Update to Interactify Beta

{
  "description": "Decide which of Interactify's 9 H5P content types actually fits a given learning goal, before calling any create_h5p_* tool - start from what the learner needs to do, not from which tool sounds closest to what the user asked for, and recognize when more than one activity (or none of these) is the honest answer.",
  "included_files": [],
  "name": "choosing-the-right-h5p-content-type",
  "skill_md_contents": "---\nname: choosing-the-right-h5p-content-type\ndescription: Decide which of Interactify's 9 H5P content types actually fits a given learning goal, before calling any create_h5p_* tool - start from what the learner needs to do, not from which tool sounds closest to what the user asked for, and recognize when more than one activity (or none of these) is the honest answer.\n---\n\nStart from the learning goal, not the request's surface wording. Someone asking to \"test my\nstudents on this chapter\" might mean recall of facts (Dialog Cards), checking they followed\nthe chapter's logic (Interactive Book with checkpoints), or a formal graded assessment\n(Quiz) - these call for different tools even though the request sounds similar. If the goal\nisn't clear from context, it's worth a quick clarifying question rather than guessing.\n\n## Decision guide\n\n**The learner needs to recall a fact, term, or definition on demand**\n→ Dialog Cards (self-paced review, flip to check) or Fill in the Blanks (production,\nnot just recognition - stronger retrieval practice than picking from options).\n\n**The learner needs to recognize and recall vocabulary in context**\n→ Drag the Words (the sentence gives context the word has to fit) or Crossword (the clue\nforces recall from a definition rather than just pattern-matching a word shape). Crossword\nspecifically rewards words that share letters with each other (thematically related sets\nwork better than a random grab-bag) - mention this if the chosen words look unrelated.\n\n**The learner needs to check their understanding of one specific idea, with one correct\nanswer among a few options**\n→ Single Choice Set for a quick sequence of individually low-stakes checks, or standalone\nmultiple-choice questions inside a Quiz if it's part of a larger graded set.\n\n**The learner needs to work through a full document, chapter, or guide and check\nunderstanding along the way**\n→ Interactive Book, with checkpoint questions placed at natural section boundaries - ask how\noften they want checks if they haven't said (every section vs. a few key spots vs. just a\nwrap-up).\n\n**The learner needs to engage with a specific video instead of watching it passively**\n→ Interactive Video, with interactions timed to actual content beats in the video, not\nevenly spaced by the clock.\n\n**The person needs to organize or let someone browse reference material - a policy doc, an\nFAQ, \"find the part that's relevant to you\"**\n→ Accordion. This isn't really an assessment, and that's the right call when nothing needs\nto be *tested*, just organized and made scannable.\n\n**The person needs a real graded or summative assessment with an overall score and pass\nmark**\n→ Quiz. This is the one format built around an overall score, not Single Choice Set or\nFill in the Blanks, even though those also \"ask questions.\"\n\n**The request implies dragging visual elements onto an image, diagram, or map**\n→ None of these fit well. Interactify's content generation is text-only (no image\npipeline) - say this plainly rather than forcing a text-only format to stand in for an\nimage-based interaction it wasn't built for.\n\n## More than one activity can be the right answer\n\nA single request sometimes genuinely calls for more than one content type - \"turn my\nonboarding guide into something interactive\" might be best served by an Interactive Book\nfor the guide itself *and* a separate Dialog Cards deck for the glossary of internal terms\nit introduces. Don't force everything into one activity when splitting it serves the\nlearning goal better; say so and offer both.\n\n## When none of the nine fit\n\nIf what's being asked for is open-ended writing, peer discussion, live debate, or anything\nthat isn't reducible to a defined-answer interaction, none of these content types are a good\nfit - that's a real limit of the current nine, not something to approximate with a\nmultiple-choice stand-in. Say so, and build the closest reasonable fit only if the user\nstill wants it with that limitation understood.\n"
}