match-structurelisted

*Split from the original match-structure (GH-291, 2026-07): the section-level driver (compare, blueprint extraction, section-by-section rewrite) moved to `match-outline`. This skill retains the quantitative metrics engine, corpus aggregation, frequency analysis, and the similarity guard that other prose skills import.* # Match structure (paragraph/sentence-level metrics) This skill provides the quantitative style measurement layer that other prose skills depend on. It profiles markdown papers at the sentence and paragraph level — distributions, passive voice, hedging, citation density, word and phrase frequencies, stock idiom usage — and aggregates those into a corpus profile. It also provides the similarity plagiarism guard used by `match-outline`'s rewrite mode and `match-voice`'s verify step. ## Where things live - **Corpus:** `<db-dir>/papers/*.md` — the markdown conversions fetched by `update-references`, selected via entries in `references.yaml`. Default selection is entries with `status: summarized`; pass `--all` to `style.py corpus` to include every entry with an `md_path`. - **Quantitative profile:** `<db-dir>/voice-profile.json`, written by `style.py corpus`. Regenerate only when the corpus changes. - **Voice anchors:** passage-level tf-idf retrieval from `writing-voice/` exemplars, via `voice_anchors.py`. - **Venue profiles:** `writing-voice/venues/<name>.yaml` — per-venue parameter bundles (anchor query, blueprint, targets, tell lexicon, gates) con