Update to Pilot

{
  "description": "Analyzes Google Analytics 4 conversions and acquisition channels through the Pilot MCP server: which channels bring sessions and key events, how they change over time, which key events are configured, and where users drop in a funnel. Use when the user asks about GA4, channels, traffic sources, conversions or funnels. Triggers: GA4 analysis, channel performance, traffic sources, conversion funnel. Déclencheurs : analyse GA4, canaux d'acquisition, sources de trafic, conversions Google Analytics, entonnoir de conversion.",
  "included_files": [],
  "name": "ga4-conversions-and-channels",
  "skill_md_contents": "---\nname: ga4-conversions-and-channels\ndescription: \"Analyzes Google Analytics 4 conversions and acquisition channels through the Pilot MCP server: which channels bring sessions and key events, how they change over time, which key events are configured, and where users drop in a funnel. Use when the user asks about GA4, channels, traffic sources, conversions or funnels. Triggers: GA4 analysis, channel performance, traffic sources, conversion funnel. Déclencheurs : analyse GA4, canaux d'acquisition, sources de trafic, conversions Google Analytics, entonnoir de conversion.\"\ncompatibility: \"Requires the Pilot MCP server (https://app.pilot.braike.com/mcp) connected in the client and authorized on a workspace with a Google Analytics 4 property attached.\"\nmetadata:\n  pilot-mcp-server: \"https://app.pilot.braike.com/mcp\"\n  pilot-mcp-tools: \"google_analytics_get_account_summaries google_analytics_get_metadata google_analytics_list_key_events google_analytics_list_channel_groups google_analytics_check_compatibility google_analytics_run_report google_analytics_run_funnel_report\"\n  pilot-mcp-read-only: \"true\"\n---\n\n# GA4 conversions and channels\n\nShow which acquisition channels bring traffic and conversions in Google Analytics 4, how that changed, and where users drop. Answer in the user's language.\n\n## Requirements\n\n- **Required MCP server:** Pilot MCP (`https://app.pilot.braike.com/mcp`), authorized on the workspace where the property is attached.\n- **Optional MCP servers:** a file storage server to save the tables, a team messaging server to share them. None is needed.\n- **Read-only:** never create or change a key event, audience, channel group or link.\n\n## Tools\n\n- `google_analytics_get_account_summaries`: the properties attached to the workspace.\n- `google_analytics_get_metadata`: the dimensions and metrics available on the property.\n- `google_analytics_list_key_events`: the events counted as conversions.\n- `google_analytics_list_channel_groups`: custom channel groups, if any.\n- `google_analytics_check_compatibility`: whether dimensions and metrics can be combined.\n- `google_analytics_run_report`: standard reports.\n- `google_analytics_run_funnel_report`: funnel reports.\n\n## Steps\n\n1. Call `google_analytics_get_account_summaries`. If several properties are attached, ask which one and pass it as `propertyId`; with one, leave it out.\n2. Call `google_analytics_list_key_events` to know what counts as a conversion. If none is configured, say so: conversion figures will be empty.\n3. Call `google_analytics_run_report` with two `dateRanges` of equal length (by default the last 28 days and the 28 days before), `dimensions: [\"sessionDefaultChannelGroup\"]`, `metrics: [\"sessions\", \"engagedSessions\", \"keyEvents\", \"totalRevenue\"]`.\n4. For the channels that moved most, break down by `sessionSource` and `sessionMedium`. When unsure a combination works, call `google_analytics_check_compatibility` first; check names with `google_analytics_get_metadata`.\n5. If the user describes a path (landing page, product page, cart, purchase), build it as a funnel with `google_analytics_run_funnel_report`.\n6. If custom channel groups exist (`google_analytics_list_channel_groups`), mention which grouping the figures use.\n\n## Output\n\n1. **Summary**: sessions, key events and revenue for both periods.\n2. **By channel**: a table with sessions, key events, conversion rate and the change.\n3. **What moved**: the sources behind the largest changes.\n4. **Funnel**, when asked: step counts and drop-off rates.\n5. **Tracking notes**: missing or doubtful key events.\n\n## Rules\n\n- Name the property, the periods and the time zone of the property when it matters.\n- A rate with an empty denominator is not available, not zero.\n- GA4 attribution differs from the ad platforms': do not expect the numbers to match theirs.\n\n## Examples\n\n- \"Which channels brought conversions this quarter?\"\n- \"Compare les canaux GA4 du mois dernier à ceux du mois précédent.\"\n- \"Where do users drop between the product page and the purchase?\"\n"
}