{"id":15741,"plugin_id":"plugin_asdk_app_6aa5700e34c0819188953778ed6a74f9","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:11:57.468Z","digest":"05e6fd8c5aea4fe18dccb29e788da727e8b62a32ad0a0bdb29cbb391da26e85c","against":null,"payload":{"name":"qualitati-results","description":"Read and summarise results of a QualiTaTi interview study (completion status, per-interview quality and coding analysis, digests, full transcripts) and write an evidence-backed theme summary. Use when the user asks what came out of their interviews, wants themes, findings, quotes, a results summary, or whether analysis has run.","included_files":[],"skill_md_contents":"---\nname: qualitati-results\ndescription: Read and summarise results of a QualiTaTi interview study (completion status, per-interview quality and coding analysis, digests, full transcripts) and write an evidence-backed theme summary. Use when the user asks what came out of their interviews, wants themes, findings, quotes, a results summary, or whether analysis has run.\nversion: 1.0.0\n---\n\n# Read results from QualiTaTi\n\nTools: `project_list`, `project_interviews`, `analysis_summary`, `analysis_results`, `analysis_run`, `analysis_digest`, `interview_get`.\n\n## 1. Locate the study\n\n`project_list` → match the user's description to a project; keep both its `uuid` (most tools) and `id`. If several match, ask.\n\n## 2. See what exists\n\n- `project_interviews(project_uuid, limit, offset)` → each interview's `uuid`, `status`, `has_transcript`, `duration`, `analysis_ready`, `quality_score`.\n- `analysis_summary(project_uuid)` → `total` vs `coded` (interviews with a stored analysis).\nReport the state honestly: e.g. \"7 interviews, 5 completed, 3 analysed\".\n\n## 3. Get the analysis\n\nFor each **completed** interview:\n- `analysis_results(interview_uuid)` → stored quality + coding (themes/codes) under `data`. If `analysis_ready` is false or it says nothing has been computed yet:\n  - `analysis_run(interview_uuid, mode=\"complete\")` (quality + coding) or `mode=\"coding\"` (themes only). This spends the owner's credits and is rate-limited (~5 runs/minute): ask before running it on more than a handful, and never re-run what already exists.\n- `analysis_digest(interview_uuid)` → keywords / summary / insight, when stored.\n- `interview_get(interview_uuid)` → metadata + the full conversation, for verbatim quotes.\n\n## 4. Write the summary\n\n- Themes ordered by how many interviews they appear in, each with: what it is, how many interviews, 1–2 **verbatim** quotes tagged with the interview (order id or name).\n- Separate description (\"participants said…\") from interpretation (\"this suggests…\").\n- State the sample size and what was not analysed. Flag low-quality interviews (`quality_score`) rather than silently including them.\n- Never invent quotes, counts or themes; if the analysis is missing, offer to run it.\n\n## Formats\n\nPlain prose with short headings for chat; a table of themes × interviews when the user wants to compare; CSV only on request.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}