This folder is an Agent Skill-style bundle for AI coding assistants: structured instructions (SKILL.md), a pipeline reference (pipelines.md), helper scripts under scripts/, and an evaluator for conversion quality.
It complements the official Docling documentation and the docling CLI; use it when you want agents to follow a consistent convert → export JSON → evaluate → refine workflow.
The same layout is published in the Docling repo at docs/examples/agent_skill/docling-document-intelligence/ (for docs and PRs).
| Path | Purpose |
|---|---|
SKILL.md |
Full skill instructions (pipelines, chunking, evaluation loop) |
pipelines.md |
Standard vs VLM pipelines, OCR engines, API notes |
EXAMPLE.md |
Installing into ~/.cursor/skills/; running scripts |
improvement-log.md |
Optional template for local “what worked” notes |
scripts/docling-convert.py |
CLI: Markdown / JSON / RAG chunks |
scripts/docling-evaluate.py |
Heuristic quality report on JSON (+ optional Markdown) |
scripts/requirements.txt |
Minimal pip deps for the scripts |
pip install -r scripts/requirements.txt
python3 scripts/docling-convert.py https://arxiv.org/pdf/2408.09869 --out /tmp/out.md
python3 scripts/docling-convert.py https://arxiv.org/pdf/2408.09869 --format json --out /tmp/out.json
python3 scripts/docling-evaluate.py /tmp/out.json --markdown /tmp/out.mdUse --pipeline vlm-local or --pipeline vlm-api for vision-model pipelines; see SKILL.md and pipelines.md.
MIT (aligned with Docling).