analytics-tracking
Design, audit, and improve analytics tracking systems that produce reliable, decision-ready data. Use when the user wants to set up, fix, or evaluate analytics tracking (GA4, GTM, product analytics, events, conversions, UTMs). This skill focuses on measurement strategy, signal quality, and validation— not just firing events.
Install with Tessl CLI
npx tessl i github:duclm1x1/Dive-Ai --skill analytics-tracking82
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that excels across all dimensions. It provides specific actions, comprehensive trigger terms covering multiple analytics platforms and user intents, explicit 'Use when' guidance, and clear scope boundaries that distinguish it from related skills. The description effectively communicates both capabilities and appropriate use cases.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Design, audit, and improve analytics tracking systems' with clear outcome focus on 'reliable, decision-ready data' and mentions specific concerns like 'measurement strategy, signal quality, and validation.' | 3 / 3 |
Completeness | Clearly answers both what ('Design, audit, and improve analytics tracking systems') and when ('Use when the user wants to set up, fix, or evaluate analytics tracking') with explicit trigger guidance and scope clarification ('not just firing events'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'GA4, GTM, product analytics, events, conversions, UTMs, analytics tracking, set up, fix, evaluate' - these are exactly what users would mention when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on analytics tracking systems with distinct triggers (GA4, GTM, UTMs, conversions). The clarification 'not just firing events' further distinguishes it from generic event tracking skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a solid strategic framework for analytics measurement with clear decision gates and structured outputs. However, it's verbose for what Claude needs to know, lacks executable code examples for implementation guidance, and keeps all content inline rather than using progressive disclosure for reference material.
Suggestions
Add executable code examples for GTM dataLayer pushes and GA4 event implementation (e.g., actual JavaScript snippets for common events)
Trim explanatory text that states obvious principles—Claude understands 'track for decisions not curiosity' without extended justification
Move the detailed scoring rubric and event taxonomy tables to separate reference files, keeping only summaries in the main skill
Add concrete validation commands or tool-specific debugging steps (e.g., GA4 DebugView usage, GTM preview mode checks)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful content but is verbose in places—the extensive tables, repeated section headers, and some redundant explanations (e.g., listing what 'not conversions' are when Claude would understand) add unnecessary tokens. The 'Core Principles' section restates concepts that could be more compact. | 2 / 3 |
Actionability | Provides good conceptual frameworks and checklists but lacks executable code examples. The GA4/GTM section says 'prefer GA4 recommended events' and 'push clean dataLayer events' without showing actual implementation code. The validation section lists what to check but not how to check it. | 2 / 3 |
Workflow Clarity | Clear phased workflow (Phase 0 → Phase 1) with explicit gates ('If verdict is Broken, stop and recommend remediation first'). The scoring system provides clear decision points, and the required output format ensures structured deliverables. Validation steps are explicitly listed. | 3 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but everything is inline in one large document. The 'Related Skills' section at the end suggests connections but the main content could benefit from splitting detailed reference material (like the full scoring rubric or event taxonomy) into separate files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.