Tracking Schema logo

Tracking Schema

Community
jtrackingai
tracking-schema

Use when the user wants schema preparation, event design, selector validation, schema review, or event-spec generation.

Overview

Publisherjtrackingai
Repositoryanalytics-tracking-automation
Skill nametracking-schema
Stars
140
Forks
39
Bundled files
1
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jtrackingai on GitHub. Read the source before you install it.

Installation

Install the Tracking Schema AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jtrackingai/analytics-tracking-automation.git /tmp/analytics-tracking-automation
mkdir -p .claude/skills
cp -r /tmp/analytics-tracking-automation/skills/tracking-schema .claude/skills/tracking-schema
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tracking Schema in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Tracking Schema on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Tracking Schema is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Tracking Schema

Use this skill for Step 3 work only.

Inputs

One of:

  • confirmed <artifact-dir>/site-analysis.json
  • existing <artifact-dir>/event-schema.json

Workflow

Role And Quality Bar

During schema work, act as an expert in event tracking design.

Your job is not to list generic events. Your job is to produce a tracking plan that is:

  • aligned with common GA4 / GTM industry standards
  • comprehensive enough to cover the site's meaningful business journeys
  • accurate enough to be implemented and verified without guesswork
  • disciplined enough to avoid noisy, redundant, or low-signal events
  • easy for the user to review, approve, QA, and maintain

Favor event definitions that are business-meaningful, implementation-ready, and analytically useful. Do not preserve weak legacy patterns just for continuity. Do not inflate the schema with events that add little reporting or decision value.

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

If schema context is not prepared yet:

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

If the site has a live GTM container installed, make sure tracking-live-gtm has already produced <artifact-dir>/live-gtm-analysis.json before running prepare-schema.

Then:

validate-schema --check-selectors launches a real Chromium via Playwright to test each schema selector against the live site. 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.

bash
./event-tracking validate-schema <artifact-dir>/event-schema.json --check-selectors
./event-tracking generate-spec <artifact-dir>/event-schema.json
./event-tracking confirm-schema <artifact-dir>/event-schema.json

During review:

  • explain what live tracking problems the schema fixes when live-gtm-analysis.json is present
  • explain what benefits the new schema brings compared with the current live baseline
  • default to a compact tracking-plan summary in this order: Event Table, Common Properties, Event-specific Properties
  • keep long parameter inventories out of the main event table
  • stop for user approval before GTM generation
  • a broad request such as "full workflow" or "全流程" does not count as schema approval
  • do not run ./event-tracking confirm-schema <artifact-dir>/event-schema.json --yes on the user's behalf unless the user explicitly confirms the schema and parameters in the current turn

Required Output

Produce and share:

  • <artifact-dir>/event-schema.json
  • optional <artifact-dir>/event-spec.md
  • optional <artifact-dir>/tracking-plan-comparison.md when live-gtm-analysis.json is present
  • <artifact-dir>/schema-decisions.jsonl after schema confirmation
  • <artifact-dir>/schema-restore/ restore snapshots after schema confirmation
  • updated <artifact-dir>/workflow-state.json

Closeout Style

  • default to a decision-ready tracking-plan summary before listing files
  • keep the chat structure in this order: Event Table, Common Properties, Event-specific Properties
  • if a live baseline comparison exists, keep it as a compact appendix rather than replacing the tracking-plan structure
  • list files and next steps only after the summary

Stop Boundary

Stop after schema approval.

Do not continue into generate-gtm from a broad workflow request alone. The user must explicitly approve the current event-schema.json and its parameters first.

Default next phase:

bash
./event-tracking generate-gtm <artifact-dir>/event-schema.json --measurement-id <G-XXXXXXXXXX>

References

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Tracking Schema AI skill do?

Use when the user wants schema preparation, event design, selector validation, schema review, or event-spec generation.

Why use Tracking Schema on TypingMind?

Because you install it once and use it with any model. Tracking Schema is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Tracking Schema in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jtrackingai/analytics-tracking-automation/tree/main/skills/tracking-schema. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Tracking Schema?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Tracking Schema?

As many as you like. As long as a model supports skills, you can use Tracking Schema with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Tracking Schema AI skill free?

Yes. It is published on GitHub by jtrackingai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇