pdf-to-mdlisted

# pdf-to-md Turn a PDF into Markdown. The right path depends on **what the document is** and **whether an OCR API key is available**: - **Scientific paper** → produce the canonical `paper-to-md` bundle (Markdown + `section_audit.json` + `article.json`) so it can feed `csag-extraction`. Convert with the **OCR API** when a key is set, else **LiteParse v2** locally. - **Any other PDF** (reports, slides, letters, forms) → just convert to Markdown with **LiteParse v2** for a fast, local, no-key result. Stop there. **LiteParse must be v2** ([run-llama/liteparse](https://github.com/run-llama/liteparse), the Rust rewrite with the `LiteParse` Python API and `lit` CLI). LiteParse v1 is a different, unsupported API. `liteparse_to_md.py` pins `liteparse>=2,<3` and refuses to run on anything else, so `uv run` always provisions the right per-platform v2 binary inside the wheel — nothing to vendor or compile, and no API key. OCR is on by default (bundled Tesseract). **LiteParse output is a draft, not the deliverable.** LiteParse is a *mechanical* parser: it has no native Markdown, infers headings from font size/weight, and introduces artifacts (split words, broken hyphenation, dropped author blocks, merged columns). Whenever LiteParse is the engine, the LLM running this skill is responsible for shaping that draft into the right form — see "Shape the LiteParse output" below. The OCR API engine needs far less shaping. ## Instructions ### Step 0 — Classify the document and pick a p