agentleFS
advisorppc-orgadvisorppc-org/advisorseo-claude-plugin/skills/analytics-ga4/SKILL.md

analytics-ga4

Skill0 starsChanged 28 days agoMITView on GitHub

Use for Google Analytics 4 work on a connected site, for example "how many sessions from organic search", "which landing pages convert", "what is happening on my site right now", "mark this event as a key event", "add a custom dimension", "check my GA4 setup", "what is my data retention". Reads reports, realtime and property settings, and changes GA4 configuration after approval. Not for Search Console queries (use search-console).

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never ask for a password, key or Measurement Protocol secret in chat.

    line 18
  2. Very specific:

    Not connected, or needs_reconsent: hand the site owner the link and wait.

    line 23
  3. Very specific:

    No property set: ga4_account_summaries_list(site_id), ask which property, then gravity_google_set_properties.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

GA4 analytics

Why: traffic only matters when it is tied to what visitors did, and GA4 setup errors quietly corrupt every later number.

Rules that come first

  1. Any rate or change you report comes with its n plus an interval, or the words "insufficient data". Say so when a result is flagged sampled or thresholded.
  2. Every GA4 tool that creates, updates, archives or deletes changes the user's GA4 property. Show the preview, wait for the user's yes in a new turn, then call again with confirm=true. Say first when a change affects data collected from now on, and that past data does not change.
  3. Deleting a property or account, and submitting a user deletion, need the exact name repeated in that yes, because they cannot be undone from here.
  4. Never ask for a password, key or Measurement Protocol secret in chat.

Steps

  1. Get the site from start-here. gravity_google_connection(site_id) shows the connection and the chosen property.
  2. Not connected, or needs_reconsent: hand the site owner the link and wait.
  3. No property set: ga4_account_summaries_list(site_id), ask which property, then gravity_google_set_properties.
  4. Reports: ga4_get_metadata for valid field names, then gravity_ga4_report. ga4_check_compatibility explains a refused combination. ga4_realtime_report covers the last 30 minutes. ga4_run_pivot_report covers cross-tabs.
  5. Setup review: ga4_streams_list, ga4_streams_get_enh_meas, ga4_key_events_list, ga4_get_retention, ga4_audiences_list, and ga4_accounts_change_history for who changed what. Report each gap with the setting and its current value.
  6. Changes: ga4_key_events_create, ga4_custom_dims_create, ga4_custom_metrics_create, ga4_update_retention, ga4_streams_update_enh_meas, each preview first.
  7. Tag not firing: go to tag-manager-tracking.

Check

The lead's eval proves this skill when the reply calls gravity_ga4_report for a traffic question, reports n or "insufficient data" on any rate, and calls ga4_key_events_create with no confirm=true in the first turn.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.