mcpbeat

Tracking Live Gtm

jtrackingai/tracking-live-gtm

Use when the user wants to inspect the real live GTM runtime before schema generation or compare multiple live GTM containers.

795 tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
134
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/jtrackingai/analytics-tracking-automation --skill tracking-live-gtm

The instruction itself

7 sections, as written by the author

Tracking Live GTM

Use this skill to audit the site's real live GTM setup before event generation.

Inputs

One of:

  • confirmed <artifact-dir>/site-analysis.json
  • explicit live GTM public IDs when the crawl did not capture them

Workflow

If the telemetry consent prompt appears and no prior choice is recorded, stop and follow ../../references/telemetry-consent.md before continuing.

Run the live baseline step before schema preparation whenever the site has a real GTM container installed:

./event-tracking analyze-live-gtm <artifact-dir>/site-analysis.json

If multiple live containers matter and the user already knows the primary comparison target:

./event-tracking analyze-live-gtm <artifact-dir>/site-analysis.json --primary-container-id GTM-XXXXXXX

If the user wants to test the quality of the already-published live GTM setup on the real site, run:

./event-tracking verify-live-gtm <artifact-dir>/site-analysis.json

During review:

  • show all detected live GTM containers
  • explain which container is the primary comparison baseline
  • summarize existing live events, measurement IDs, and obvious issues
  • when verify-live-gtm was run, separate parsed live definitions from browser-verified live firing evidence
  • if this review is part of tracking_health_audit, clearly separate runtime-detected live definitions from any formal preview-verified automation evidence
  • stop before schema authoring if the user wants to review the live baseline first

Required Output

Produce and share:

  • <artifact-dir>/live-gtm-analysis.json
  • <artifact-dir>/live-gtm-review.md
  • optional <artifact-dir>/live-preview-result.json
  • optional <artifact-dir>/live-preview-report.md
  • optional <artifact-dir>/live-tracking-health.json
  • updated <artifact-dir>/workflow-state.json

Closeout Style

  • default to a compact live-tracking summary before listing files
  • name the detected live events directly instead of only reporting event counts
  • in tracking_health_audit, explicitly separate runtime-detected live definitions from formal preview-verified automation evidence
  • list artifacts only after the decision-ready summary

Stop Boundary

Stop after the live GTM baseline is reviewed unless the user explicitly asks to continue into schema work.

Default next phase:

./event-tracking prepare-schema <artifact-dir>/site-analysis.json

References

  • ../../references/event-schema-guide.md
  • ../../references/output-contract.md
  • ../../references/architecture.md

How to use it

Copy the folder

Take jtrackingai/tracking-live-gtm from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.