analytics-product

Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.

Quality

41%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/analytics-product/SKILL.md

Quality

Discovery

54%

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 effectively establishes a clear niche in product analytics with strong trigger terms including specific tool names and domain concepts. However, it reads as a keyword/topic list rather than describing concrete actions the skill performs, and critically lacks any 'Use when...' guidance to help Claude know when to select it.

Suggestions

Add explicit 'Use when...' clause, e.g., 'Use when the user asks about product analytics, tracking events, building funnels, analyzing retention, or setting up dashboards in PostHog or Mixpanel.'

Convert the topic list into concrete action descriptions, e.g., 'Configures event tracking, builds conversion funnels, defines user cohorts, analyzes retention curves, and creates product dashboards in PostHog and Mixpanel.'

Dimension	Reasoning	Score
Specificity	The description names the domain (product analytics) and lists relevant concepts (events, funnels, cohorts, retention, north star metric, OKRs, dashboards), but doesn't describe concrete actions — it reads more like a topic list than a list of specific capabilities (e.g., 'create funnels', 'build dashboards', 'define cohorts').	2 / 3
Completeness	The description answers 'what domain' but lacks any explicit 'when to use' clause or trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'what' is also weak (topic listing rather than clear capabilities), this scores a 1.	1 / 3
Trigger Term Quality	Includes strong natural keywords users would actually say: PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs, dashboards de produto. These cover a wide range of terms a user working in product analytics would naturally use.	3 / 3
Distinctiveness Conflict Risk	The combination of specific tool names (PostHog, Mixpanel) and domain-specific terms (funnels, cohorts, retention, north star metric) creates a clear niche that is unlikely to conflict with other skills.	3 / 3
	Total	9 / 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 contains some useful, concrete code examples (PostHog integration, A/B testing, cohort retention) but is severely undermined by excessive length, generic boilerplate sections, and lack of organization. The content is heavily tailored to a specific product ('Auri') which limits reusability, and many sections (Best Practices, Common Pitfalls, Limitations) are filled with vague, unhelpful platitudes that waste tokens.

Suggestions

Remove all generic boilerplate sections (When to Use, Do Not Use, Common Pitfalls, Best Practices, Limitations) — they contain no domain-specific value and waste tokens.

Split the monolithic content into separate reference files (e.g., EVENTS.md for taxonomy, AB_TESTING.md for significance calculations, RETENTION.md for cohort analysis) and keep SKILL.md as a concise overview with links.

Define or remove undefined functions like `calculate_wow_growth` and `show_new_onboarding` to ensure all code examples are complete and executable.

Add explicit validation/verification steps to workflows — e.g., after implementing event tracking, verify events appear in PostHog; after running A/B tests, validate sample size requirements before drawing conclusions.

Dimension	Reasoning	Score
Conciseness	The skill is bloated with generic boilerplate sections (When to Use, Do Not Use, Common Pitfalls, Best Practices, Limitations) that add no value and contain only vague platitudes. The quote, the extensive event taxonomy specific to 'Auri', and benchmark tables add bulk without being universally actionable. Many sections explain things Claude already knows.	1 / 3
Actionability	The code examples for PostHog tracking, cohort retention, A/B test significance, and feature flags are mostly executable and concrete. However, several pieces are incomplete (e.g., `calculate_wow_growth` is referenced but never defined, `show_new_onboarding` is undefined), and the commands table lists slash commands with no implementation details.	2 / 3
Workflow Clarity	The funnel optimization section provides a reasonable 6-step process, but lacks explicit validation checkpoints or error recovery loops. The overall skill reads more like a reference catalog than a guided workflow — there's no clear sequence for when/how to apply these analytics tools together.	2 / 3
Progressive Disclosure	The skill is a monolithic wall of text with no references to external files for detailed content. All code examples, benchmarks, event taxonomies, and formulas are inlined in a single file, making it overwhelming. The Related Skills section mentions other skills but provides no meaningful navigation or context for when to use them.	1 / 3
	Total	6 / 12 Passed

Validation

90%

Warnings & errors only

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: sickn33/antigravity-awesome-skills
Commit: 1a9f5ac

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.