Generates a numbered list of one-sentence summaries for each slide in a presentation by analyzing slide images and optional extracted text. It produces a concise textual outline of the visual content.
Quality gate: FAIL · makes it possible · measured 2026-10-24 Delivered a valid file in 0 of 2 requests; the bare model cannot produce this file type. 0/2 requests produced a file that opens
Security scan: clean · 2026-10-24 · 1 files · ran in sandbox no network calls, shell tricks, credential access or instruction tampering found in its files.
Try asking
Say it in your own words; the assistant finds this recipe by itself. Examples:
“Lav en nummereret oversigt over slides i mappen ./min_praesentation/.”
“Sammenfæt hvert slide i /data/slides/ med én sætning.”
“Jeg har konverteret mine slides til billeder. Kan du beskrive indholdet af hvert billede kort?”
“Please create a numbered outline of the slides in the folder ./deck_images/.”
“Summarize each slide in my presentation located at /home/user/pptx_output/ with one sentence.”
“I have the slide images ready. Can you generate a brief description for each one?”
Try this skill from Claude, ChatGPT or a chat on your own page. Free plan, no credit card.Get started free
Do not use this if you need to edit the slides, extract raw text for OCR purposes, or convert slides to PDF. For full-text extraction, use the extract-slide-text skill; for converting PDFs to images, use convert-slides-to-images.
Details
When it is the right choice
Use this skill when you have a set of slide images (e.g., slide_1.png) and need a quick textual overview of the presentation's flow. It is ideal for creating a high-level summary or table of contents from visual slide data. It works best when combined with extracted text to ensure accuracy of content descriptions.
The full recipe the assistant reads
Outline slides
Generate a numbered outline of all slides with one-sentence summaries per slide.
Input
A directory containing slide images named slide_1.png, slide_2.png, etc. (produced by the convert-slides-to-images skill).
Optionally, a slide_ascii.md file containing extracted text per slide (produced by the extract-slide-text skill).
Procedure
Find all *slide_.png files in the specified directory, sorted numerically by slide number.
If slide_ascii.md is available, read it and use the extracted text as ground truth for each slide's content. This prevents misidentifying embedded screenshots or demo captures as actual slide content.
Look at each slide image and write a one-sentence summary describing the content of that slide. When slide_ascii.md is available, base the summary primarily on the extracted text, using the image only for visual context (diagrams, screenshots, etc.).
Output a numbered list matching the slide numbers.
For large presentations (more than 50 slides), work through the slides in batches of 50.
Output format
1. Title slide introducing the presentation on [topic]
2. Agenda slide listing the main sections to be covered
3. Diagram showing the architecture of [system]
4. Code example demonstrating [technique]
...
Example usage
To outline slides that have already been converted to images:
Please outline the slides in presentations/my-talk/outputs/slide_images/
Save the output to outputs/outline.txt in the presentation folder for caching.
Files in this skill (2)
LICENSE
SKILL.md
Where it comes from
Vendored from pamelafox/presentation-skills, commit 2b809b3a8d2f, path .agents/skills/outline-slides, licence MIT. The upstream licence file ships inside the skill.