Update to Kismet

{
  "name": "kismet-reviews-fit",
  "description": "Judging fit from guest reviews on Kismet. Use whenever the guest asks whether a property suits them or their group — \"good for couples?\", \"is it quiet?\", \"how is it in October?\", \"what do people say?\", \"will our dog be happy there?\" — and whenever you are recommending between finalists, even if the guest never says the word \"reviews\". Covers persona and season filtering, empty-filter fallback, reading for fit signals, and honest expectation-setting.",
  "included_files": [
    {
      "relative_path": "assets/icon.png",
      "size_in_bytes": 18919
    }
  ],
  "skill_md_contents": "---\nname: kismet-reviews-fit\ndescription: Judging fit from guest reviews on Kismet. Use whenever the guest asks whether a property suits them or their group — \"good for couples?\", \"is it quiet?\", \"how is it in October?\", \"what do people say?\", \"will our dog be happy there?\" — and whenever you are recommending between finalists, even if the guest never says the word \"reviews\". Covers persona and season filtering, empty-filter fallback, reading for fit signals, and honest expectation-setting.\n---\n\n# Kismet Reviews & Fit\n\nStar averages answer nothing. \"Will this work for US, THEN\" is the question —\nanswer it with filtered evidence.\n\n## Filter to the guest's situation\n\n- `get_bookable_reviews` takes `persona` (family, couples, solo…) and\n  `season` (winter/spring/summer/fall). \"Good for couples in October?\" →\n  persona=couples first, then season=fall. Cite what those guests actually\n  said, not the global average.\n- **Empty-filter fallback:** a filtered call can return the headline count\n  with zero review texts — that means the filter matched nothing, NOT that\n  reviews are unavailable. Retry unfiltered before concluding anything, and\n  say what you did (\"no fall-specific reviews; overall, guests say…\").\n- Recency matters: default sort is newest — prefer recent texts when the\n  property may have changed (renovations, new hot tub, new management).\n\n## Read for fit signals, not sentiment\n\nScan review texts for the things averages hide: noise and neighbors, stairs\nand accessibility, wifi quality (working trips), bed comfort, host\nresponsiveness, parking, how \"cozy\" maps to square feet. Match signals to\nTHIS guest: a couple doesn't care that the bunk room sleeps four.\n\n## Honest expectation-setting\n\n- Surface known quirks as expectation-setting, not deal-killers: a rustic\n  property's wildlife/pest policy, quiet hours, wood-stove heating, gravel\n  roads. Guests forgive what they were told about.\n- Don't launder negatives. If a recent review mentions an issue (e.g. a\n  cracked stove the host accommodated), you may weigh it as minor — but if\n  the guest asks about that dimension, report it.\n- The property description is marketing; policies and reviews are evidence.\n  When they disagree, evidence wins.\n\n## Output shape\n\nWhen comparing finalists, verdict-first per property: one line of fit\n(\"best for you because: riverfront + real king bed + dogs genuinely\nwelcome\"), one honest caveat, then the evidence. Recommend ONE, say why the\nrunner-up lost.\n"
}