docs: add agent skill bundle for coding assistants (SKILL.md, pipelines, convert/evaluate)

docs/examples/agent_skill/docling-document-intelligence/EXAMPLE.md

@@ -0,0 +1,93 @@
+# Using the Docling agent skill
+
+[Agent Skills](https://agentskills.io/specification) are folders of instructions that AI coding agents (Cursor, Claude Code, GitHub Copilot, etc.) can load when relevant.
+
+## Where this bundle lives
+
+- **Cursor (local):** `~/.cursor/skills/docling-document-intelligence/` (or copy this folder there).
+- **Docling repository (docs + PRs):** `docs/examples/agent_skill/docling-document-intelligence/` in [github.com/docling-project/docling](https://github.com/docling-project/docling).
+
+The two trees are kept in sync; use either source.
+
+## Install (copy into your agent’s skills directory)
+
+```bash
+# From a checkout of the Docling repo
+cp -r docs/examples/agent_skill/docling-document-intelligence ~/.cursor/skills/
+
+# Or copy from another machine / archive into e.g. ~/.claude/skills/
+```
+
+No extra config is required beyond installing Python dependencies (below).
+
+## Usage
+
+Open your agent-enabled IDE and ask, for example:
+
+```
+Parse report.pdf and give me a structural outline
+```
+
+```
+Convert https://arxiv.org/pdf/2408.09869 to markdown
+```
+
+```
+Chunk invoice.pdf for RAG ingestion with 512 token chunks
+```
+
+```
+Process scanned.pdf using the VLM pipeline
+```
+
+The agent should read `SKILL.md`, match the task, and run the appropriate pipeline.
+
+## Running the helper scripts directly
+
+From the **bundle root** (the `docling-document-intelligence` directory):
+
+```bash
+pip install -r scripts/requirements.txt
+
+python3 scripts/docling-convert.py report.pdf
+
+python3 scripts/docling-convert.py report.pdf --ocr-engine rapidocr
+
+python3 scripts/docling-convert.py report.pdf --format chunks --max-tokens 512
+
+python3 scripts/docling-convert.py scanned.pdf --pipeline vlm-local
+
+python3 scripts/docling-convert.py doc.pdf \
+    --pipeline vlm-api \
+    --vlm-api-url http://localhost:8000/v1/chat/completions \
+    --vlm-api-model ibm-granite/granite-docling-258M
+```
+
+## Evaluate and refine
+
+```bash
+python3 scripts/docling-convert.py report.pdf --format json --out /tmp/doc.json
+python3 scripts/docling-convert.py report.pdf --format markdown --out /tmp/doc.md
+python3 scripts/docling-evaluate.py /tmp/doc.json --markdown /tmp/doc.md
+```
+
+If the report shows `warn` or `fail`, follow `recommended_actions`, re-convert,
+and optionally append a note to `improvement-log.md` (see `SKILL.md` section 6).
+
+## What the skill covers
+
+| Task | How to ask |
+|---|---|
+| Parse PDF / DOCX / PPTX / HTML / image | "parse this file" |
+| Convert to Markdown | "convert to markdown" |
+| Export as structured JSON | "export as JSON" |
+| Chunk for RAG | "chunk for RAG", "prepare for ingestion" |
+| Analyze structure | "show me the headings and tables" |
+| Use VLM pipeline | "use the VLM pipeline", "process scanned PDF" |
+| Use remote inference | "use vLLM", "call the API pipeline" |
+
+## Further reading
+
+- [Agent Skills specification](https://agentskills.io/specification)
+- [Docling documentation](https://docling-project.github.io/docling/)
+- [Docling GitHub](https://github.com/docling-project/docling)

docs/examples/agent_skill/docling-document-intelligence/README.md

@@ -0,0 +1,34 @@
+# Docling agent skill (Cursor & compatible assistants)
+
+This folder is an **[Agent Skill](https://agentskills.io/specification)**-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](https://docling-project.github.io/docling/) and the [`docling` CLI](https://docling-project.github.io/docling/reference/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).
+
+## Contents
+
+| Path | Purpose |
+|------|---------|
+| [`SKILL.md`](SKILL.md) | Full skill instructions (pipelines, chunking, evaluation loop) |
+| [`pipelines.md`](pipelines.md) | Standard vs VLM pipelines, OCR engines, API notes |
+| [`EXAMPLE.md`](EXAMPLE.md) | Installing into `~/.cursor/skills/`; running scripts |
+| [`improvement-log.md`](improvement-log.md) | Optional template for local “what worked” notes |
+| [`scripts/docling-convert.py`](scripts/docling-convert.py) | CLI: Markdown / JSON / RAG chunks |
+| [`scripts/docling-evaluate.py`](scripts/docling-evaluate.py) | Heuristic quality report on JSON (+ optional Markdown) |
+| [`scripts/requirements.txt`](scripts/requirements.txt) | Minimal pip deps for the scripts |
+
+## Quick start (from this directory)
+
+```bash
+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.md
+```
+
+Use `--pipeline vlm-local` or `--pipeline vlm-api` for vision-model pipelines; see `SKILL.md` and `pipelines.md`.
+
+## License
+
+MIT (aligned with [Docling](https://github.com/docling-project/docling)).