Percerno Skillsbeta
← everything it can do · slides

Extract Slide Text PPTX

Extracts text content from each page of a PDF file using pdftotext and writes it to a markdown file. The output includes a heading, an image reference, and the extracted text for each slide.

10 uses this weeksource pamelafoxlicence MITneeds internet for packages
Quality gate: PASS · fewer tokens, same result · measured 2026-10-23
Same outcome with 0 % fewer tokens than reading the file into the model (3 requests).
3/3 requests produced a file that opens
Security scan: clean · 2026-10-24 · 2 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:

“Træk teksten ud af min præsentation.pdf og gem den i slides.md”
“Jeg har brug for tekstindholdet fra alle slides i deck_v2.pdf til mine noter.”
“Kør tekstekstraktion på PDF'en med kvartalsrapporten.”
“Extract the text from my presentation.pdf and save it to slides.md”
“I need the text content from every slide in deck_v2.pdf for my notes.”
“Run the text extraction on the quarterly report PDF.”
Try this skill from Claude, ChatGPT or a chat on your own page. Free plan, no credit card.Get started free

Good for

pdftext-extractionmarkdownslidespdftotextparsingcontent-extraction

Not for

Do not use this skill if you need to analyze the visual layout, design, or graphical elements of the slides, as it only extracts text. It is not suitable for PDFs that are primarily scanned images without a text layer, as pdftotext will fail to extract meaningful content. Use an OCR-based skill instead if the PDF contains no selectable text.

Details

When it is the right choice

Use this skill when you need to convert the textual content of a PDF presentation into a structured markdown format. It is ideal for creating a text-based record of slides or preparing data for further text analysis. It is particularly useful when you need ground-truth text to verify slide content without relying on visual interpretation.

The full recipe the assistant reads

Extract slide text from PDF

Run the extract_slide_text.py script to extract the text content of each PDF page into a structured markdown file:

uv run .agents/skills/extract-slide-text/extract_slide_text.py <pdf_path> <output_path> [images_dir]

Arguments

  • pdf_path (required): Path to the PDF file.
  • output_path (required): Path to write the output markdown file
  • images_dir (optional): Path to the slide images directory. Used to generate correct relative image references. Defaults to slide_images/.

Output format

A markdown file with one section per slide:

## Slide 1

![Slide 1](slide_images/slide_1.png)

\```
Extracted text content from slide 1
\```

## Slide 2

![Slide 2](slide_images/slide_2.png)

\```
Extracted text content from slide 2
\```

Pages with no extractable text (e.g., full-bleed images) show (no extractable text).

Why this matters

PDF text extraction is deterministic — it produces ground-truth slide content without relying on vision models. This prevents misidentification of embedded screenshots or demo captures as actual slide content, a common failure mode when using only image-based slide analysis.

Prerequisites

Poppler utilities must be installed (provides the pdftotext command):

  • macOS: brew install poppler
  • Ubuntu: apt-get install poppler-utils
Files in this skill (3)
  • LICENSE
  • SKILL.md
  • extract_slide_text.py
Where it comes from

Vendored from pamelafox/presentation-skills, commit 2b809b3a8d2f, path .agents/skills/extract-slide-text, licence MIT. The upstream licence file ships inside the skill.