Menu
Extract text and structured data from images and PDFs using OpenAI Vision
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Merge a GitHub pull request, merge when green, use a merge queue, or decide whether a pull request is mergeable. Use only for explicit merge intent, not ordinary review.
Run hosted browser automation and page extraction through the Skills runtime.
Run hosted deep research with parallel search, synthesis, citations, source notes, and downloadable report artifacts.
Generate images using OpenAI, Minimax, or Gemini through the hosted Skills runtime with provider-cost pricing.
Create and manage grouped tmux sessions where each session focuses on its own window and its own folder. Knows workspace layout, naming conventions, and both multi-project and multi-agent patterns.
Transcribe audio, video, YouTube, Vimeo, and generic media URLs with iapp-transcriber or the hosted Skills runtime. Supports OpenAI GPT-4o transcription, OpenAI diarization, ElevenLabs Scribe v2, DeepGram, chunking, source metadata, subtitles, and JSON outputs.
| name | extract |
| description | Extract text and structured data from images and PDFs using OpenAI Vision |
Extract text, data, and structured content from images and PDF documents using OpenAI Vision.
# Extract text from an image
bun run src/index.ts extract --input ./receipt.png --output ./receipt.txt
# Extract as Markdown from a PDF
bun run src/index.ts extract -i ./document.pdf -o ./document.md -f markdown
# Extract with custom prompt
bun run src/index.ts extract \
--input ./invoice.png \
--format json \
--prompt "Extract invoice number, date, total amount, and line items"
# High-detail extraction for small text
bun run src/index.ts extract \
--input ./handwriting.jpg \
--detail high \
--format text
| Option | Short | Description |
|---|---|---|
--input | -i | Input file path (required) |
--output | -o | Output file path (optional) |
--format | -f | Output format: text, markdown, json |
--prompt | -p | Custom extraction prompt |
--model | -m | OpenAI model (default: gpt-4o) |
--detail | -d | Image detail: low, high, auto |
export OPENAI_API_KEY="your-openai-key"
bun run src/index.ts extract \
--input ./receipt.jpg \
--format json \
--prompt "Extract store name, date, items with prices, subtotal, tax, and total"
bun run src/index.ts extract \
--input ./report.pdf \
--format markdown \
--output ./report.md
bun run src/index.ts extract \
--input ./notes.jpg \
--detail high \
--prompt "Transcribe the handwritten text, preserving the structure"