Chengfeng Visual logo

Chengfeng Visual

CommunityPopular
Agentchengfeng
chengfeng-visual

给剪好的口播配画面:在录屏上盖 HTML 层(圈重点标注 / 小黑整屏动画 / 推近),层绑字幕屏、由播放器逐帧驱动、直接在预览里看。用户说做分镜、配画面、加动画、圈重点、B-roll、做 storyboard 时使用。不要用于删词剪辑、字幕、物理剪切或成片渲染。

Overview

PublisherAgentchengfeng
Repositorychengfeng-videocut-skills
Skill namechengfeng-visual
Stars
3K
Forks
385
Bundled files
36
LicenseApache-2.0
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.

  • 36 bundled files

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

  • Open source

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

Installation

Install the Chengfeng Visual 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.
  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/Agentchengfeng/chengfeng-videocut-skills.git /tmp/chengfeng-videocut-skills
mkdir -p .claude/skills
cp -r /tmp/chengfeng-videocut-skills/plugins/chengfeng-videocut/skills/chengfeng-visual .claude/skills/chengfeng-visual
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Chengfeng Visual 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 Chengfeng Visual 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 Chengfeng Visual 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.

画面(分镜)

这是一件事,不是流程的一段。 用户什么时候喊它就什么时候做,改完剪辑可以回来再做。

前提只有两个:账本和字幕已经存在(层按字幕屏放、时间从账本算)。

text
需要   edit-list.json、transcript.json、subtitles.json
产出   visuals.json + modules/<序号-名字>/index.html

干完就停,不指挥用户下一步

先读取并执行 业务 Skill 的阶段合同。 模块写法的硬规矩见 模块契约, 判断规则见 画面判断

0. 就绪

先执行 检查更新 的「就绪检查」——skills 是否 最新、Runtime 是否配套;插件根也在那里定位(本文命令里的 <插件根> 都代入 那个字面路径)。只有「就绪」才继续;「需新会话」或「停」按它的处置执行 (含「禁止自制替代界面」禁令),业务 Skill 不自带环境逻辑。

若就绪结果为 runtime.kind=desktop-managed,直接复用桌面 App 已安装的稳定 CLI 与 同一 launchd/windows-task 服务;不要解析 Electron 路径、另装依赖或起第二个 Runtime。

命令

bash
node "<插件根>/scripts/ensure-running.cjs" --json
node "<插件根>/scripts/videocut-cli.cjs" visual get   <project> --json
node "<插件根>/scripts/videocut-cli.cjs" visual frame <project> --cues sub-0004,sub-0005 --count 12 --out <dir> --json
node "<插件根>/scripts/videocut-cli.cjs" visual add   <project> --module modules/01-xx/index.html --cues sub-0004,sub-0005 [--zoom x,y,w,h] [--id vis-0001] --json
node "<插件根>/scripts/videocut-cli.cjs" visual remove <project> --id vis-0001 --json

ensure-running 必须先证明 canonical 5190 属于当前平台的托管服务;失败就透传并 停止,不回退 foreground 或自选端口。

层绑字幕屏--cues),产品自己换算成词 id——层永远不可能绑上没人说的词, 剪辑变了层自己跟着挪。不存秒数。

四步,一步不跳

text
① 文字定任务    读 subtitles.json,按语义分段,每段回答:
               教程/演示/证明,还是概念/逻辑/过渡?
② 抽帧看画面    visual frame 抽 8-12 帧,真的用眼睛看。
               实测 12 段里有 2 段被画面推翻文字预判 —— 这步不是走形式
③ 量运动窗口    相邻帧做像素差,找出滚动/切换/操作的时刻。
               层只盖稳定窗口,圈在画面开始动之前退场
④ 做层放层     写模块 → visual add → 在预览里逐层核对

② 的判断规则

text
画面正是他说的东西     → 标注:圈住、说到哪个词圈哪里。真证据不许盖
画面弱相关/空白       → 小黑动画:整屏白底,从风格库做
画面自身足够清楚      → 不动。这是最常见的正确答案(实测 13 段里 4 段不动)

③ 的产出物是数字,不是感觉

text
圈的坐标      像素统计量出来(灰度扫描找文字行),不许目测 —— 目测差过 50px
互动时刻      逐帧像素差找突变(实测一次从 4 跳到 335),圈在它之前 0.2s 退完
稳定窗口      开头常有滚动(他在找内容),层从停稳那屏的 cue 开始绑

推近(zoom)用之前先想

text
默认不推近。   960x720 的录屏放大就糊,用户会立刻看出来
非推不可时     ≤1.6 倍、区域取 62.5% 见方居中 —— 构图完整 > 读清小字
字太小读不清   用圈引导视线就够了;真要读清,答案是高分辨率重录,不是放大

审阅循环

模块目录用序号命名01-daily-report05-anim-task-split), 时间线轨道上显示目录名,用户报号你改那一层,别的不动。

两条改层纪律,各对应一次真事故:

text
改层必查模块     层收窄/延长后,模块里写死的相对时刻不会跟着变 ——
                圈的出场时刻可能落到层结束之后,永远不出现
验收看像素      截图看画面,不查 DOM 属性。「可见性翻转正确」的 iframe
                曾经物理上不在画面里 —— 属性全对、屏幕全空

不许做什么

  • 不许跳过抽帧和运动窗口直接做(两种错各犯过一次:盖掉真证据、圈悬在滚动上)
  • 不许把每段都做点什么——铺满不是目标,不动是常见答案
  • 不许存秒数、不许目测坐标、不许在白底页面上加压暗
  • 没有真实内容不许拿占位图充数
  • 风格从注册表选,不得凭空发明
  • 品牌图标用官方字形,不许手画替身(X 用两笔交叉线画过,被用户抓了)。 本地索引没有的,从 simple-icons 取单色官方 glyph(黑白风格正好配), 原 svg 存进模块目录备查;同一条片里同一品牌只能长一个样

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 Chengfeng Visual AI skill do?

给剪好的口播配画面:在录屏上盖 HTML 层(圈重点标注 / 小黑整屏动画 / 推近),层绑字幕屏、由播放器逐帧驱动、直接在预览里看。用户说做分镜、配画面、加动画、圈重点、B-roll、做 storyboard 时使用。不要用于删词剪辑、字幕、物理剪切或成片渲染。

Why use Chengfeng Visual on TypingMind?

Because you install it once and use it with any model. Chengfeng Visual 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 Chengfeng Visual in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Agentchengfeng/chengfeng-videocut-skills/tree/main/plugins/chengfeng-videocut/skills/chengfeng-visual. 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 Chengfeng Visual?

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 Chengfeng Visual?

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

Is the Chengfeng Visual AI skill free?

Yes. It is published on GitHub by Agentchengfeng under the Apache-2.0 license. 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 👇