outline-slides
Skill129 starsChanged 7 months agoMITView on GitHub
Generate a numbered outline of presentation slides with one-sentence summaries. Looks at each slide image and produces a brief description. USE FOR: summarize slides, outline presentation, describe slide images, create slide summary.
In this repository15 other files it gives its agents.
- capture-video-framesSkill
- convert-slides-to-imagesSkill
- discussion-commenterSkill
- extract-slide-textSkill
- extract-transcriptSkill
- fetch-slidesSkill
- generate-images-maiSkill
- generate-writeupSkill
- make-revealjs-presentationSkill
- make-speaker-promo-cardsSkill
- pdf-to-markdownSkill
- review-presentationSkill
- thumbnail-of-pptxSkill
- youtube-descriptionSkill
- youtube-live-chatSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
If slide_ascii.md is available, read it and use the extracted text as ground truth for each slide's content.
- Distinctive: line 22
Look at each slide image and write a one-sentence summary describing the content of that slide.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

