Home / dsy-xueai / image2editable · GitHub

image-to-ppt SKILL.md skillA

image-to-ppt from dsy-xueai/image2editable is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add dsy-xueai/image2editable/image-to-ppt@git:20260913.b1ba2b7

Pins git:20260913.b1ba2b7 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
dsy-xueai/image2editable
Path
skills/image-to-ppt/SKILL.md
Versions recorded
10
Latest version
git:20260913.b1ba2b7, committed Sep 13, 2026
First version recorded
Aug 15, 2026
Size
18,400 bytes
Repository stars
61
License
MIT

将图片、PDF、图片版 PPTX 或含原生对象的混合 PPTX 转换为严格质量校验、分层可编辑的 PowerPoint；保留既有原生文字、形状、表格和图表，并使用宿主视觉 Agent 完成组件决策。用于截图、设计稿、科研图和幻灯片页面的组件重建、残影检查与可编辑输出。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Image to PPT

把输入图片重建为分层可编辑 PPTX。质量未达标时，根据具体缺陷继续修复并重新验证；不得将整页 flatten 为单张图片，也不得将仅能打开的文件当作合格成品。

全部文字（包括艺术字）必须为可编辑文字，保留原有曲线、描边和多色。文字截图、转曲轮廓、透明文字叠在原字图上均不满足该要求。复用已验证的 OCR 和组件资产，只对存在缺陷的区域继续处理；渲染与编辑验收未通过时，不宣称转换完成。

清理描边文字时同时检查内部浅色填充及外侧阴影；只清除轮廓不代表文字已移除。重建范围须覆盖实际文字清理边缘，不能仅依据原 OCR 框。修复背景中的条纹、残色和字影仍属于未通过状态。

## 环境

- 转换前必须阅读并执行 [自动环境准备](references/setup.md)，完整仓库和仅安装 Skill 在 Windows、macOS、Linux 都自动准备缺失的 Python、Git、项目 Runtime、依赖、OCR、模型和所需渲染器。不得为依赖或模型安装向用户询问确认；遵循宿主实际审批与权限限制。
- Windows 新安装优先 D 盘，再选其他非 C 本地磁盘，仅在不存在其他本地磁盘时使用 C 盘；macOS/Linux 优先其他已挂载的本地磁盘，否则使用用户目录。使用 `scripts/skill_environment.py` 统一环境、模型、OCR、下载缓存与临时目录；复用已有可用环境和已验证模型。
- 使用 Python 3.10–3.12。仅有 Skill 时自动安装项目 Runtime，默认使用下文 Runtime Host Agent 流程处理图片、PDF 和 PPTX；不再要求使用者预先配置模型路径。
- 模型准备使用 `image2editable models install runtime --yes`，随后执行 `image2editable doctor`。LaMa 由本地 TorchScript adapter 调用，依赖 `torch>=2.5.1,<3`；SAM/LaMa/DINO 从已校验的 runtime receipt 解析。
- 原生 PDF 先复用 PowerPoint 或 LibreOffice，缺少时按自动准备流程安装；Windows PowerPoint 需要 `image2editable[render-qa]`。实际渲染校验通过后才能交付。
- 优先使用当前平台已正确安装的硬件加速环境；产品环境须通过 `doctor`，所有环境须通过下列设备预检。不要仅为 WSL 建议离开已经可用的环境：

  ```bash
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add dsy-xueai/image2editable/image-to-ppt@sha256:e9f563503a332ced

The line at the top of this page pins the label git:20260913.b1ba2b7, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ffcqraiwg5eavjhs.svg)](https://markdownregistry.com/a/art_ffcqraiwg5eavjhs)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 10 versions of this file, between Aug 15, 2026 and Sep 13, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
git:20260913.b1ba2b7 latest2026-09-13 b1ba2b7 18,400 BA view · diff
git:20260913.b096f262026-09-13 b096f26 20,160 BA view · diff
git:20260913.61aeaf52026-09-13 61aeaf5 20,033 BA view · diff
git:20260913.20329082026-09-13 2032908 19,658 BA view · diff
git:20260913.3a9daca2026-09-13 3a9daca 18,753 BA view · diff
git:20260911.be8f80c2026-09-11 be8f80c 18,537 BA view · diff
git:20260902.9adf9d22026-09-02 9adf9d2 16,583 BA view · diff
git:20260824.47803d72026-08-24 47803d7 17,510 BA view · diff
git:20260817.99491b32026-08-17 99491b3 17,273 BA view · diff
git:20260815.e674d9a2026-08-15 e674d9a 16,984 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (18400 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

dsy-xueai/image2editable · 61 stars · license MIT · pushed 2026-10-09 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ffcqraiwg5eavjhs
GET https://markdownregistry.com/api/v1/resolve?ref=dsy-xueai/image2editable/image-to-ppt
GET https://markdownregistry.com/api/v1/blob/e9f563503a332cede0651f2b99231605e82d2ee3165ab8039eb4b7952cba8d45

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from dsy-xueai/image2editable

image-to-psd SKILL.md skill
dsy-xueai/image2editable · skills/image-to-psd/SKILL.md · 将一张或多张图片转换为经过严格质量校验的分层 PSD；自动准备运行环境，通过当前 Agent 执行转换。输出修复背景、独立透明视觉组件和可编辑 Photoshop 文字图层。仅支持图片输入，不用于 PDF 或 PPTX。
git:20260913.b1ba2b7 · audit A · 61 stars

Every file in dsy-xueai/image2editable

Browse by kind, by grade A, or by owner.