AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Tracking Verify

skill-jtrackingai-analytics-tracking-automation-tracking-verify · by jtrackingai

Use when the user wants preview QA, failure interpretation, release readiness, or an explicit publish handoff.

↗ Website ↗ Repository
— No reviews yet
0 installs
27 views
0.0% view→install

Install

$ agentstack add skill-jtrackingai-analytics-tracking-automation-tracking-verify

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-jtrackingai-analytics-tracking-automation-tracking-verify)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
○ 4mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Tracking Verify? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Tracking Verify

Use this skill for verification and optional publish handoff.

Inputs

  • /event-schema.json
  • /gtm-context.json

Workflow

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

Run preview:

./event-tracking preview /event-schema.json --context-file /gtm-context.json

If comparing against an older preview run, pass the previous health baseline:

./event-tracking preview /event-schema.json --context-file /gtm-context.json --baseline

preview launches a real Chromium via Playwright and exercises the live site to fire GA4/GTM events for verification. 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.

Then interpret:

  • blockers
  • expected failures
  • selector mismatches
  • unexpected fired events outside the approved schema
  • release readiness

If the user explicitly wants to publish after verification:

./event-tracking publish --context-file /gtm-context.json --version-name "GA4 Events v1 - "

If tracking-health.json is missing, still manual-only, or has blockers, publish now stops by default. Only use --force when the user explicitly wants to override that gate.

Required Output

Produce and share:

  • /preview-report.md
  • /preview-result.json
  • /tracking-health.json
  • /tracking-health-report.md
  • /tracking-health-history/
  • updated /workflow-state.json

Closeout Style

  • default to a verification verdict first: healthy, blocked, or manual follow-up required
  • summarize blockers, unexpected events, and release-readiness in plain language before listing files
  • keep raw preview data and artifact references after the summary

Stop Boundary

  • stop after preview if the user only asked for QA
  • publish only when the user explicitly wants to affect the live site

If the platform is Shopify, switch to the Shopify-specific rules in tracking-shopify.

References

  • [../../references/preview-report.md](../../references/preview-report.md)
  • [../../references/gtm-troubleshooting.md](../../references/gtm-troubleshooting.md)
  • [../../references/output-contract.md](../../references/output-contract.md)

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Data & Analytics