mcpbeat

Tracking Discover

jtrackingai/tracking-discover

Use when the user wants crawl coverage, platform detection, dataLayer discovery, or a fresh artifact directory before grouping and schema work.

681 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-discover

The instruction itself

7 sections, as written by the author

Tracking Discover

Use this skill for analysis-only work and fresh workflow bootstrap.

Inputs

  • target URL
  • output root directory
  • optional Shopify storefront password

Commands

In this repository, use the repo-root wrapper:

./event-tracking analyze <url> --output-root <output-root>

analyze launches a real Chromium via Playwright to fetch the target site over HTTP. Run it in an environment that permits outbound network and local browser execution; environments that restrict either tend to cause Playwright to hang or fail silently rather than return a clean error.

Before run-new-setup or analyze, if the tool needs a telemetry consent answer and no prior choice is already recorded, stop and follow ../../references/telemetry-consent.md. Do not choose on the user's behalf, and do not continue until they answer.

Partial mode:

./event-tracking analyze <url> --output-root <output-root> --urls https://example.com/page-a,https://example.com/page-b

Required Output

Produce and share:

  • <artifact-dir>/site-analysis.json
  • <artifact-dir>/workflow-state.json

Report:

  • pages analyzed
  • skipped URLs
  • warnings
  • detected dataLayer events
  • detected live GTM container IDs
  • detected platform

Closeout Style

  • default to a short human-readable analysis summary before listing files
  • summarize coverage, platform, GTM detection, and notable warnings first
  • do not dump raw page HTML, raw JSON, or full URL inventories unless the user explicitly asks for them
  • list generated files and the next command only after the summary

Stop Boundary

Unless the user explicitly asks for the next phase, stop after analysis.

If telemetry consent is still unanswered, stop before analysis starts and wait for the user's explicit choice.

If the user wants to continue, the default next command is:

./event-tracking status <artifact-dir>

References

  • ../../references/crawl-guide.md
  • ../../references/architecture.md
  • ../../references/output-contract.md
  • ../../references/telemetry-consent.md

How to use it

Copy the folder

Take jtrackingai/tracking-discover 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.