← NoibuCONTENT HISTORY

Update to Noibu

Snapshot Nov 7, 2026 · 06:14 UTC · version 1.2.8

Collection source: downloaded plugin package.

WHAT CHANGED

First saved snapshot

No earlier snapshot is available to establish a change.

Save Noibu and check future changes in Following.

Up to 3 plugins free · no card required.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "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"
}

SHA-256 of public snapshot: 9c3af38b3509316a100406035171b515935d1097827308eaab317d2344aa457a