Update to Caveman Mode

{
  "description": "Teach a bounded concept in a supported Persona app voice, check the learner's own explanation, and correct misunderstandings. Use for character-led explanations with a teach-back or understanding check. Do not use for simple factual answers, unsupported claims of mastery, or language-conversation practice.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 252
    }
  ],
  "name": "persona-teach-back",
  "skill_md_contents": "---\nname: persona-teach-back\ndescription: Teach a bounded concept in a supported Persona app voice, check the learner's own explanation, and correct misunderstandings. Use for character-led explanations with a teach-back or understanding check. Do not use for simple factual answers, unsupported claims of mastery, or language-conversation practice.\n---\n\n# Persona Teach-Back\n\nUse a character's imagery to explain a concept, then check the underlying idea.\n\n## Inputs\n\nUse the concept or supplied learning material, learner's starting level, desired\noutcome, and requested persona. Infer level from context when possible. Ask for\nmissing material when the user wants an explanation of a specific unavailable\nsource; do not pretend to have read it.\n\n## Workflow\n\n1. Bound the lesson to one idea and identify what a correct explanation should\n   include. Use supplied material when present; identify gaps or uncertainty\n   rather than allowing character flair to stand in for evidence.\n2. Resolve the persona using the registered `activate-persona` `personaId` enum.\n   Offer a fitting supported voice if unspecified. Open `display-persona-picker`\n   with an optional `reason` when the user requests buttons, then wait for their\n   choice or a model-visible activation.\n3. Call `activate-persona` with the chosen supported `personaId` and an optional\n   `reason`, unless the latest visible activation already matches. Follow\n   `structuredContent.activePersona.instruction`. Report a failed call or absent\n   `activePersona` before claiming activation.\n4. Give a short explanation and one character-flavored analogy suited to the\n   learner. Map the analogy back to the actual concept and explain its most\n   relevant limitation so the fictional imagery does not become a false rule.\n5. Ask the learner to explain the idea in their own words or apply it to one new\n   example. Wait for their answer before evaluating it.\n6. Identify what their answer gets right and one specific gap, if any. Correct\n   that gap and invite a focused retry. Adjust to their response rather than\n   repeating the whole lesson or inventing a learner answer.\n\n## Deliverable and boundaries\n\n- Finish with a corrected explanation, a compact recap, and one useful check\n  question or next practice step. Ground feedback in the learner's actual reply.\n- Preserve factual meaning and the conversation language unless another is\n  requested. Treat the persona as delivery style, without implying expertise.\n- Use available sources when verification is needed; the Persona tools supply\n  voices, not research, source retrieval, grading, or learning-history storage.\n- Keep progress in chat. Do not infer mastery, scores, private widget state, or\n  unseen prior attempts. Honor requests to change voice or stop the lesson.\n"
}