ningzimu/codex-ppt-skill

GPT-Image-2 PPT Generator Skill for Creating Image-Based PowerPoint Presentations in Codex and Other Skill-Compatible Agents

What it solves

Codex PPT Skill is designed to transform long-form content—such as articles, reports, papers, and course notes—into visually compelling presentation slides. It solves the problem of manually designing slides from scratch by automating the outline planning, visual style selection, and slide generation process.

How it works

The tool operates as a "skill" for AI agents (like Codex, Claude Code, OpenClaw, and Hermes Agent). It follows a structured, phased workflow:

  1. Planning: The agent reads the input material and creates a detailed outline (outline.md) with titles and key points for each page.
  2. Styling: The user confirms a visual style (either from 12 built-in presets or a custom style analyzed from uploaded reference images/PDFs).
  3. Generation: The agent generates each slide as a full-page image using an image generation backend (such as gpt-image-2 or other OpenAI-compatible APIs).
  4. Assembly: A local Python script (assemble_ppt.py) compiles these images into a final .pptx file, while a separate speech.md file provides the accompanying speaker notes.

Who it’s for

  • Researchers and Students: For creating academic defense slides or project reports from papers.
  • Professionals: For business reports, product introductions, and survey summaries.
  • Educators: For converting course notes into teaching materials.
  • Technical Writers: For turning technical articles into presentation decks.

Highlights

  • Multi-Agent Compatibility: Works across various agents that support SKILL.md (Codex, Claude Code, OpenClaw, Hermes Agent).
  • Custom Style Replication: Can analyze uploaded images or PDFs to replicate specific visual elements, colors, and layouts.
  • Personal Style Library: Allows users to save successful styles to a local directory (~/.codex-ppt-skill/references/) for future reuse.
  • Integrated Speaker Notes: Automatically generates a speech.md file and embeds it into the PowerPoint notes section.
  • Image-Based Approach: Focuses on high-visual impact "full-page image" slides rather than editable text boxes, ensuring consistent professional aesthetics.
  • Flexible Input: Supports a wide range of formats including Markdown, PDF, Word, and raw text.

Related

  • Project
    JuneYaooo/gpt-image2-ppt-skills

    A tool for AI agents to generate high-aesthetic PowerPoint presentations using gpt-image-2, featuring template cloning and an optional mode to convert visual slides into editable PowerPoint objects.

  • Project
    ningzimu/image-to-editable-ppt-skill

    A multi-agent AI skill that converts images, PDFs, and image-based PPTs into editable PowerPoint presentations by reconstructing text, shapes, and visual assets.

  • Project
    CRui5in/paper-ppt-agent

    An AI-powered tool that transforms academic papers (PDF/TeX) into editable PowerPoint presentations using a multi-agent pipeline for content extraction and visual design.

  • Project
    op7418/guizang-ppt-skill

    An AI agent skill for generating professional single-file HTML presentations with built-in presenter mode and two distinct high-end visual styles.

  • Project
    crazyykhllc-bit/CyberPPT

    A Codex Skill that converts business documents and research data into high-density, editable, consulting-style PowerPoint presentations using a structured analysis and blueprinting process.