analytics-tracking
Design, audit, and improve analytics tracking systems that produce reliable, decision-ready data.
43
30%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-analytics-tracking/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a clear domain (analytics tracking) and lists high-level actions, but lacks the concrete specificity and explicit trigger guidance needed for reliable skill selection. The absence of a 'Use when...' clause is a significant gap, and the trigger terms could be expanded to cover more natural user language variations.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about event tracking, analytics instrumentation, tracking plans, data collection validation, or debugging analytics implementations.'
Include more specific concrete actions, e.g., 'Create tracking plans, validate event schemas, debug data collection pipelines, audit tag manager configurations, review analytics instrumentation code.'
Add common tool/platform keywords users might mention, such as 'Google Analytics', 'Segment', 'Mixpanel', 'GTM', 'event tracking', 'UTM parameters', or 'conversion funnels'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (analytics tracking systems) and lists some actions (design, audit, improve), but these actions are fairly high-level and don't describe concrete specific tasks like 'create event schemas' or 'validate tracking implementations'. | 2 / 3 |
Completeness | Describes what the skill does (design, audit, improve analytics tracking systems) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when' clause caps completeness at 2, and since the 'what' is also somewhat vague, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'analytics', 'tracking', and 'data', but misses common user-facing variations such as 'event tracking', 'Google Analytics', 'Mixpanel', 'UTM parameters', 'conversion tracking', 'instrumentation', or 'telemetry'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on 'analytics tracking systems' provides some specificity, but terms like 'data' and 'analytics' are broad enough to potentially overlap with data analysis, business intelligence, or general data engineering skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a comprehensive analytics knowledge base than a focused, actionable skill for Claude. It over-explains general analytics concepts Claude already understands while under-delivering on concrete, executable guidance (no code examples, no specific tool commands). The phased structure provides some workflow clarity, but the extreme verbosity and monolithic format significantly reduce its effectiveness as a skill file.
Suggestions
Cut 60-70% of the content by removing explanations of concepts Claude already knows (what conversions are, why data quality matters, basic privacy principles) and focus only on the specific scoring methodology and output format.
Add concrete, executable examples: a sample dataLayer.push() call for GTM, a GA4 event configuration snippet, or a real filled-out tracking plan table showing the expected output.
Split the scoring rubric, event taxonomy, and tool-specific guidance into separate referenced files to improve progressive disclosure and reduce the main skill's token footprint.
Add explicit validation commands or scripts (e.g., 'Use GA4 DebugView to verify event X fires with properties Y') instead of listing validation types as abstract bullet points.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines, explaining many concepts Claude already knows (what qualifies as a conversion, what PII is, basic UTM rules, privacy principles). Extensive sections like 'Core Principles' and 'Event Model Design' describe general analytics knowledge rather than providing novel, actionable instructions. Much of this could be condensed to 1/3 the length. | 1 / 3 |
Actionability | The skill provides structured frameworks (scoring index, event taxonomy, output tables) which give some concrete guidance, but lacks executable code, specific tool commands, or copy-paste ready implementations. The GA4/GTM section is notably vague ('Prefer GA4 recommended events', 'Push clean dataLayer events') without actual code examples for dataLayer pushes or GTM configurations. | 2 / 3 |
Workflow Clarity | There is a clear phased sequence (Phase 0 → Phase 1 → design → implementation) with a gate condition ('If verdict is Broken, stop'), which is good. However, validation steps are listed as bullet points without specific commands or tools, and there are no explicit feedback loops for error recovery during implementation. The validation section says 'required' but doesn't specify how to actually perform each check. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no bundle files to reference. All content—scoring rubric, event taxonomy, conversion strategy, GA4 guidance, UTM rules, privacy, validation—is inlined in a single file. The 'Related Skills' section references other skills but the core content itself would benefit greatly from splitting into separate reference files (e.g., event taxonomy, scoring rubric, tool-specific guides). | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- boisenoise/skills-collections
- Commit
431bfad
- 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.