transcribing-images

transcribing-images is a skill for Claude Code from oaustegard/claude-skills. It costs 151 tokens per session (1,163 once invoked), scanned A, original, MIT.

A visual transcription workflow for slides, document pages, and images, including charts, diagrams, screenshots, and scanned pages. It reads what the image shows rather than extracting only text embedded in the file.

In plain words
What is it for?
It is for transcribing or describing visually rich PPTX, PDF, and image files, including their text, charts, diagrams, and layout.
Why use it?
Text extraction can miss important content when a PDF or presentation is made from images or contains visual information.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the media-processing plugin — 6 skills shipped together

Good fit It is for transcribing or describing visually rich PPTX, PDF, and image files, including their text, charts, diagrams, and layout.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oaustegard/claude-skills/transcribing-images
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add oaustegard/claude-skills --skill transcribing-images
Clone the repo
git clone --depth 1 https://github.com/oaustegard/claude-skills

Made for: Claude Code.

Or install media-processing, the plugin that ships this one along with the rest of its 6 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for transcribing-images

README.md
[![agentmods](https://agentmods.dev/badge/skills/oaustegard/claude-skills/transcribing-images/github.svg)](https://agentmods.dev/skills/oaustegard/claude-skills/transcribing-images)
Your own site
<a href="https://agentmods.dev/skills/oaustegard/claude-skills/transcribing-images"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/transcribing-images/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for transcribing-images

Your own site · 80×15
<a href="https://agentmods.dev/skills/oaustegard/claude-skills/transcribing-images"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/transcribing-images.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,163 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00151 $0.01163
Opus 5 $0.00076 $0.00581
Sonnet 5 $0.00030 $0.00233
Haiku 4.5 $0.00015 $0.00116

Measured 2d ago against content hash 8e4f09118ecb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

transcribing-images scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/transcribe_pages.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/media-processing/skills/transcribing-images/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Transcribing Images

Read what a slide, page, or image actually shows — text plus charts, diagrams, screenshots, and layout — by rasterizing it and sending the picture to a vision model. This is the fix for the gap the built-in pptx and pdf skills leave: they extract embedded text only, so an image slide, a chart, or a scanned figure reads as empty. Visual transcription reads it the way a person looking at the slide would.

When to reach for this vs. the built-in skills

Use the pptx / pdf skills first for text-native documents — a normal deck or report where the content is real text boxes. They are faster and exact.

Switch to this skill when text extraction comes back thin or empty on a file you can see is visually rich, or whenever the meaningful content is a picture: chart, graph, diagram, screenshot, photo, scanned page, or a slide exported as one flat image. Don't guess which case you're in — if pptx/pdf returned little from a file that clearly has content, that is the signal.

The pipeline

Everything routes through scripts/transcribe_pages.py, which handles all three ingress paths and one bad page never aborts the rest:

  • .pptx / .ppt → LibreOffice headless → PDF → pdftoppm → one PNG per slide
  • .pdfpdftoppm → one PNG per page
  • image file → used directly as a single page

Each page image is then transcribed by a vision model. Run it directly:

python3 scripts/transcribe_pages.py deck.pptx                  # all slides
python3 scripts/transcribe_pages.py report.pdf --pages 3-7     # subset
python3 scripts/transcribe_pages.py slide.png --model opus     # one image
python3 scripts/transcribe_pages.py deck.pptx --json out.json  # structured

Or import transcribe_file(...) for programmatic use; it returns a list of {page, image, text, error} dicts.

Choosing the model

The transcription core and its empirical cost/recall data are reused from browsing-bluesky/scripts/image_transcribe.py — same registry, kept in sync. Pick with --model:

Read the full file on GitHub · 94 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago Changed · +2 lines 8e4f09118ecb
  2. 9d ago First seen · 92 lines · 151 tokens per session scan A 5ab2c123e2c7

Subscribe to this mod's changes

transcribing-images is a skill published in the GitHub repository oaustegard/claude-skills (148 stars, last pushed yesterday), licensed MIT. It adds 151 tokens to every session and 1,163 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

claude-students

Transforma una carpeta cruda de material de un parcial universitario (PDFs, DOC/DOCX, PPT, audios .ogg de WhatsApp, capturas) en un material de estudio polished y completo — HTML SOTA autocontenido + paquete de artefactos de NotebookLM (podcast en español, infografía, guía de estudio, briefing doc, mind map, quiz…

josuebustosn/claude-students · 234 tokens

pydicom

Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.

K-Dense-AI/scientific-agent-skills · 56 tokens

markitdown

Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.

K-Dense-AI/scientific-agent-skills · 61 tokens

open-notebook

Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and summaries, creating multi-speaker…

K-Dense-AI/scientific-agent-skills · 123 tokens

pptx-posters

Create and audit editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Use when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.

K-Dense-AI/scientific-agent-skills · 59 tokens

liteparse

Local document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; running OCR on scans; producing layout-preserved JSON for RAG; batch-ingesting folders of papers; or rendering pages to PNG for multimodal agents. Distinguishing capabilities…

K-Dense-AI/scientific-agent-skills · 86 tokens