Agent skill

Drawai Image2ppt

by Renaissance-Mind in Renaissance-Mind/DrawAI

把已经确定的页面图像转成可编辑 PowerPoint。支持 Workbench 中的 DrawAI-Flow 和当前会话 Skill 两种模式,按当前模型与工具能力给出默认路由;包含原生 PPT 构建、编辑、导出和检查工具包。

Apache-2.0Auto-check passedDocuments & Office

Install Drawai Image2ppt

skills CLI
$ npx skills add Renaissance-Mind/DrawAI --skill drawai-image2ppt -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Renaissance-Mind/DrawAI drawai-image2ppt --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Renaissance-Mind/DrawAI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/drawai-image2ppt .claude/skills/drawai-image2ppt && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
drawai-image2ppt
GitHub stars
146
Token cost
~803 tokens
SKILL.md length
161 words
Files
74 (incl. scripts, references, assets)
Skills in repo
3
Repo updated
First seen
Licence
Apache-2.0

At a glance

把已经确定的页面图像转成可编辑 PowerPoint。支持 Workbench 中的 DrawAI-Flow 和当前会话 Skill 两种模式,按当前模型与工具能力给出默认路由;包含原生 PPT 构建、编辑、导出和检查工具包。

  • Works in 4 steps: status 不带批次 ID,检查当前连接与实际健康信息。 → submit 传入… → 用户指定在工作台手动操作时打开该入口继续。用户要求直接制作或已经确定执行流程时调用… → …
  • Tasks that involve PowerPoint presentations
  • SKILL.md covers 输入与模式, DrawAI-Flow, 当前会话 Skill and 环境与验证
  • Runs Python scripts from its folder; calls python

What it does

Drawai Image2ppt is an agent skill from Renaissance-Mind/DrawAI. 把已经确定的页面图像转成可编辑 PowerPoint。支持 Workbench 中的 DrawAI-Flow 和当前会话 Skill 两种模式,按当前模型与工具能力给出默认路由;包含原生 PPT 构建、编辑、导出和检查工具包。

Its SKILL.md is about 800 tokens, which your agent loads only when the skill is triggered. The skill folder holds 81 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/rebuildable-deck/assets/src/line_chart.py` and `assets/rebuildable-deck/build.py`).

It sits in Documents & Office, covering PowerPoint presentations. It works with Microsoft PowerPoint and Python. The repository describes itself as: Make raster image ediatble. 将生成图像(如GPT-Image-2或Nano Banana)或截图变为可编辑的格式,实现高质量PPT、论文图直出。 The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve PowerPoint presentations

Example prompts

  • “/drawai-image2ppt”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. status 不带批次 ID,检查当前连接与实际健康信息。
  2. submit 传入 visual_manifest,上传经过验证的页面图像,返回本任务的排队批次与 Workbench 地址;提交本身不代表转换成功。
  3. 用户指定在工作台手动操作时打开该入口继续。用户要求直接制作或已经确定执行流程时调用 start,执行本任务的批次,随后用 status 查看真实进度。出现失败或等待素材审阅时处理实际原因;不要把请求发送成功当成成品。
  4. 全部页面完成后调用 export,传入本任务的 batch_id 和新的 output_path,下载完整 PPTX,再按下述文件验收检查。

What it can do on your machine

Read from SKILL.md and the folder at commit 212857e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Drawai Image2ppt loads about 803 tokens when it runs, and up to ~2.4M if it reads all its reference files. Until then it costs about 33 tokens; SKILL.md has 161 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~803
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4M

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from Renaissance-Mind/DrawAI at commit 212857e, republished under its Apache-2.0 licence (© Renaissance-Mind). 161 words, ~803 tokens.

Download SKILL.mdSave it as .claude/skills/drawai-image2ppt/SKILL.md (or your agent's skills folder). This skill also uses 73 other files; get the full folder from GitHub.
name
drawai-image2ppt
description
把已经确定的页面图像转成可编辑 PowerPoint。支持 Workbench 中的 DrawAI-Flow 和当前会话 Skill 两种模式,按当前模型与工具能力给出默认路由;包含原生 PPT 构建、编辑、导出和检查工具包。

DrawAI Image2PPT

在 DrawAI 插件中使用时,先阅读 drawai-readme,沿用已经确认的模式。输入是 drawai-design 确定的页面图像,或用户直接提供的完整页面图像。本阶段负责实际 PPT 构建、原生对象编辑、导出、检查与制作源交付。独立复制本目录的工具包时,可直接使用其 Python API/CLI 和用户已经指定的转换方式。

输入与模式

先验证 drawai.visual-deck.v1 清单,按保存的页序与原图处理:

bash
python "$SKILL_DIR/scripts/visual_deck.py" verify visual-deck.json

只提供图片时先登记清单;已有可编辑 PPTX 的明确局部修改可直接进入原生编辑流程。模板和视觉设计需要改变时回到 drawai-design 更新输入,不暗中改动已确定的内容。

模式执行方式
DrawAI-Flow将图像提交现有 Workbench,由其配置的流程、处理器与模型完成解析、素材处理、重建和导出,工作台显示实际阶段进度
Skill在当前会话看图、编写和执行本地重建代码,调用本技能工具包创建与检查 PPT,不启动另一个 Agent 进程处理视觉理解

默认使用 drawai-readme/scripts/plan.py 或 drawai_plan 的路由:GPT 5.6+、Claude 5+、DeepSeek Flash v4.1+ 使用 Skill,其余或版本未知使用 Flow。用户明确选择优先;Skill 需要看图与本地执行能力,Flow 需要现有 Workbench 与已配置的运行环境。模型名单只是默认执行策略,不能替代实际文件验收。

DrawAI-Flow

先确认 Workbench 可连接、所需处理器与 Agent 配置可用。默认浏览器入口是 http://127.0.0.1:5174/,API 是 http://127.0.0.1:8890;使用当前安装配置的实际地址。启动和首次模型准备遵循仓库运行文档,不重建 Studio 项目服务。

有 drawai_flow 时使用以下操作:

  1. status 不带批次 ID,检查当前连接与实际健康信息。
  2. submit 传入 visual_manifest,上传经过验证的页面图像,返回本任务的排队批次与 Workbench 地址;提交本身不代表转换成功。
  3. 用户指定在工作台手动操作时打开该入口继续。用户要求直接制作或已经确定执行流程时调用 start,执行本任务的批次,随后用 status 查看真实进度。出现失败或等待素材审阅时处理实际原因;不要把请求发送成功当成成品。
  4. 全部页面完成后调用 export,传入本任务的 batch_id 和新的 output_path,下载完整 PPTX,再按下述文件验收检查。

只有使用本任务提交结果中的批次 ID 才能启动或导出。DRAWAI_WORKBENCH_API_URL 与 DRAWAI_WORKBENCH_UI_URL 配置服务地址;本地 Python 路径可用 DRAWAI_PYTHON 指定。没有 MCP 时,可在 Workbench 上传相同图像并执行,或使用现有 REST API/CLI 完成同一流程。

当前会话 Skill

查看每页原图与已知文字、数据,拆分文字、形状、连线、表格、图表和复杂局部素材。简单结构用原生对象;照片、复杂插画与纹理可用局部原图裁剪。需要可编辑的内容按对象重建,不能把整页图像当成最终 PPT 背景。

保持确定的画布、相对位置、样式、分组与层叠顺序。有真实原始数据时使用数据构建图表;只有曲线图片时记录无法恢复的精确数据与近似。用户 PPTX 模板的格式要求通过实际模板解析与原生结构处理。

文档使用 presentation.document.v1,以 pt 作为位置、尺寸、字号与线宽单位;96 DPI 下像素坐标统一乘 0.75。可写文档 JSON,或用 Python 构造页面对象。将重建与修改的实现、素材处理和导出源保存在任务目录。

bash
python "$SKILL_DIR/scripts/ppt.py" export deck.document.json --pptx output/v1/deck.pptx --svg-dir output/v1/svg --report output/v1/export.json

文档 API 与图片重建、PPTX 原生修改、SVG 插入流程分别见 文档 API 和 制作与编辑。复杂素材见 素材,属性条件见 实现矩阵。实际实现与扩展方法见 代码指南。

环境与验证

使用 Python 3.12+,安装本目录 scripts/requirements.txt。LibreOffice 与 Poppler 用于真实 PPTX 渲染和 SVG 导出;LaTeX 转 Office Math 需要 Pandoc。字体必须可用,报告记录实际字体替代。预览默认忽略临时渲染副本的嵌入字体引用,交付原件保留嵌入字体;需要原字体渲染时使用 --embedded-fonts preserve。

bash
python "$SKILL_DIR/scripts/ppt.py" validate output/v1/deck.pptx
python "$SKILL_DIR/scripts/ppt.py" inspect output/v1/deck.pptx --output output/v1/inventory.json
python "$SKILL_DIR/scripts/ppt.py" render output/v1/deck.pptx --output-dir output/v1/preview

两种模式都检查实际 PPTX:页数、页序、尺寸、文字与数据、可编辑对象、引用关系,以及预览中的断行、裁剪、遮挡、连线与模板一致性。发现问题后在新版本目录修正并重新导出。模板复制、备注或原生 XML 编辑涉及结构时,目标 PowerPoint 可用则实际打开,确认没有修复提示;不具备该环境时说明实际完成的检查。

最终交付 PPTX、页面预览、视觉图像清单,以及所用脚本、文档源、素材、相关数据和转换报告。Flow 的完整运行包和 Skill 的文档模型保留各自实际来源;统一阶段输入与交付,不把内部数据格式差异伪装成同一种运行记录。

© Renaissance-Mind, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 73 other files (scripts, references, assets) in skills/drawai-image2ppt of Renaissance-Mind/DrawAI.

  • SKILL.md
  • LICENSE
  • agents/openai.yaml
  • assets/demo/agent_workflow.png
  • assets/demo/demo_figure.png
  • assets/demo/formula.svg
  • assets/rebuildable-deck/assets/src/line_chart.py
  • assets/rebuildable-deck/build.py
  • assets/rebuildable-deck/data/metrics.csv
  • assets/rebuildable-deck/requirements.txt
  • references/code-map.md
  • references/document-api.md
  • references/export-capabilities.csv
  • … and 61 more

Open the folder on GitHubat commit 212857e

Compare with similar skills

Drawai Image2ppt next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Drawai Image2ppt compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Drawai Image2ppt this skillRenaissance-Mind/DrawAI146—~803Automated safety check: PassApache-2.0
PowerPoint Reader and BuilderTokenRhythm/opensquilla7.1k—~3.8kAutomated safety check: NotesApache-2.0
PPTXAgentTeam-TaichuAI/ScienceClaw671—~2.5kAutomated safety check: PassProprietary
Native Enhance PPTXbyungjunjang/slide-master280—~330Automated safety check: PassMIT
Office To Mdshuyu-labs/WebCode278—~1kAutomated safety check: NotesCustom licence
Ppt Masterbyungjunjang/slide-master280—~407Automated safety check: PassMIT

Similar skills

  • PowerPoint Reader and Builder

    TokenRhythm/opensquilla

    Reads, edits in place, or creates PowerPoint .pptx decks, picking one of three paths based on what tools and files are available.

    7.1k GitHub stars~3.8k tokensUpdated yesterday
    Documents & OfficeAuto-check: notes
  • PPTX

    AgentTeam-TaichuAI/ScienceClaw

    Use this skill any time a .pptx file is involved — as input, output, or both.

    671 GitHub stars~2.5k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed
  • Native Enhance PPTX

    byungjunjang/slide-master

    Enhance a finished PPTX while keeping visible content and layout stable.

    280 GitHub stars~330 tokensUpdated 11 days ago
    Documents & OfficeAuto-check passed
  • Office To Md

    shuyu-labs/WebCode

    Convert Office documents (Word, Excel, PowerPoint, PDF) to Markdown format.

    278 GitHub stars~1k tokensUpdated 3 mo ago
    Documents & OfficeAuto-check: notes
  • Ppt Master

    byungjunjang/slide-master

    Post-router owner for authoring or regenerating presentation visuals through the PPT Master SVG pipeline: new decks from source material or a topic, PPTX re-architecture, generation from an…

    280 GitHub stars~407 tokensUpdated 11 days ago
    Documents & OfficeAuto-check passed
  • Exam Ingest

    ZeKaiNie/universal-examprep-skill

    从学生上传的课件/大纲/老师勾的重点/真题,一键初始化并验证备考工作区:解析 PDF、DOCX、PPTX、 XLSX、常见独立图片与 txt/md,建立分章节 LLM Wiki、标准题库、结构化接管队列与进度状态;仅在 Python 确实无法运行时 明确降级为手动写盘。当工作区尚未建立、资料发生变化、或建库 readiness 被阻断时使用。

    303 GitHub stars~5.6k tokensUpdated 13 days ago
    Documents & OfficeAuto-check passed

More from Renaissance-Mind/DrawAI

  • Drawai Design

    Renaissance-Mind/DrawAI

    确定 DrawAI PPT 的页面视觉图像。根据内容、参考图与 PPTX 模板逐页设计和生成,或接收用户已经确定的页面图像;需要参考时接入模板页面,交付有序图像清单给 drawai-image2ppt。

    146 GitHub stars~421 tokensUpdated yesterday
    Auto-check passed
  • Drawai Readme

    Renaissance-Mind/DrawAI

    DrawAI 插件的整体说明与 PPT 制作入口。用户通过 DrawAI 制作或编辑 PPT 时先读本技能,检查当前图像工具和模型,按需补齐参考、页面细节与转换模式,再进入视觉设计和图像转 PPT。

    146 GitHub stars~616 tokensUpdated yesterday
    Auto-check passed
  • Drawai Simple

    Renaissance-Mind/DrawAI

    Reconstruct a single raster image as a standalone, visually faithful, structurally editable SVG using the DrawAI Simple Baseline protocol.

    146 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Drawai Image2ppt

What does Drawai Image2ppt do?

把已经确定的页面图像转成可编辑 PowerPoint。支持 Workbench 中的 DrawAI-Flow 和当前会话 Skill 两种模式,按当前模型与工具能力给出默认路由;包含原生 PPT 构建、编辑、导出和检查工具包。. Drawai Image2ppt is an agent skill from Renaissance-Mind/DrawAI.

When should I use Drawai Image2ppt?

Drawai Image2ppt fits situations like: tasks that involve PowerPoint presentations.

How do I install Drawai Image2ppt in Claude Code?

Run `npx skills add Renaissance-Mind/DrawAI --skill drawai-image2ppt -a claude-code`. Or copy the skill folder (skills/drawai-image2ppt in Renaissance-Mind/DrawAI) into .claude/skills/drawai-image2ppt in your project. Claude Code loads it when a task matches its description.

How do I install Drawai Image2ppt in Codex?

Run `npx skills add Renaissance-Mind/DrawAI --skill drawai-image2ppt -a codex`. Or copy the skill folder (skills/drawai-image2ppt in Renaissance-Mind/DrawAI) into .agents/skills/drawai-image2ppt in your project. Codex loads it when a task matches its description.

Can I use Drawai Image2ppt in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Renaissance-Mind/DrawAI --skill drawai-image2ppt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/drawai-image2ppt, .gemini/skills/drawai-image2ppt, .github/skills/drawai-image2ppt and .opencode/skills/drawai-image2ppt in your project.

What does Drawai Image2ppt need to run?

Going by SKILL.md and its folder, Drawai Image2ppt needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Drawai Image2ppt access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Drawai Image2ppt safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Drawai Image2ppt use?

Drawai Image2ppt is published under the Apache-2.0 licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Drawai Image2ppt use?

About 803 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.4M tokens, read only when the agent opens those files.

What are the alternatives to Drawai Image2ppt?

Skills that share tags, products or a category with Drawai Image2ppt: PowerPoint Reader and Builder (TokenRhythm/opensquilla, 7.1k stars), PPTX (AgentTeam-TaichuAI/ScienceClaw, 671 stars), Native Enhance PPTX (byungjunjang/slide-master, 280 stars) and Office To Md (shuyu-labs/WebCode, 278 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Drawai Image2ppt?

Renaissance-Mind (a GitHub organization) maintains it in Renaissance-Mind/DrawAI, which has 146 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 10, 2026.

Source: Renaissance-Mind/DrawAI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.