benchmark-comparelisted

# Benchmark Compare Compare the user's current page against benchmark-backed patterns. This is more diagnostic than `find-examples` and more concise than `improve-page`. ## Output Behavior Write: - `.webanatomy/benchmark-compare/{target}-{YYYY-MM-DD}/report.md` - `.webanatomy/benchmark-compare/{target}-{YYYY-MM-DD}/report.html` - `.webanatomy/benchmark-compare/{target}-{YYYY-MM-DD}/references/` The HTML report is the primary visual output. Chat is only a short summary and pointer to the saved files. If the user asks for a fast answer, still produce a concise saved report when possible. ## Deterministic Report Renderer When file access is available, do not hand-write the final HTML. Write structured report data first: - `.webanatomy/benchmark-compare/{target}-{YYYY-MM-DD}/report-data.json` Then run the shared renderer from this skill pack: ```bash node <skill-dir>/scripts/render-report.mjs --input=.webanatomy/benchmark-compare/{target}-{YYYY-MM-DD}/report-data.json ``` Resolve `<skill-dir>` relative to this `SKILL.md`. The renderer validates the report data, downloads every `screenshotUrl` into `references/`, writes `report.md`, writes `report.html`, and renders "screenshot unavailable" when no screenshot exists. Use this report-data shape: - `title`, `summary`, optional `eyebrow`, `subtitle`, `target` - `currentSnapshot`: `{ "label": "...", "text": "..." }[]` - `references`: `{ "title": "...", "company": "...", "section": "...", "sourceUrl": "...", "screenshotUr