Markitdown
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
Reads the visual content of slides, pages, and images the way a human would, not just their embedded text.
Install Transcribing Images
$ npx skills add oaustegard/claude-skills --skill transcribing-images -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install oaustegard/claude-skills transcribing-images --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/oaustegard/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/transcribing-images .claude/skills/transcribing-images && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "transcribing-images" agent skill from https://github.com/oaustegard/claude-skills/tree/main/transcribing-images into .claude/skills/transcribing-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "transcribing-images", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/oaustegard/claude-skills/tree/main/transcribing-imagesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add oaustegard/claude-skills --skill transcribing-images -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install oaustegard/claude-skills transcribing-images --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oaustegard/claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/transcribing-images .agents/skills/transcribing-images && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "transcribing-images" agent skill from https://github.com/oaustegard/claude-skills/tree/main/transcribing-images into .agents/skills/transcribing-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "transcribing-images", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add oaustegard/claude-skills --skill transcribing-images -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install oaustegard/claude-skills transcribing-images --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oaustegard/claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/transcribing-images .cursor/skills/transcribing-images && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "transcribing-images" agent skill from https://github.com/oaustegard/claude-skills/tree/main/transcribing-images into .cursor/skills/transcribing-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "transcribing-images", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/oaustegard/claude-skills.git --path transcribing-images--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add oaustegard/claude-skills --skill transcribing-images -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install oaustegard/claude-skills transcribing-images --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oaustegard/claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/transcribing-images .gemini/skills/transcribing-images && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "transcribing-images" agent skill from https://github.com/oaustegard/claude-skills/tree/main/transcribing-images into .gemini/skills/transcribing-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "transcribing-images", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install oaustegard/claude-skills transcribing-imagesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add oaustegard/claude-skills --skill transcribing-images -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/oaustegard/claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/transcribing-images .github/skills/transcribing-images && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "transcribing-images" agent skill from https://github.com/oaustegard/claude-skills/tree/main/transcribing-images into .github/skills/transcribing-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "transcribing-images", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add oaustegard/claude-skills --skill transcribing-images -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install oaustegard/claude-skills transcribing-images --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oaustegard/claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/transcribing-images .opencode/skills/transcribing-images && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "transcribing-images" agent skill from https://github.com/oaustegard/claude-skills/tree/main/transcribing-images into .opencode/skills/transcribing-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "transcribing-images", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
transcribing-images- GitHub stars
- 150
- Token cost
- ~1.3k tokens
- SKILL.md length
- 643 words
- Files
- 3 (incl. scripts)
- Skills in repo
- 67
- Repo updated
- First seen
- Licence
- MIT
At a glance
Reads the visual content of slides, pages, and images the way a human would, not just their embedded text.
- PDF has image slides
- SKILL.md covers When to reach for this vs. the…, The pipeline, Choosing the model and OCR fallback (tesseract), plus 2 more sections
- Runs Python scripts from its folder; calls python3
- Scanned figures
What it does
Transcribing Images is an agent skill from oaustegard/claude-skills. Reads the visual content of slides, pages, and images the way a human would, not just their embedded text. Use when a PPTX or PDF has image slides, screenshots, charts, scanned figures, or flattened-to-image layouts that the built-in pptx/pdf skills read as empty; when asked to transcribe, describe, OCR, or extract what is shown in an image, slide deck, or document page; or when embedded-text extraction returned little or nothing from a visually rich file. Triggers on 'read this deck', 'what's on these slides'…
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `CHANGELOG.md` and `scripts/transcribe_pages.py`).
It sits in Documents & Office, covering Slides and decks, Transcription and PowerPoint presentations. It works with Microsoft PowerPoint. The repository describes itself as: My collection of Claude skills. The licence is MIT.
When your agent uses it
- PDF has image slides
- Scanned figures
- Flattened-to-image layouts that the built-in pptx/pdf skills read as empty
- Asked to transcribe
Example prompts
- “read this deck”
- “s on these slides”
- “transcribe”
- “/transcribing-images”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 90b0f1b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Transcribing Images loads about 1.3k tokens when it runs. Until then it costs about 164 tokens; SKILL.md has 643 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from oaustegard/claude-skills at commit 90b0f1b, republished under its MIT licence (© oaustegard). 643 words, ~1,307 tokens.
Download SKILL.mdSave it as
.claude/skills/transcribing-images/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- transcribing-images
- description
- Reads the visual content of slides, pages, and images the way a human would, not just their embedded text. Use when a PPTX or PDF has image slides, screenshots, charts, scanned figures, or flattened-to-image layouts that the built-in pptx/pdf skills read as empty; when asked to transcribe, describe, OCR, or extract what is shown in an image, slide deck, or document page; or when embedded-text extraction returned little or nothing from a visually rich file. Triggers on 'read this deck', 'what's on these slides', 'transcribe', 'OCR', 'extract text from image', 'describe this chart/diagram', .pptx/.pdf/.png/.jpg with visual content.
- metadata.version
- 0.2.0
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.pdf→pdftoppm→ 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 # structuredOr 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:
gemini-lite(default) — cheapest and fastest, ~95% token recall on dense screenshots. Right for routine deck reading.gemini-flash— token-perfect, ~3x the cost. Use when exact text matters.gemini-3.5-flash— heavier reasoning alongside transcription, ~19x cost. Use when a page needs interpretation, not just reading. Checkinvoking-gemini's model table for the current frontier Flash before assuming this is still the strongest reasoning tier available.opus— for interactive sessions where you want the reading in your own context anyway.haiku— only if constrained to single-vendor Anthropic; weak at dense transcription (tends to summarize instead of transcribe). That finding is from Haiku 4.5; the alias now resolves toclaude-haiku-5-5and has not been re-measured.
Default to gemini-lite and escalate only when recall or reasoning demands it.
Show full SKILL.md (252 more words)Show less
OCR fallback (tesseract)
Tesseract 5.x is installed (eng + osd language packs only) and is exposed
as --engine tesseract. It returns glyphs, not a reading — no chart
interpretation, no diagram description, no layout meaning. Use it only for
pages you already know are plain scanned text, when you want a zero-cost,
fully-offline pass. For anything with a chart, diagram, or visual layout, the
vision path is the correct tool; tesseract on those pages will quietly lose the
content that mattered.
When the deliverable is a file rather than a reading, use ocring-pdfs instead.
It installs ocrmypdf at runtime (~18s) and writes the OCR back as an invisible
text layer over the original page images, so the output is a PDF that
pdftotext and grep can read. The --engine tesseract path here returns
loose text with no page anchoring.
Interactive shortcut
In an interactive session you can often skip the model call entirely:
rasterize with scripts/transcribe_pages.py … --json to get the page PNGs, or
just convert and view each page image yourself — Claude reads images natively.
The script's vision-model path exists for batch and autonomous runs where no
human-in-loop reader is available, or when a deck has more pages than is
practical to view one by one.
DPI
Default raster is 150 DPI — legible for a vision model and safely under the
5 MB/image base64 ceiling. Bump to --dpi 200–300 only for pages with dense
small fonts; higher DPI risks exceeding the per-image size limit and costs more
tokens for no gain on normal slides.
© oaustegard, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (scripts) in transcribing-images of oaustegard/claude-skills.
- SKILL.md
- CHANGELOG.md
- scripts/transcribe_pages.py
Open the folder on GitHubat commit 90b0f1b
Compare with similar skills
Transcribing Images next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Transcribing Images this skilloaustegard/claude-skills | 150 | — | ~1.3k | Automated safety check: Pass | MIT | |
| MarkitdownImCa0/just-laws | 781 | 14 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Paper Deckzsyggg/paper-craft-skills | 1.3k | — | ~1.4k | Automated safety check: Pass | None | |
| Markitdownjimmc414/Kosmos | 595 | 2 repos | ~1.7k | Automated safety check: Pass | None | |
| Paper2slidesQuZhan51496/paper2anything | 450 | — | ~3.8k | Automated safety check: Notes | Apache-2.0 | |
| Ky Markdown RebuilderKyrieCheungYep/ky-markdown-rebuilder | 117 | — | ~5.7k | Automated safety check: Pass | None |
Similar skills
Paper Deck
zsyggg/paper-craft-skills
将论文、技术文章或知识内容制作成高真实感的 AIGC 幻灯片。先做叙事结构和逐页视觉导演，再调用生图模型生成每一页 16:9 slide image，最后合成为 PPTX/PDF。适合论文汇报、组会、公开课、技术分享、商业化研究展示；当用户提到“论文PPT”“AI生成PPT”“不像AI的PPT”“高质感幻灯片”“逐页生图PPT”时使用。
Markitdown
jimmc414/Kosmos
Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing.
Paper2slides
QuZhan51496/paper2anything
Turn an academic paper PDF into a presentation deck (.pptx) end-to-end.
Ky Markdown Rebuilder
KyrieCheungYep/ky-markdown-rebuilder
Rebuild visual documents into reliable Markdown by combining text extraction with page or screenshot alignment.
Sci HTML
ShZhao27208/Aut_Sci_Write
Generate academic presentation-style HTML slide decks and browser reports from PDFs, structured text, Markdown, paper summaries, outlines, or research notes.
More from oaustegard/claude-skills
All 67 skills in this repoVega-Lite Interactive Charts
oaustegard/claude-skills
Builds interactive Vega-Lite charts from uploaded data: analyzes the fields, picks five to ten fitting chart types, and produces a React artifact with the data embedded inline.
Single-File HTML Composer
oaustegard/claude-skills
Builds self-contained single-file HTML pages such as reports, decks, postmortems, flowcharts and prototypes from a small spec using a bundled Python composer and templates.
Deciding With Confidence
oaustegard/claude-skills
Routes, triages, flags and rates a piece of text with a probability for every option: which department or queue a ticket goes to, which intent a message expresses, whether a yes/no condition holds…
Declauding
oaustegard/claude-skills
Rewrites model-sounding prose into plain technical writing and checks that every claim survives, for PR text, docs, commit messages and similar drafts.
Preact Developer
oaustegard/claude-skills
Guides building standards-based Preact apps with native-first choices, HTM syntax, import maps and vendored ESM, from single-file demos to larger builds.
Bluesky Zeitgeist Sampler
oaustegard/claude-skills
Deprecated sampler that captures short windows of the Bluesky firehose, clusters trending terms and builds an HTML report; replaced by the browsing-bluesky skill.
Related
Works with
Categories
Questions about Transcribing Images
What does Transcribing Images do?
Reads the visual content of slides, pages, and images the way a human would, not just their embedded text. Transcribing Images is an agent skill from oaustegard/claude-skills. Reads the visual content of slides, pages, and images the way a human would, not just their embedded text.
When should I use Transcribing Images?
Transcribing Images fits situations like: PDF has image slides; scanned figures; flattened-to-image layouts that the built-in pptx/pdf skills read as empty; asked to transcribe.
How do I install Transcribing Images in Claude Code?
Run `npx skills add oaustegard/claude-skills --skill transcribing-images -a claude-code`. Or copy the skill folder (transcribing-images in oaustegard/claude-skills) into .claude/skills/transcribing-images in your project. Claude Code loads it when a task matches its description.
How do I install Transcribing Images in Codex?
Run `npx skills add oaustegard/claude-skills --skill transcribing-images -a codex`. Or copy the skill folder (transcribing-images in oaustegard/claude-skills) into .agents/skills/transcribing-images in your project. Codex loads it when a task matches its description.
Can I use Transcribing Images in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add oaustegard/claude-skills --skill transcribing-images -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/transcribing-images, .gemini/skills/transcribing-images, .github/skills/transcribing-images and .opencode/skills/transcribing-images in your project.
What does Transcribing Images need to run?
Going by SKILL.md and its folder, Transcribing Images needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Transcribing Images access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Transcribing Images safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Transcribing Images use?
Transcribing Images is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Transcribing Images use?
About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Transcribing Images?
Skills that share tags, products or a category with Transcribing Images: Markitdown (ImCa0/just-laws, 781 stars), Paper Deck (zsyggg/paper-craft-skills, 1.3k stars), Markitdown (jimmc414/Kosmos, 595 stars) and Paper2slides (QuZhan51496/paper2anything, 450 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Transcribing Images?
oaustegard (a GitHub user) maintains it in oaustegard/claude-skills, which has 150 GitHub stars. The repository holds 67 skills in this directory. The repository was last updated on October 9, 2026.
Source: oaustegard/claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.