doa-ppt

doa-ppt is a skill for Claude Code, Codex from medalsoftchina/workcopilot. It costs 76 tokens per session (19,530 once invoked), scanned A, original, Apache-2.0.

A workflow for creating business, product, technical, and project presentations as HTML previews and PowerPoint files. It can also turn source material such as PDFs, screenshots, notes, or existing slides into a presentation.

In plain words
What is it for?
Use it to build multi-page slide previews, export high-fidelity or editable PowerPoint files, adapt existing materials, and verify page count and output quality.
Why use it?
It organizes source material into a decision-focused slide story and checks the HTML layout before exporting the final file.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit Use it to build multi-page slide previews, export high-fidelity or editable PowerPoint files, adapt existing materials, and verify page count and output quality.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/medalsoftchina/workcopilot/doa-ppt
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add medalsoftchina/workcopilot --skill doa-ppt
Clone the repo
git clone --depth 1 https://github.com/medalsoftchina/workcopilot

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for doa-ppt

README.md
[![agentmods](https://agentmods.dev/badge/skills/medalsoftchina/workcopilot/doa-ppt/github.svg)](https://agentmods.dev/skills/medalsoftchina/workcopilot/doa-ppt)
Your own site
<a href="https://agentmods.dev/skills/medalsoftchina/workcopilot/doa-ppt"><img src="https://agentmods.dev/badge/skills/medalsoftchina/workcopilot/doa-ppt/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for doa-ppt

Your own site · 80×15
<a href="https://agentmods.dev/skills/medalsoftchina/workcopilot/doa-ppt"><img src="https://agentmods.dev/badge/skills/medalsoftchina/workcopilot/doa-ppt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 19,530 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.19530
Opus 5 $0.00038 $0.09765
Sonnet 5 $0.00015 $0.03906
Haiku 4.5 $0.00008 $0.01953

Measured 8d ago against content hash 869fb2cc7afa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

doa-ppt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (references/pptx-converter-template.py, references/screenshot-pptx-template.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

embedded-skills/doa-ppt/SKILL.md · 1,209 lines

How it starts

The opening of the file, as written. The whole thing — 1,209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HTML to PPTX — 商务演示文稿生成

工作流概览

用户输入(描述 + 参考图)
  → 确认PPT规模
  → 使用公司模板(唯一默认模板)
  → 生成可翻页 HTML 预览
  → 逐页检查 HTML 是否越界/裁切/重叠
  → 用户确认/调整 HTML
  → 只有用户明确确认 HTML 无问题后,才进入 PPT 模式选择
  → 默认推荐截图高保真模式(用户如需二次编辑再切换到可编辑)
  → 生成 PPT

本次实战经验固化

当用户提供 PDF、截图、既有 HTML 或已有 PPT,并要求“基于这个继续生成 / 整合 / 扩展 / 转 PPT”时,必须先把资料链路整理清楚,再改版式。

2026-05-30 延峰项目增补(强制)

  1. HTML 是唯一语义源slides.html 才是可维护源文件;截图型 .pptx/.pdf 只作为交付物,不作为反向编辑来源。
  2. 双导出链路必须物理分离
  • 截图高保真:export_pptx.py
  • 可编辑重建:export_editable_pptx.py
  • 严禁在同一脚本里混合两种导出逻辑,避免需求反复切换时互相污染。
  1. 需求切换优先级规则:当用户在“可编辑 / 不可编辑”之间反复切换时,始终以“最后一次明确指令”为准,立即切换导出模式,不纠缠历史决策。
  2. 先定稿再导出:只有在用户明确确认“按当前 HTML 导出”后,才执行最终导出;导出阶段不再顺手改布局,避免一边改版一边导出导致版本漂移。
  3. 输出文件不得覆盖旧版本:每次最终交付使用新文件名(建议带日期和后缀,如 _Editable_YYYYMMDD_HD_YYYYMMDD),防止 PermissionError 和历史交付丢失。
  4. 导出后必须二次验证:至少校验文件存在、页数一致、截图分辨率正确(高清链路应为 2560×1440),再对外宣称“已完成交付”。

资料驱动型 PPT 的处理顺序

  1. 先定位源材料:在工作区搜索 .pdf.html.pptx、生成脚本和相关资源,确认哪一个是主源文件、哪一个是导出结果。
  2. PDF 先提取文本,失败再转图片阅读:优先用 pypdf/pdfplumber;如果每页文本为空,说明多半是扫描型 PDF,应使用 PyMuPDF 渲染为图片后逐页查看。
  3. 先总结再入页:不要把 PDF 原文堆进 PPT。先提炼为“调研范围 → 候选路线 → 选型结论 → 当前方案”的决策链路。
  4. 封面优先确认:封面通常是客户第一眼看到的页面。若用户要求“第 N 页挪到首页作为封面”,必须同步调整 active 状态、data-index 和页码。
  5. 插入/删除页面后整体重编号:任何插页、删页、重排都要统一更新以下内容,缺一不可:
    • 每页 data-index 属性(从 0 连续递增)
    • 每页 .page-no 页码(当前页 / 新总数
    • 目录页中对应条目的增删和序号重编
    • HTML 注释中的页码标注(如 <!-- P7: xxx -->
    • 使用 multi_replace_string_in_file 一次性完成所有页码更新,避免遗漏

技术方案类 PPT 推荐叙事结构

对于架构、安全、技术选型类 PPT,优先采用以下结构:

  1. 封面:结论导向,明确方案对象、日期和一句话判断
  2. 调研范围:说明为什么要调研,选型标准是什么
  3. 候选路线:把语言级、进程级、内核级、容器级、云托管等方案放在一张对比页
  4. 选型结论:说明为什么选择当前方案,而不是只说“推荐方案”
  5. 风险论证:用业务可理解的语言说明备选方案的风险边界
  6. 推荐架构:给出控制面、执行面、隔离边界、运行时治理
  7. 落地配置:给出参考规格、扩容方式、运维和审计能力
  8. 最终结论:用一句客户能复述的话收束,例如“跑自己的任务用 Job,跑别人的代码用沙箱”

版式与导出踩坑记录

  • 固定幻灯片画布仍使用 1280×720。浏览器预览可以通过 CSS/JS 做自适应缩放,但导出截图必须保持 .slides-viewport 的原始 1280×720 尺寸。
  • 每次新增 layout class 后,要检查它是否覆盖 .content{height:600px}。如果直接把 .grid-* 用在 .content 上,必须补 .content.grid-*{height:600px} 防止内容压到 footer。
  • 高保真导出脚本激活页面时不要写 slide.className = 'slide active',否则会丢失 cover 等特殊 class。应使用 classList.remove('active','exit-left')classList.add('active')
  • PowerShell 执行带空格路径的 Python 时必须用调用运算符:& "c:/path with spaces/.venv/Scripts/python.exe" script.py
  • 如果 PPT 文件可能正被 PowerPoint 打开,优先输出到新文件名,避免 PermissionError

Read the full file on GitHub · 1,209 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 1,209 lines · 76 tokens per session scan A 869fb2cc7afa

Subscribe to this mod's changes

doa-ppt is a skill published in the GitHub repository medalsoftchina/workcopilot (4 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 19,530 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

converting-files

Convert a file from one format to another inside the container — documents, images, audio, video. Routes to the right engine (pandoc, LibreOffice, ImageMagick, ffmpeg) by format pair. Triggers on "convert X to Y", "turn this docx into a pdf", "make a gif from this mp4", "md to docx", "batch-convert these images", or…

oaustegard/claude-skills · 134 tokens

deck-studio

A Chinese-language workflow for producing presentation decks, slide outlines, speaker notes, visual page drafts, and infographics.

staruhub/ClaudeSkills · 219 tokens

presentations

Use when creating or editing slide decks (.pptx). Covers slide structure, using layouts and templates correctly, charts and images, speaker notes, and building a deck that communicates rather than decorates.

nimadorostkar/Claude-Skills-collection · 42 tokens

ppt-roadshow-generator

A tool that turns documents into complete roadshow videos for product launches or company presentations. The videos can include voice-over, subtitles, and transition animations across 15 to 100 pages.

anbeime/skill · 75 tokens

kelly-ppt-factory

A project workspace for producing many PowerPoint presentations with a consistent visual style. It plans slides as reviewable cards, generates PPTX files, and renders them for quality checks.

mr-kelly/skills · 117 tokens

mckinsey-deck

Turn any content into a top-tier McKinsey-style deck — a 1280×720 page-turning HTML presentation that also prints to a clean per-slide PDF. Use when the user wants a "McKinsey-style deck / presentation", a polished slide deck or PDF from notes/content, an executive/board/investor deck, or to "make slides / a deck / a…

norahe0304-art/30x-mckinsey-research-deck · 119 tokens