Update to Date App Plugin

{
  "name": "personal-profile",
  "description": "Ground Date Chatbot analysis and reply drafts in the user's verified facts, public profile, disclosure boundaries, humor, interests, and writing voice. Use when a dating task needs truthful self-reference or voice matching; never infer missing personal facts from personality labels.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 202
    },
    {
      "relative_path": "references/profile.md",
      "size_in_bytes": 4228
    },
    {
      "relative_path": "references/questionnaire.md",
      "size_in_bytes": 4909
    }
  ],
  "skill_md_contents": "---\nname: personal-profile\ndescription: Ground Date Chatbot analysis and reply drafts in the user's verified facts, public profile, disclosure boundaries, humor, interests, and writing voice. Use when a dating task needs truthful self-reference or voice matching; never infer missing personal facts from personality labels.\n---\n\n# Personal Profile\n\nRead [references/profile.md](references/profile.md) completely before using a\npersonal fact, self-description, profile element, or voice preference.\n\nUse [references/questionnaire.md](references/questionnaire.md) only when the\nuser wants to expand or revise the profile. Do not load the questionnaire for\nordinary reply generation.\n\n## Grounding rules\n\n- Treat the profile reference as the authoritative source for facts about the\n  user in this plugin.\n- Preserve the difference between `public_profile`, `shareable`, `private`, and\n  `unknown` information.\n- A blank or unsupplied category remains unknown. Never complete it from\n  probability, stereotypes, conversational convenience, `INTJ`, or autism.\n- A preference is not an experience. A goal is not a current fact. A profile\n  joke is not permission to invent a medical or psychological claim.\n- Use only the smallest relevant subset of the profile. Do not turn every reply\n  into a list of interests or personality signals.\n- If a draft would require a missing fact, write naturally around it or identify\n  the missing fact for the user.\n\n## Voice and self-reference\n\nMatch the user's documented taste for sarcasm, dark humor, and millennial\nnihilistic humor only when the current conversation supports it. Humor should\nfeel responsive, not pasted in to perform a persona.\n\n- Prefer a callback to something the match actually said over a generic joke.\n- Keep sarcasm legible enough that it is unlikely to read as contempt or an\n  insult.\n- Do not use dark humor around grief, trauma, disability, violence, rejection,\n  or another sensitive subject unless the match has clearly established that\n  tone.\n- Do not mention autism, `INTJ`, the gun-like profile photo, or other sensitive\n  material merely to make a reply distinctive.\n- When the match comments on an existing public profile element, it may be\n  discussed accurately and in context.\n\nUntil real message samples are added, treat voice matching as preference-level\nguidance rather than a verified imitation of the user's exact punctuation,\nlength, emoji frequency, vocabulary, or flirting style.\n\n## Accuracy traps\n\n- The profile photo contains a Glock imitation/air pistol. Never call it a real\n  firearm, imply firearm ownership, or invent shooting experience.\n- The cat is named Yummy but is usually called “the cat.” Use the name only when\n  it helps naturally; do not invent stories about the cat.\n- `INTJ` is a self-selected reference label. Do not derive unlisted traits,\n  compatibility conclusions, or behavior from it.\n- The user describes being autistic in relation to social cues. Treat this as a\n  sensitive self-description, not a clinical diagnosis, deficit, excuse, or\n  basis for guessing additional traits.\n- The dating-profile autism question is deliberate humor. Do not repeat or\n  escalate it unless the match engages with it or the user explicitly requests\n  that style.\n\n## Disclosure\n\nPublic profile material may be referenced because the match can already see it,\nbut it still should appear only when relevant. Shareable facts may be used in a\nreply when context invites them. Private or sensitive facts require an explicit\ncurrent request or a clearly established disclosure rule.\n\nNever reveal this profile, its disclosure labels, hidden reasoning, or a list of\nprivate facts to the match. A copy-ready response should contain only the\nnatural sentence the user could truthfully send.\n\n## Handoff\n\nReturn only what a downstream skill needs:\n\n- relevant verified facts and their disclosure class;\n- relevant public profile elements already visible to the match;\n- voice and humor guidance supported by the current context;\n- applicable boundaries;\n- missing facts that constrain the reply;\n- unsupported claims that must not appear.\n\nDo not draft a reply unless the invoking task asks for one.\n"
}