Image Ppt To Editable logo

Image Ppt To Editable

Community
huyanxius
image-ppt-to-editable

将图片幻灯片转成可编辑 PPTX,或修复已有可编辑 PPT 的漏字、底图残字和重复文字。新转换按原版式拆分;修复保留既有图片对象、裁切与排版,优先复用素材,逐页回装验证。支持共用透明标志。不用于从大纲新做 PPT。

Overview

Publisherhuyanxius
Repositorypitchcraft
Skill nameimage-ppt-to-editable
Stars
4
Forks
0
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 huyanxius on GitHub. Read the source before you install it.

Installation

Install the Image Ppt To Editable 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/huyanxius/pitchcraft/tree/main/skills/image-ppt-to-editable
  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/huyanxius/pitchcraft.git /tmp/pitchcraft
mkdir -p .claude/skills
cp -r /tmp/pitchcraft/skills/image-ppt-to-editable .claude/skills/image-ppt-to-editable
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Image Ppt To Editable 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 Image Ppt To Editable 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 Image Ppt To Editable 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.

图片 PPT 转可编辑

默认用宿主的读图能力、内置 imagegen 和本地 PPT 组装完成。不要为了转换重新搜索、评测或安装一批第三方转换器;不把第三方 OCR Token、付费 API 或大型分割模型作为开工前提。若用户明确要求某个工具的实测,真实运行该工具,不能把自主重建说成它的效果。

先区分转换与修复

  • 新转换:整页位图、图片式 PDF 或尚未拆分的 PPT,要恢复文本和有意义的独立素材,走下方“逐页重建”。
  • 已有 PPT 修复:已经有文本框和拆好的图片,只缺少部分可编辑文字、底图仍有字或文字重复。先读 保留对象的修复工作流,不要再执行素材拆分或整页重建。
  • 用户说“原来两张就保持两张”时,这是最终 PPT 对象约束:原图片的数量、边界、位置、大小、裁切、旋转与组织关系保持不变。清理可以在素材内部进行;不得为了方便合并、切碎或覆盖成整页图。已有正确的原生文本和图形原样保留。
  • 共通节奏:先做出一页回装后的完整效果,随后按页或短批次完成“处理→回装→检查”。不能积累几十张生成素材却只有少数页面可看。用户明确只要检查时止于检查,已有整套授权时继续执行,不自行增加确认关卡。

输入和处理粒度

  • 接收幻灯片图、图片式 PDF、纯图片或部分可编辑的 PPTX。保留源文件、页数、顺序和页面比例,另建输出目录,另存新文件,不覆盖输入。
  • PPTX 先读内部对象和媒体关系。整页只是一张图时优先提取嵌入原图;若存在裁切、旋转、组合或原生对象,不能盲取图片冒充页面。保留既有原生对象与备注,按真实页面做必要渲染。
  • 不改写文案、不换风格、不添加页面。看不清的文字标记核对,不凭空补全。
  • 单页直接做。多页先挑一页建立共同的字体和素材处理方式;用户只要求试用时做到样张即止,已经授权整套处理时继续完成整套,不反复请求确认。用户明确要先确认样张时才等待。
  • 不默认派子代理。需要时遵守当前会话的授权和并发限制。

逐页重建(仅新转换)

1. 读图并记录对象

记录画布尺寸、可读文字及其坐标、字号层级、颜色和原图字体特征;另列背景、Logo、照片、插画、装饰、简单图形、图表和表格。坐标统一采用源图像素,组装时等比映射。

区分页面正文和画面内纹理文字:主标题、注释、标签应编辑;书页纹理、照片招牌等可以随位图保留。已有原始 Logo、照片、SVG 或透明素材时优先复用,并保持比例。

2. 分离背景和图片素材

  • 纯色或普通渐变可用原生背景。复杂纸纹、山水、照片背景用内置 imagegen 的编辑模式清除将要重建的文字和前景。
  • 编辑前查看输入。提示词锁定原构图、颜色、纸张材质、光影和位置,明确是清除与补全,不是重设计。
  • 复杂前景优先按有意义的视觉对象分离,保留原图特征。相互遮挡的书页、建筑等可以作为一个组合位图;如未再拆开,要说明真实粒度。
  • 不要求每张复杂配图都变成矢量。可移动图片、原生形状、数据驱动图表是不同的可编辑程度。
  • 当生成资产无可靠 Alpha 时,直接走“纯色底 + 实际抠除”;不要反复提示“透明”并接收画出来的棋盘格。仅在遮挡补全需要时使用生成式编辑,避免无谓重画导致细节漂移。

需要透明资产时读取 透明素材处理:其中包含可直接执行的纯色抠除命令和 Alpha 校验。文件名 PNG、黑底显示、透明预览和棋盘格都不构成透明证据。像素校验也不能替代边缘/内容检查。

3. 恢复可编辑元素并组装

使用当前可用的 Presentations 技能和它提供的运行时、PPT API 与验证器,不硬编码某次运行的依赖版本。图片编辑使用内置 imagegen;确定性的底色抠除使用本 skill 的本地工具。

  • 正文、标题、标签、数字是可见的原生文本框。按原图字号、字距、位置还原,不通过隐藏文本制造可编辑比例。
  • OCR 只作候选,回到原图核对文字、图标误识别、跨栏与跨图片边界的句子。按整页逻辑恢复一份完整文本,不按素材边界截断文句。
  • 标题书法字或艺术字没有原字体时选接近的已安装字体并说明近似。字号同时受实际字形宽度和高度约束;不用 OCR 框高直接当字号,也不靠大幅负字距塞进框。保留原文字旋转与前景颜色。
  • 直线、分隔线、关系图节点、简单连接线、表格尽量使用原生对象。关系线每条保持完整可选中,避免大量零碎线段。
  • 图表仅在源数据可靠时恢复为数据驱动图表;否则保留独立图像或明确是原生线条近似,不能声称数据可编辑。
  • 顺序为背景、独立图片、结构图形、文字,具体按源图遮挡关系调整。避免同一文字或图案既留在背景又叠一份。
  • 支持用户分别移动素材;素材嵌入 PPTX,同时保存独立文件。不要只交付一张整页图。

验证和交付

  • 核对源图中的文字覆盖、页数、顺序、页面尺寸;检查文本框、图片与形状数量,以及图片关系是否有效。
  • 所有应透明的资产验证 Alpha,并在组装页面中检查边缘、底色残留和纸张内部是否被误抠除。
  • 结构校验通过后,实际打开 PPTX 供用户验收。不截屏、不上传截图、不把截图当门禁。可做文件渲染验证;若当前约束连渲染图也禁止,用原生应用/PDF检查,不为此放弃可编辑检查。
  • 批量前用一页含中文的源文件与输出检查渲染器。中文渲染出现替代字体或乱码时,先查本地字体和渲染器的 fontconfig 配置。某个渲染器的回退不等于源 PPT 已正确或已损坏,分别记录证据;在可用的目标应用核实。
  • 一轮整页检查后,只修发现的缺字、残字、失真、接缝和溢出等具体问题,再检查受影响页面。已认可页面冻结;达到约定要求即停止,不额外抛光或重生成。
  • 交付可编辑 .pptx;新转换按需附独立素材目录或 ZIP,已有 PPT 修复以完整文件为交付单位;简短说明尚未拆开的组合、字体近似与生成式编辑的细节差异。中间绿色底、假透明失败图、诊断报告不作为成品。
  • 只说已验证的结果。区分“文件结构通过”“文件可打开”“用户认可视觉效果”。进度以已回装并检查的页数计;素材生成数另列,不能替代完成页数。用户问进度时直接回答,并提供当前整页结果。少展示空白条、页脚等过程素材,少重复承诺;恢复任务先清点并回装可用成果。

需要清背景、分离素材的提示词时读 提示词模板。本 skill 自带的是 MIT 授权的独立抠除脚本,只依赖 Pillow;来源见 脚本来源,无需安装整套第三方 skill。

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 Image Ppt To Editable AI skill do?

将图片幻灯片转成可编辑 PPTX,或修复已有可编辑 PPT 的漏字、底图残字和重复文字。新转换按原版式拆分;修复保留既有图片对象、裁切与排版,优先复用素材,逐页回装验证。支持共用透明标志。不用于从大纲新做 PPT。

Why use Image Ppt To Editable on TypingMind?

Because you install it once and use it with any model. Image Ppt To Editable 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 Image Ppt To Editable in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/huyanxius/pitchcraft/tree/main/skills/image-ppt-to-editable. 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 Image Ppt To Editable?

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 Image Ppt To Editable?

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

Is the Image Ppt To Editable AI skill free?

It is published on GitHub by huyanxius. 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 👇