Tracking Verify Agent Skill

by jtrackingai

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

761 tokens

context cost

the whole folder, loaded on every use

files

instructions only

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-verify

The instruction itself

7 sections, as written by the author

Tracking Verify

Use this skill for verification and optional publish handoff.

Inputs

<artifact-dir>/event-schema.json
<artifact-dir>/gtm-context.json

Workflow

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

Run preview:

./event-tracking preview <artifact-dir>/event-schema.json --context-file <artifact-dir>/gtm-context.json

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

./event-tracking preview <artifact-dir>/event-schema.json --context-file <artifact-dir>/gtm-context.json --baseline <previous-tracking-health.json>

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 <artifact-dir>/gtm-context.json --version-name "GA4 Events v1 - <date>"

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:

<artifact-dir>/preview-report.md
<artifact-dir>/preview-result.json
<artifact-dir>/tracking-health.json
<artifact-dir>/tracking-health-report.md
<artifact-dir>/tracking-health-history/
updated <artifact-dir>/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/gtm-troubleshooting.md
../../references/output-contract.md

Other skills for the same job

different authors, same section of the catalogue

Skill Creator

by anthropics

vendor ×10

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Replace with description of the skill and when Claude should use it.

35 tokens

Dispatching Parallel Agents

by ZhanlinCui

×5

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Use when creating new skills, editing existing skills, or verifying skills work before deployment

26k tokens scripts

How to use it

Copy the folder

Take jtrackingai/tracking-verify 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.