Menu
Extract tables, forms, invoices, and semi-structured PDF content into CSV and JSON datasets through the hosted Skills runtime.
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 | pdf-to-dataset |
| description | Extract tables, forms, invoices, and semi-structured PDF content into CSV and JSON datasets through the hosted Skills runtime. |
Convert PDF content into structured datasets and extraction reports. The implementation runs through the hosted Skills runtime, so agents get the instruction file and generated artifacts without receiving parser source, scripts, or model code.
dataset.json, dataset.csv, schema.json, extraction-report.md, and manifest.json.skills run pdf-to-dataset -- --input ./invoice.pdf --schema "invoice_number,date,total,vendor"
skills run pdf-to-dataset -- --input ./reports --mode tables --output ./exports/pdf-data
| Option | Description | Default |
|---|---|---|
--input <path-or-url> | PDF file, folder, or URL | required |
--schema <fields> | Comma-separated field hints | inferred |
--mode <mode> | tables, forms, invoice, or auto | auto |
--output <dir> | Output directory | current run export directory |
--pages <ranges> | Page ranges like 1-3,8 | all pages |
skills auth login.skills mcp --register all