{"id":41005,"plugin_id":"plugin_asdk_app_6a53f7d79b5c81919a02e9814eb9f070","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-10-24T12:56:56.393Z","digest":"770699d0c9344aa42e0c9d861f140a6c397d3c6c8f44a52d21868f6b95591ed7","against":null,"payload":{"description":"Reverse-engineers your best-converting Supademo demos into a reusable structural playbook — hook, length, chapter shape, CTA placement. Use before building new demos so they start from what already works.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":217}],"name":"top-performer-patterns","skill_md_contents":"---\nname: top-performer-patterns\ndescription: Reverse-engineers your best-converting Supademo demos into a reusable structural playbook — hook, length, chapter shape, CTA placement. Use before building new demos so they start from what already works.\n---\n\n# Top-Performer Pattern Extractor\n\nYour best demos already know what converts. This skill writes it down.\n\n## Prerequisites\n\n- Supademo MCP connected\n- Enough history for \"top\" to mean something (a handful of demos with real traffic)\n\n## Workflow\n\n1. **Identify the winners.** `get_top_performing_demos` supports server-side ranking by views, uniqueViews, or engagement. For completion or CTA engagement, fetch all relevant pages first, then sort the returned fields client-side, excluding null metrics and noting sample sizes. The returned population excludes showcases and unshared demos; do not call it the entire library.\n2. **Dissect each.** `get_demo` per winner, plus `get_demo_hotspot_performance` for where viewers engage hardest. Record:\n   - Total steps and estimated watch time\n   - What step 1 shows — product outcome, problem statement, or UI tour?\n   - Where the \"aha\" screen lands (step number)\n   - Chapter structure and titles\n   - CTA count and placement (mid-demo, end, both)\n   - Voiceover: present or not; annotation length norms\n3. **Find the pattern.** What do 4 of 5 share? Be honest when winners diverge — report \"two archetypes\" rather than forcing one template.\n4. **Contrast with the laggards.** Pull 2–3 low-completion demos and note what the winners do that they don't. The differences are the playbook.\n5. **Write the playbook:**\n\n```\n## Demo playbook — extracted {date}\n- Length: {n}–{m} steps (~{x} min)\n- Step 1: {pattern}\n- Aha moment: by step {n}\n- Chapters: {pattern}\n- CTA: {pattern}\n- Copy: {avg words}/step, {register}\nEvidence: {demo} — {completion}%, {demo} — {completion}%...\n```\n\n## Guardrails\n\n- Correlation caveat up front: top demos may win because of the feature they show, not their structure. The playbook is a strong prior, not a law.\n- Re-run quarterly; patterns drift as the library and audience change.\n\n## Supademo tool conventions\n\nRead [the tool conventions](../supademo-onboarding/references/tool-use.md) before calling Supademo tools for this workflow.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}