{"id":46764,"plugin_id":"plugin_asdk_app_6abed98cf9b08191b2c40cc2c305459b","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-10-24T13:31:01.905Z","digest":"c3893ae9a820334a3c1453beb10ef8fd103b9e36584a717e7a8daaea22cb3c95","against":null,"payload":{"description":"Use with the Great Question tools when summarizing research, answering a question that spans sessions or studies, or interpreting what participants said. How we ground every claim in transcript evidence and never fabricate quotes.","included_files":[],"name":"synthesis-and-insights","skill_md_contents":"---\nname: synthesis-and-insights\ndescription: \"Use with the Great Question tools when summarizing research, answering a question that spans sessions or studies, or interpreting what participants said. How we ground every claim in transcript evidence and never fabricate quotes.\"\n---\n\n# Synthesis & Insights\n\nIf your Great Question workspace has its own skill for this, follow that instead.\n\nUse this whenever you summarize research, answer a question that spans sessions or studies, or interpret what participants said. Every claim must trace back to something a participant actually said or did.\n\n## Ground everything in transcripts\n\n- Work from the actual transcript text, not from titles, summaries, or study names. Read what was said.\n- When a question spans more than one study, search across transcripts rather than opening studies one at a time.\n- Note which session and which participant each piece of evidence comes from, so a claim can be traced back.\n\n## Search widely before you conclude\n\nTranscript search runs two arms at once: a meaning-based one and a literal full-text one. They reward opposite styles of query, so use each as intended rather than typing the same string into both.\n\n- For the meaning-based arm, write the way a person would talk. A natural phrase or a real question works better than keywords, and phrasing something as a question retrieves differently from a statement.\n- For the full-text arm, name the one or two words a participant would actually say, and OR the synonyms rather than stacking terms. Unquoted words are ANDed, so more than two of them together will usually match nothing at all. Reserve quotes for a phrase said verbatim.\n- Vary the wording across several searches. Participants describe the same thing differently (\"onboarding\" / \"getting started\" / \"first time\" / \"setup\"), and one query rarely surfaces everything.\n- Search more than one surface. Transcripts, session responses, and existing repository highlights and insights each hold different evidence.\n- Go broad, then narrow. Start unscoped to see the whole landscape, then scope to specific studies once you know what's relevant.\n- Don't stop at the first page. A page of matches is not the same as all of them.\n- Know when you're done. Stop when new searches stop turning up new evidence, not when the first query returns something plausible.\n\n## From evidence to a finding\n\n- Think of it as a chain: what a participant said, then a notable moment, then a theme, then a finding. Don't skip levels.\n- A single participant saying something is a signal, not a finding.\n- Treat something as a finding only when two or more participants independently support it.\n- State findings as observations about users, not recommendations. (\"Users abandon at the payment step,\" not \"Add a progress bar.\")\n- Always carry at least one supporting verbatim quote with the finding.\n\n## Weighing evidence\n\n- Say how many participants support a claim and how strongly.\n- Distinguish what participants said from what they did, stated preference and observed behavior often diverge; call it out when they do.\n- Don't overstate confidence. Small samples describe, they don't prove.\n\n## Guardrails\n\n- Never fabricate a quote or attribute one to the wrong participant. If you can't find supporting evidence, say the claim is unsupported rather than inventing support.\n- Keep participant PII out of anything summary-level or shareable.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}