agentleFS
vizuhvizuh/clicktrail-claude-plugin/skills/click-tracking-audit/SKILL.md

click-tracking-audit

Skill0 starsChanged 3 months agoMITView on GitHub

Diagnose lost click IDs and attribution handoffs across landing pages, redirects, consent, forms, CRM records, and offline conversions. Use when someone asks to check my click tracking, debug GCLID/GBRAID/WBRAID/FBCLID/MSCLKID loss, preserve UTMs, fix offline conversion tracking, explain a GA4 versus Google Ads discrepancy, or attach click IDs to a CRM lead.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Read the host project's instructions, tracking documentation, manifests, and canonical acquisition, consent, form, server, CRM, and …

    line 22
  2. Very specific:

    Read ../../references/clicktrail-safety-contract.md.

    line 24
  3. Distinctive:

    Check GCLID, GBRAID, WBRAID, FBCLID, MSCLKID, and UTMs only where the host contract permits them.

    line 30
  4. Very specific:

    If the ClickTrail MCP server is already attached, pass only a caller-supplied source snapshot to inspect_project, then use …

    line 34
  5. Distinctive:

    If a user asks for current ClickTrail or Grok documentation, use public sources and cite them.

    line 47

≈ “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

Audit a click-tracking handoff

Remain read-only. Do not install packages, edit files, submit forms, call an ad platform, write to a CRM, or claim provider delivery.

  1. Read the host project's instructions, tracking documentation, manifests, and canonical acquisition, consent, form, server, CRM, and conversion entry points.
  2. Read ../../references/clicktrail-safety-contract.md. Treat browser attribution as untrusted context and keep the host application authoritative for consent, identity, tenant, lifecycle, credentials, retries, and business records.
  3. Trace the same allowlisted touchpoint through each boundary: CAPTURE -> PERSIST -> CARRY -> ATTACH -> REPORT -> DEDUPE -> VERIFY. Check GCLID, GBRAID, WBRAID, FBCLID, MSCLKID, and UTMs only where the host contract permits them. Look for query loss in redirects, consent-gated storage, SPA navigation, cross-domain transfer, form serialization, CRM mapping, stable event IDs, and reconciliation.
  4. If the ClickTrail MCP server is already attached, pass only a caller-supplied source snapshot to inspect_project, then use detect_attribution_gaps and diagnose_missing_click_ids. Use simulate_ad_click, verify_capture, verify_form_attachment, verify_crm_attachment, and attribution_health with synthetic values only. verify_conversion_delivery is unknown without an explicit provider receipt. Never pass PII, raw requests, secrets, or arbitrary payloads.
  5. Report a compact stage table with file evidence, the host-owned seam, and the smallest correction. Classify findings as Critical, Important, or Minor. Separate source evidence, synthetic evidence, runtime behavior, and provider receipt. A captured click ID alone is not conversion attribution.

If a user asks for current ClickTrail or Grok documentation, use public sources and cite them. Do not turn web or X search results into implementation or provider proof.

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.