Plus 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 Wan Cover Plus 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 Wan Cover Plus 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.

WanCover+

WanCover+ 是一个面向内容视觉生产的 Claude Code Skill。

它适合两类任务：

  • 图片生成：公众号封面图、小红书封面图、种草图、海报重排版
  • 视频生成：文生视频、静态图转丝滑动态视频、参考图 / 参考视频转视频

什么时候必须使用这个技能

当用户的目标是做图或做视频，而不是单纯写文章、写文案、做摘要时，优先判断是否属于以下任务：

  • 公众号封面图
  • 文章头图
  • 小红书封面
  • 种草图
  • 海报改版
  • 横版改竖版
  • 文生视频
  • 图片转视频
  • 静态图转动态视频
  • 参考图转视频
  • 参考视频转视频
  • 丝滑动态视频

如果用户只是讨论文案，没有明确图片或视频交付目标，不要误触发这个技能。

重要：路径解析

这个技能可能安装在不同位置。执行任何命令前，先根据当前加载的 SKILL.md 所在目录确定技能根目录，然后把下文中的 <SKILL_DIR> 替换成实际路径。

一、图片任务：先判断任务性质，再选场景

第一步：判断是“从零出图”还是“改已有视觉”

  • 如果用户重点是“根据标题/卖点生成一张图”，按从零出图处理
  • 如果用户重点是“保留原主体 / 保留信息层级 / 横改竖 / 重排版”，按改已有视觉处理

这个判断优先级高于平台词。

第二步：再判断目标平台或传播形态

  • 横版文章头图、公众号封面、技术媒体头图 → wechat_cover
  • 竖版信息流封面、小红书封面、种草图 → xiaohongshu_cover
  • 保留原视觉结构并改版 → relayout_poster

图片 scene 冲突裁决表

冲突输入正确处理
“小红书封面” + “保留原海报主体”优先 relayout_poster，因为任务本质是改版，不是从零出图
“公众号头图” + “竖版传播”先确认平台目标；如果最终是社媒竖版卡片，优先 xiaohongshu_cover
“做个封面” + “横版改竖版”优先 relayout_poster
“技术文章头图” + “给我更像小红书一点”优先看最终分发平台；公众号发文优先 wechat_cover，小红书分发优先 xiaohongshu_cover
“就用这个标题出图” + “保留信息层级”如果没有旧视觉结构，仍是从零出图，不要误选 relayout_poster

二、视频任务：先判断 task_type

视频任务不要误走图片 scene 路由，优先按 task_type 判断。

text_to_video

适合：

  • 用户只给文字描述
  • 想直接生成一段产品演示、氛围片、短视频片段
  • 没有参考图或参考视频也能跑

image_to_video

适合：

  • 用户明确给了一张静态图
  • 想让静态图“动起来”
  • 重点是保留主体、加轻微镜头运动和自然动态
  • 默认模型位：wan2.7-i2v
  • 也兼容：wan2.6-i2v-flash
  • 协议差异：Wan 2.6 用 input.img_url，Wan 2.7 用 input.media，图片类型为 first_frame

reference_to_video

适合：

  • 用户有参考图或参考视频
  • 希望保留主体一致性、参考素材风格或动作节奏
  • 可接受本地路径或 URL
  • 默认模型位：wan2.7-r2v
  • 也兼容：wan2.6-r2v-flash
  • 协议差异：Wan 2.6 用 input.reference_urls，Wan 2.7 用 input.media，图片 / 视频类型分别为 reference_image / reference_video

视频任务的判断原则

  • 只有静态图 → 优先 image_to_video
  • 有参考图或参考视频，希望保留参考特征 → 优先 reference_to_video
  • 没有任何参考素材，只有文字创意 → text_to_video

三、最小输入判断

只保留最小判断，不在主文件里展开完整字段手册。

图片任务

至少要能确定：

  • title
  • scene
  • style

视频任务

  • text_to_video：至少有 title 或 prompt
  • image_to_video：至少有 reference_images
  • reference_to_video：至少有 reference_images 或 reference_videos

如果字段不确定，不要猜，转去读 references/input-schema.md。

四、什么时候读 reference

  • 字段不确定时：读 references/input-schema.md
  • 图片 scene 不确定时：读 references/scenes.md
  • API / 输出 / 配置 / 成功判定不确定时：读 references/api-behavior.md

不要一次性把所有 references 全读一遍。

  • 只是图片生成，不要把视频排查说明一起加载
  • 只是视频生成，不要把 scenes.md 当视频路由文档
  • 用户已给完整 JSON 时，不要为了保险重读字段手册

五、如何判断是否真的成功

以下条件都满足，才算真正成功：

  1. API 返回成功
  2. 图片任务拿到了可解码或可下载的图片内容，或视频任务拿到了 video_url
  3. 输出文件实际写入成功
  4. .prompt.txt 文件实际生成
  5. JSON 里的 output_files 指向真实存在的文件

缺任意一项，都不应被表述为“已经成功生成”。

NEVER 列表

  • NEVER 在缺少 wan.api_key 时假装可以正常生成图片或视频
  • NEVER 在用户没有要求出图或出视频时误触发这个技能
  • NEVER 把 relayout_poster 当成所有视觉任务的默认兜底场景
  • NEVER 在字段不完整时臆造品牌色、参考图、参考视频、URL 或编辑指令
  • NEVER 把视频任务错路由到图片 scene 上
  • NEVER 在 API 返回失败时伪造“生成成功”的结果
  • NEVER 在没有真正拿到 .png 或 .mp4 文件时声称任务完成
  • NEVER 把 config.example.yaml 当成真实配置直接使用后又不提醒用户补 key
  • NEVER 为了凑效果擅自改变用户的核心主题、参考素材或任务类型

参考文档

  • references/README.md
  • references/input-schema.md
  • references/scenes.md
  • references/api-behavior.md

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 Wan Cover Plus AI skill do?

使用 Wan2.7-image 生成公众号封面图、小红书封面图、种草图和海报改版视觉稿，并支持文生视频、静态图转丝滑动态视频、参考图 / 参考视频转视频，以及为视频自动补 Edge TTS 配音与字幕烧录。视频任务兼容 Wan 2.6 与 Wan 2.7 模型，可通过 config.yaml 默认配置或输入 JSON 的 model 字段覆盖。用于把标题、副标题、卖点、品牌色、结构化 JSON、参考图或参考视频转成真实图片或视频输出；当用户提到封面图、头图、配图、种草图、视觉稿、海报重排版、横版改竖版、文生视频、图片转视频、静态图转动态视频、参考图转视频、参考视频转视频、丝滑动态视频、视频配音、字幕烧录、Edge TTS 配音时，必须优先考虑这个技能。支持 Prompt 构建、场景选择、真实 Wan API 调用、PNG / MP4 文件输出与 prompt sidecar 保存。

Why use Wan Cover Plus on TypingMind?

Because you install it once and use it with any model. Wan Cover Plus 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 Wan Cover Plus in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wwwzhouhui/skills_collection/tree/main/wan-cover-plus. 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 Wan Cover Plus?

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 Wan Cover Plus?

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

Is the Wan Cover Plus AI skill free?

It is published on GitHub by wwwzhouhui. 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.

Related AI Skills

View all
NousResearch logo

Pixel Art

NousResearch
OrganizationPopular

Pixel art w/ era palettes (NES, Game Boy, PICO-8).

53.5K
250.4K
6 files
View
NousResearch logo

Inference Sh Cli

NousResearch
OrganizationPopular

Run 150+ AI apps (image, video, LLM) via inference.sh CLI.

53.5K
250.4K
4 files
View
NousResearch logo

Weights And Biases

NousResearch
OrganizationPopular

W&B: log ML experiments, sweeps, model registry, dashboards.

53.5K
250.4K
3 files
View
NousResearch logo

Nemo Curator

NousResearch
OrganizationPopular

Curate LLM training data: dedupe, filter, PII redaction.

53.5K
250.4K
2 files
View

Set up your own AI workspace now

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