Update to Date App Plugin

{
  "description": "Interpret Date Chatbot timeline events—liked message, ghosted, CTA, and lost interest—and convert them into psychologically grounded, low-pressure strategy without claiming certainty about motives. Use when a Match timeline or status contains one of these event states.",
  "included_files": [
    {
      "relative_path": "references/event-catalog.md",
      "size_in_bytes": 4796
    }
  ],
  "name": "event-state-engine",
  "skill_md_contents": "---\nname: event-state-engine\ndescription: Interpret Date Chatbot timeline events—liked message, ghosted, CTA, and lost interest—and convert them into psychologically grounded, low-pressure strategy without claiming certainty about motives. Use when a Match timeline or status contains one of these event states.\n---\n\n# Event State Engine\n\nInterpret state events as changes in conversational strategy. An event records\nwhat happened operationally; it does not reveal why it happened.\n\nRead [references/event-catalog.md](references/event-catalog.md) before applying\nan event-specific strategy or recommending re-entry, contact exchange, or\nclosure.\n\n## Resolve the current state\n\n`match.messages` is chronological. Supported event kinds are:\n\n- `liked_message` — she reacted to a message without adding a written reply;\n- `ghosted` — no reply arrived within the user's chosen waiting period;\n- `cta` — the user marked that the interaction is ready for a next-step call to\n  action;\n- `lost_interest` — the user marked that interest has been lost by one or both\n  sides; the event does not encode whose interest changed.\n\nUse the latest timeline item as the current boundary. A later real message from\neither author means the conversation is active again and supersedes an earlier\nevent for current-state strategy. Retain the older event only as history.\n\nInspect the immediately preceding conversational turn and relevant private note\nbefore interpreting an event. Do not infer missing timing, who initiated an\nevent, or whether an event represents an explicit statement.\n\n## Psychological frame\n\nUse uncertainty-aware, situational explanations first. Dating apps can create\nhigh message volume, fragmented attention, choice overload, notification\nfatigue, competing priorities, and accidental forgetting. These are plausible\nnon-personal explanations for low effort or silence—not established facts and\nnot claims about women as a group.\n\nAlso preserve other plausible explanations: the previous message may not have\ninvited a response, the thread may have felt complete, timing may be poor, the\nmatch may be busy, interest may have decreased, or the match may have chosen not\nto continue. Do not diagnose attention span, attachment style, personality, or\nintent from an event.\n\nApply these principles:\n\n- avoid the fundamental attribution error: behavior does not prove character;\n- match effort rather than escalating after low-effort feedback;\n- reduce cognitive load with one easy conversational move;\n- preserve autonomy and an easy way not to engage;\n- avoid pressure, guilt, scorekeeping, or mentioning competition;\n- treat uncertainty as a reason for restraint, not repeated testing.\n\n## Strategy by event\n\n### Liked message\n\nTreat a like as acknowledgement with low conversational investment. It often\nmeans the current thread is paused and no further written answer should be\nexpected immediately. It is weak positive evidence that the message was seen or\nreceived, but it does not establish attraction, rejection, exhaustion, low\nattention span, or future intent.\n\nCheck whether the liked message naturally required a reply. If it was a joke,\nphoto, compliment, or closing statement, a reaction may be a complete social\nresponse. If it contained a clear question, the like still does not answer it;\nthe conversation remains paused.\n\nDo not instantly chase the reaction with another demand for attention. Either\nwait or later open one easy, fresh thread. Do not ask why she only liked it.\n\n### Ghosted\n\nTreat silence as missing behavioral response, not an explanation. A useful\nself-protective interpretation is that the conversation did not retain enough\nattention in a competitive, overloaded environment; this is a strategy model,\nnot proof that the user was uninteresting or that she forgot.\n\nReview whether the last user turn was answerable, overly demanding, closed, or\ndependent on missing context. If no explicit rejection or boundary exists, one\nlater low-pressure reintroduction may be considered. Prefer a fresh, specific,\neasy-to-answer topic over “why did you disappear?” or repeating the ignored\nmessage.\n\nAfter one unanswered re-entry, stop. Never recommend repeated follow-ups,\nalternate-account contact, guilt, urgency, or confrontation.\n\n### CTA\n\nTreat CTA as readiness to propose a concrete next step, not evidence that the\nmatch has already consented. The user's preferred sequence is exchanging\nInstagram or Facebook before an in-person meeting, because preserving contact\nreduces the practical risk of losing the connection after an unmatch.\n\nConfirm that the recent interaction has enough reciprocal engagement for an\nask. Recommend one clear, low-pressure action with an easy opt-out. Prefer a\nsocial-contact exchange first unless the current user explicitly requests a\nmeeting or the conversation already contains mutual meeting plans.\n\nDo not present contact exchange as creating responsibility, certainty,\ncommitment, exclusivity, or safety. Do not request multiple channels at once or\npressure after hesitation.\n\n### Lost interest\n\nFirst determine whose interest appears to have changed from direct messages,\nnotes, and the current user request. If this cannot be established, keep it\nambiguous.\n\nIf the match explicitly rejected contact, set a boundary, unmatched, blocked,\nor clearly asked not to continue, close the interaction. Do not recommend a\nretry regardless of attractiveness or other favorable details.\n\nIf no explicit rejection exists and the event is the user's own uncertain or\ntemporary loss of interest, the user may reconsider once. High attractiveness\nor favorable non-blocking Wiki assessments may explain the user's desire to\nre-evaluate, but they do not create entitlement or evidence of her interest. A\nretry must be one low-pressure, contextually plausible message with no complaint\nor demand. If it receives no response, stop.\n\n## Precedence and retry budget\n\nApply this order:\n\n1. explicit rejection, consent, safety issue, or boundary;\n2. latest real message after an event;\n3. latest current event;\n4. direct conversational evidence;\n5. private user note and current instruction;\n6. Wiki preferences and compatibility assessments;\n7. psychological hypotheses.\n\nExplicit boundaries cannot be overridden by attractiveness, a positive Wiki\nassessment, prior chemistry, a liked message, or the belief that silence was\naccidental.\n\nAcross `liked_message`, `ghosted`, and ambiguous `lost_interest`, allow at most\none suggested re-entry after the current pause unless a later real message\nreactivates the conversation. The event engine must surface whether that retry\nhas already occurred; it must not reset the budget by changing wording or\nchannel.\n\n## Handoff\n\nReturn an event brief rather than drafting the message:\n\n- `eventKind` and event ID;\n- whether it is current or superseded;\n- directly observed behavior;\n- plausible explanations, labeled as hypotheses;\n- explanations that must not be claimed;\n- strategic state: `wait`, `low_pressure_reentry`, `advance`, `close`, or\n  `active_again`;\n- retry eligibility and remaining retry budget;\n- relevant boundary or consent constraint;\n- recommended effort level;\n- what the next strategy may do and must avoid.\n\nKeep private psychological framing, attractiveness assessments, competition,\nand Wiki judgments out of copy-ready messages.\n"
}