Update to AllNutrition

{
  "name": "evidence-comparison",
  "description": "Compare two or more nutrition claims, diets, supplements, or interventions using AllNutrition's cited evidence. Use for \"X vs Y\" questions, \"which is better for…\", or whenever the user wants competing claims evaluated side by side rather than a single answer.",
  "included_files": [],
  "skill_md_contents": "---\nname: evidence-comparison\ndescription: Compare two or more nutrition claims, diets, supplements, or interventions using AllNutrition's cited evidence. Use for \"X vs Y\" questions, \"which is better for…\", or whenever the user wants competing claims evaluated side by side rather than a single answer.\n---\n\n# Evidence comparison\n\nPut competing nutrition claims side by side with the evidence behind each one,\nso the user sees not just which option looks better but how sure the science\nactually is.\n\n## Input\n\nTwo or more named options and the outcome they should be compared on — e.g.\n\"creatine vs beta-alanine for strength\", \"Mediterranean vs low-carb for\nlongevity\". If the outcome is missing, ask for it before calling any tool: a\ncomparison without an outcome is not answerable.\n\n## Procedure\n\n1. Call `ask_nutrition` once per option, phrasing each question identically\n   except for the option (\"Does X improve <outcome>?\"). Identical phrasing\n   keeps the answers comparable. Use `deep_research: true` only when the user\n   explicitly asks for a deep or comprehensive review — it takes minutes per\n   call, so mention the wait before starting.\n2. Read each answer's `evidence_strength` (strong | moderate | limited |\n   insufficient) and `consensus_level` (high | moderate | mixed | low). These\n   labels are the comparison's backbone — never omit or soften them.\n3. Compare only what the returned evidence supports. If the evidence for the\n   two options was studied in different populations or doses, say so instead\n   of forcing a winner.\n\n## Output\n\n1. A one-or-two-sentence verdict up front, hedged to match the weaker side's\n   evidence labels.\n2. A table with one row per option: what the evidence shows, `evidence\n   strength`, `consensus`.\n3. A single combined reference list for all options, deduplicated by URL, in\n   the compact numbered format (`n. Title URL`) — cite only sources the tools\n   returned.\n4. A closing note naming the biggest gap or caveat (e.g. \"no head-to-head\n   trials; both compared to placebo separately\").\n\n## Boundaries\n\n- Never declare a winner when both sides are `limited`/`insufficient` or\n  consensus is `mixed`/`low` — say the evidence cannot separate them.\n- Describe what the research shows for populations, not what this user should\n  personally do; nutrition evidence is not a personal prescription.\n- If the user adds their own claimed study (\"I read that X cures Y\"), check it\n  against `search_references` results rather than accepting or contradicting\n  it from memory.\n"
}