Marketplace for trusted AI agent skills

Generate Template-Matched PPTX Decks with gpt-image2-ppt-skills

Skill Detail

Generate Template-Matched PPTX Decks with gpt-image2-ppt-skills

Use gpt-image2-ppt-skills to have an agent create image-first or editable PowerPoint decks with gpt-image-2, bundled styles, template cloning, and render review.

Image & Creative AutomationMulti-Framework
Image & Creative Automation Multi-Framework Security Reviewed
⭐ 1.1k GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill generate-template-matched-pptx-decks-with-gpt-image2-ppt-skills Copy
Works best when you want a reusable capability, not another fragile one-off prompt.
View source Documentation
At a glance
Tools required
Claude Code, Codex, OpenClaw, Cursor, Hermes Agent, or another skill-capable agent; Git; Python 3.8 or later; pip; OpenAI gpt-image-2 access or compatible agent-native image generation; optional PowerPoint, Keynote, or LibreOffice renderer for template cloning and editable-mode validation
Install & setup
Clone `https://github.com/JuneYaooo/gpt-image2-ppt-skills`, run `bash install_as_skill.sh –target claude` for Claude Code or `bash install_as_skill.sh –target codex` for Codex, install the Python requirements through the script, configure image-generation access only when the active agent does not provide native image generation, then restart the agent so the skill loads.
Author
JuneYaooo
Publisher
Open Source Project
Last updated
Jul 30, 2026
Quick brief

Use gpt-image2-ppt-skills to install the deck-generation skill, select a style or analyze a provided template, plan slides, generate high-resolution page images with gpt-image-2, package them into a 16:9 PPTX, and optionally rebuild text and graphics as editable PowerPoint objects with local render checks. The workflow includes visual confirmation, asset output, and renderer-backed review when template cloning or editable delivery depends on local Office, Keynote, or LibreOffice behavior.

How it works

What this skill actually does

What the agent/operator does

When to invoke

Invoke this skill when a user wants a finished presentation deck from natural-language content, needs a new deck to follow an existing PPTX template, or explicitly needs editable PowerPoint output that an agent can render and visually verify before delivery.

Scope boundary

This is not a generic OpenAI image API listing or a presentation product card. Keep the workflow bounded to agent-driven PPTX generation: install the skill, gather deck requirements or template input, choose the visual mode, generate and review slide outputs, and return the PPTX plus rendered assets.