{"id":85634,"plugin_id":"plugin_asdk_app_6ada68616590819197685ef0b29787d2","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-07T06:14:30.215Z","digest":"9c3af38b3509316a100406035171b515935d1097827308eaab317d2344aa457a","against":null,"payload":{"description":"Compare devices, countries, channels, and campaigns using Noibu, identify conversion regressions, and provide an interactive report with investigation, dashboard, export, and scheduling actions.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":329},{"relative_path":"references/queries.md","size_in_bytes":5331}],"name":"segment-analysis","skill_md_contents":"---\nname: segment-analysis\ndescription: Compare devices, countries, channels, and campaigns using Noibu, identify conversion regressions, and provide an interactive report with investigation, dashboard, export, and scheduling actions.\n---\n\n# Segment conversion analysis\n\n- Read [shared query guidance](../querying-noibu-data/SKILL.md) and [runtime/actions](../querying-noibu-data/references/chatgpt-runtime.md). Use skill `segment-analysis`; resolve the store and saved context. Default to 30 days.\n- Focused questions need only relevant queries. For a full review, follow [queries](references/queries.md):\n  - Fetch device, country and UTM source/medium aggregates plus a direct whole-domain baseline.\n  - Compare channels with peers of similar intent/objective; compare devices with their own history. Use equal halves with exact dates for within-window device ratios.\n  - Assess traffic quality and sparse purchases; zero conversion or geography alone does not identify bots.\n  - Select up to three supported signals and run campaign, landing-page or funnel follow-ups.\n\n## Dashboard and opportunities\n\nUse the packaged [inline presentation](../querying-noibu-data/references/presentation.md).\n\n- Lead with one or two measured conclusions.\n- Overview: site-wide/mobile/desktop conversion, purchasing/session denominators, exact window/timezone and a few nonduplicative country/channel highlights. No mandatory funnel.\n- Under Show more/Show less, use three `placement: \"overview\"` tables when supported: Countries, Best converting channels, Most visited channels. Include Sessions/CVR/Revenue per session with measured currency components kept separate.\n- State each ranking's volume filter, population and top-N bounds. A capped result cannot establish a global winner. Retain five-row previews/all rows; history/campaign/landing tables use `supporting`.\n- Use up to three visible `overviewNotes` for material attribution, reconciliation or currency caveats; retain detailed evidence too.\n- Each top opportunity has a factual tag, specific cohort, actual traffic unit and concise evidence; `fix` holds expandable investigation/verification.\n- Keep **Save as Live Site** directly after dashboard content, then opportunities, then separate **Download & schedule** controls. Shared styling supplies light panels and orange measured declines.\n\n## Interpretation\n\n- A stable device gap is not a regression. A worsening ratio driven by faster desktop improvement or traffic mix does not prove mobile deteriorated.\n- Separate country opportunity, channel intent and campaign objective; exposure is not proven blocked users or lost orders.\n- Do not merge source/medium aliases or call all unattributed sessions Direct without evidence.\n- Missing UTM share needs a complete unattributed aggregate and whole-domain denominator, not overlapping cohort sums. Missing tags do not prove a tracking defect.\n- For absent paid-traffic UTM rows, use the shared guide's referrer-parameter recovery and label results a lower bound.\n- Preserve low-volume uncertainty, count discrepancies and currency boundaries; do not invent signals to fill cards.\n\n## Follow-ups\n\n- Investigate retains the selected evidence. Route genuine technical findings to tech-diagnosis and [source access](../querying-noibu-data/references/source-access.md), not ordinary marketing findings.\n- Site saves use [persistent dashboards](../querying-noibu-data/references/connected-dashboard.md) and [permission preflight](../querying-noibu-data/references/site-permissions.md), including the confirmed weekly-refresh offer.\n- **Schedule Insights** uses [shared connected delivery](../querying-noibu-data/references/scheduling-delivery.md), fresh rolling scope and the confirmed equal-half/other baselines. Daily is not offered here.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}