# pptx

Adopt this skill: https://proskills.md/skills/other/pinvou-pinvou-agent-pinvou3-app-src-tauri-resources-common-skill-marketplace-ppt

Page: https://proskills.md/skills/other/pinvou-pinvou-agent-pinvou3-app-src-tauri-resources-common-skill-marketplace-ppt
This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required.

## File: pinvou3-app/src-tauri/resources/common/skill-marketplace/pptx/SKILL.md
size: 2007
sha: 799c9a92c7e148d52e5fbe1f7b42f0d4031addca
upstream: https://github.com/pinvou/pinvou-agent/blob/main/pinvou3-app/src-tauri/resources/common/skill-marketplace/pptx/SKILL.md

```text
---
name: pptx
description: 本地直出可编辑 PowerPoint（.pptx）：用户要做 PPT / 幻灯片 / 演示文稿 / 汇报 / 方案时使用。先列大纲确认，再产结构化 deck 并按内容自动选主题，调 mcp_pptx_make_pptx 生成，产物必须上产物卡。
---

# PPT 生成

本地生成可编辑 .pptx：模型产结构化大纲，渲染器套主题模板生成，真·可编辑图表，自带封面缩略图，数据不出机。

## 流程（严格按序）

1. **先列一版大纲**（章节 + 每页要点）给用户确认/修改
2. 确认后产结构化 deck：封面 / 目录 / 章节 / 要点 / 双栏 / KPI / 图表 / 表格 / 配图 / 结尾
3. **按 PPT 内容自动选一套主题**（business-blue / tech-dark / gov-red / creative-purple / fresh-green / warm-orange / navy-gold / minimal-mono / midnight），并一句话说明理由，用户可改
4. 调 `mcp_pptx_make_pptx` 生成 .pptx（连接器工具默认延迟加载：工具列表里没有它时先 `tool_search` 激活；`tool_search` 返回 `mcp_boot` connecting（MCP 服务仍在启动）就等待数秒重试，connecting 消失后仍搜不到，才说明『PPT 生成』连接器未安装——按下方「严格禁止」处理，不要硬拼成品）
5. 拿到 path 后**必须再调 `mcp_pinvou3_present_artifact(path, title)`** 上产物卡（普通模式的产物工具会在后端健康时随会话加载：工具列表里没有它时先 `tool_search` 激活；`tool_search` 返回 `mcp_boot` connecting（MCP 服务仍在启动）就等待数秒重试，connecting 消失后仍搜不到，才算产物卡后端本轮不可用——直接交付并在回复里说明产物卡不可用）

## 严格禁止

- 全程**不要用 HTML 代替** .pptx
- 没点名平台时默认本地生成，**不要用飞书/在线文档代替**——只有用户明确说"做成飞书文档 / 发到飞书"才走飞书技能

## 环境说明

首次安装 MCP 部分会自动下载 python-pptx 依赖（需联网）。
```

## File: README.md
upstream: https://github.com/pinvou/pinvou-agent/blob/main/README.md

````text
<div align="center">

<img src="pinvou3-app/src-tauri/icons/icon.png" alt="Pinvou Agent logo" width="120" />

# Pinvou Agent

**An open-source desktop AI agent workspace for work, design, and coding.**

[English](README.md) · [简体中文](README.zh-CN.md) · [日本語](README.ja.md)

[![CI](https://github.com/Pinvou/pinvou-agent/actions/workflows/pr-check.yml/badge.svg)](https://github.com/Pinvou/pinvou-agent/actions/workflows/pr-check.yml)
[![License: MIT](https://img.shields.io/github/license/Pinvou/pinvou-agent)](LICENSE)
[![Version](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fraw.githubusercontent.com%2FPinvou%2Fpinvou-agent%2Fmain%2Fpinvou3-app%2Fpackage.json&query=%24.version&label=version&color=blue)](pinvou3-app/package.json)
[![Platform](https://img.shields.io/badge/platform-Windows%20%7C%20macOS%20%7C%20Linux-lightgrey)](#-quick-start)
[![GitHub Stars](https://img.shields.io/github/stars/Pinvou/pinvou-agent?style=flat)](https://github.com/Pinvou/pinvou-agent/stargazers)

[Download Preview](https://github.com/Pinvou/pinvou-agent/releases) · [Website](https://pinvou.com/) · [QQ Group](#-community--security) · [Issues](https://github.com/Pinvou/pinvou-agent/issues) · [Discussions](https://github.com/Pinvou/pinvou-agent/discussions) · [Security](SECURITY.md)

<p align="center">
  <a href="https://pinvou.com/assets/videos/pinvou-agent-feature-update-2026-07.mp4">
    <img src="docs/assets/screenshots/mode-work.webp" alt="Pinvou Agent Work mode">
  </a>
</p>
<p align="center">
  <a href="https://pinvou.com/assets/videos/pinvou-agent-feature-update-2026-07.mp4"><strong>▶ Watch the 90-second feature demo (Chinese)</strong></a>
</p>

</div>

Pinvou Agent is more than a chat window. It brings everyday work, visual design, and software development into one desktop workspace — designed for tasks that should end with **a result**, not just another chat response. Use tools, work with files, and build personal knowledge; bring a dedicated coding agent into a real project over ACP; or turn a prompt into a visual artifact you can continue editing.

Use a local model for a fully private loop, connect any OpenAI-compatible endpoint, and extend the agent with MCP servers, CLI connectors, Skills, and workflows.

## 🧭 One workspace, three ways to work

### 💼 Work: give the agent a real task

Combine attachments, personal knowledge, specialist personas, Skills, MCP tools, and workflows to research, analyze, write, and deliver reusable files — not just another block of chat text.

### 🎨 Design: from a prompt to an editable visual

Create posters and data visualizations in natural language. Open the result in design mode, select elements directly, and adjust copy, fonts, colors, dimensions, and layout — or keep describing changes and let the agent iterate on the current design.

### 💻 Code: bring a coding agent into a real project

Use **Codex, Claude Code, or Kimi** through [ACP](docs/multi-agent-acp.md) in the same desktop workspace. The coding agent can read and edit a real project or an isolated temporary workspace, run commands, and surface plans, tool steps, permission requests, and file changes. Sessions stay bound to their workspace and can be continued after restarting the app.

## ✨ Features

### 🎯 From conversation to deliverables

- **Multi-session workspace** with title search — messages, tool calls, and artifacts persist with each session
- **Attachments** for PDF, Office documents, images, and text — drag, drop, or paste them in
- **Artifact panel** automatically collects every file the agent creates or edits; preview, locate, and open them in one place
- **Editable Markdown artifacts** — edit directly, or select a passage and ask the agent to revise it
- **Plan / YOLO modes** — review the plan first for complex work, or execute directly when the task is clear
- **Auxiliary chat** — ask side questions while a task runs, in a per-task side session whose only tool is a server-enforced read-only view of that task's own history (ADR-0024), isolated from the task's execution context

### 🧠 Knowledge and memory

- **Local knowledge base** with file management, full-text and vector retrieval; attach multiple collections to one chat, enable or disable each independently, and retain collection and file provenance in answers
- **Memory center** captures long-term preferences and context, with explicit candidate review and confirmation
- **Persona card pool** — create, save, and apply specialist roles for different domains
- **Skills, Commands, and workflows** turn proven methods into stable, reusable capabilities

### 🔌 Real tools and connectors

- **Unified tool store** for local MCP servers, remote MCP servers, CLI tools, and API connectors
- **OAuth / SSO authorization** where supported — no manual key pasting
- Ready-made connectors for **Feishu (Lark), DingTalk, WeCom, Tencent Meeting, Tencent Docs, Tencent ima, Obsidian**, plus QCC, PatSnap, Canva, AMap Weather, and more
- **Remote control** — scan a QR code from your phone to view and steer the running workspace

### 🖥️ Built for daily operation

- **Windows system tray** — closing the main window keeps it running in the notification area; click the tray icon to return, or right-click → Exit to quit ([details](docs/windows-system-tray.md))
- **Global bring-to-front shortcut** (off by default, `Ctrl/Cmd+Alt+P`) — enable it in Settings → General to summon the window with a key while it runs in the background
- **Local voice input** with on-demand speech model downloads
- **Centralized monitoring** of GPU, memory, disk, model service, and context usage
- **Updates via GitHub Releases** — in-app update checks are not enabled yet
- Sessions, settings, knowledge, and runtime extensions all live under `~/.pinvou3/`

> [!NOTE]
> Whether data leaves your machine depends on the model and tools you enable. A local model with local tools stays fully local. Cloud models, remote MCP servers, and third-party connectors send the relevant requests to their respective services.

## 📸 Screenshots

<table>
  <tr>
    <td width="50%"><img src="docs/assets/screenshots/mode-design.webp" alt="Pinvou Agent Design mode"></td>
    <td width="50%"><img src="docs/assets/screenshots/mode-code.webp" alt="Pinvou Agent Code mode"></td>
  </tr>
  <tr>
    <td align="center">Design mode for posters and data visualizations</td>
    <td align="center">Code mode with Codex, Claude Code, and Kimi</td>
  </tr>
  <tr>
    <td width="50%"><img src="docs/assets/screenshots/tool-store.webp" alt="Pinvou Agent tool store"></td>
    <td width="50%"><img src="docs/assets/screenshots/artifacts-preview.webp" alt="Pinvou Agent artifact preview"></td>
  </tr>
  <tr>
    <td align="center">Extend the agent with tools and connectors</td>
    <td align="center">Preview and deliver generated artifacts</td>
  </tr>
</table>

## 🤖 Model Access

Pinvou Agent works with **local vLLM** and any **OpenAI-compatible API**. Save multiple model configurations in the app, give cloud configurations optional display aliases, and switch between them per session without changing the model identifier sent to the provider. Built-in templates cover local vLLM, DeepSeek, Kimi, Qwen, Doubao, MiniMax, Zhipu (GLM), MiMo, OpenAI, Anthropic, Gemini, and xAI — or fill in any custom compatible endpoint.

Local vLLM example:

```bash
export DEEPSEEK_BASE_URL="http://127.0.0.1:8000/v1"
export DEEPSEEK_API_KEY="local-no-auth"
export DEEPSEEK_MODEL="your-model-name"
```

Endpoints, model names, and API keys can also be managed directly in the application settings. For a non-loopback plain HTTP endpoint in a trusted development network, explicitly set `DEEPSEEK_ALLOW_INSECURE_HTTP=1`.

## 🚀 Quick Start

### Prerequisites

- Git with submodule support
- Node.js and npm
- A current Rust toolchain
- The [Tauri 2 system dependencies](https://v2.tauri.app/start/prerequisites/) for your platform
- An accessible OpenAI-compatible model endpoint

The source tree supports **Linux, Windows, a
````
