analytics-product

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

Quality

57%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/analytics-product/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is genuinely actionable, with several executable, copy-paste-ready Python examples for product analytics, but it is held back by generic boilerplate filler and a monolithic structure with no progressive disclosure of reference material into separate files.

Suggestions

Remove the generic boilerplate sections (When to Use, Do Not Use, Best Practices, Common Pitfalls, Related Skills, Limitations) or replace their filler text with domain-specific guidance to improve conciseness.

Split the large inline reference material (the full AURI_EVENTS taxonomy and the A/B-test significance calculator) into a references/ file with a one-line pointer from SKILL.md to improve progressive disclosure.

Add explicit validation checkpoints to the dashboard/north-star and event-tracking sections (e.g., verify events appear in PostHog, confirm SQL returns expected WAC range) to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	The technical core is lean and code-forward, but generic boilerplate sections ("When you need specialized assistance with this domain", "Combine with other complementary skills", and four identical "Complementary skill for enhanced analysis" entries) add tokens Claude does not need, matching 'mostly efficient but includes some unnecessary explanation'.	2 / 3
Actionability	Provides multiple complete, executable Python functions with real imports (PostHog track/identify, cohort retention, north star SQL, feature flags, scipy A/B-test significance calculator) and a concrete event-taxonomy dict, matching 'fully executable code/commands; copy-paste ready'.	3 / 3
Workflow Clarity	The 'Otimizando O Funil' section gives a clear 6-step sequence with a significance checkpoint (p-value < 0.05), but the skill as a whole is a reference catalog where most sections (event taxonomy, dashboard, north star) lack explicit sequencing and validation, matching 'steps listed but validation gaps'.	2 / 3
Progressive Disclosure	Content is organized into clear headed sections, but it is a ~285-line monolithic SKILL.md with all reference material (full event taxonomy, A/B-test calculator) inline and no bundle files or one-level-deep references, matching 'some structure but content that should be separate is inline'.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 is a strong topic enumeration for product analytics but reads as a keyword list rather than an action-and-trigger description. It lacks an explicit 'Use when...' clause, which caps both completeness and trigger quality at 2.

Suggestions

Add an explicit trigger clause such as 'Use when configuring event tracking, building conversion funnels, analyzing cohorts/retention, or defining a north star metric in PostHog or Mixpanel.'

Reframe the topic nouns as concrete actions (e.g., 'Configure event tracking, build conversion funnels, compute cohort retention, and define north star metrics') to lift specificity toward 3.

Add common natural-language variations users might say (e.g., 'product analytics', 'event tracking', 'A/B test significance') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and many specific topics/tools ("PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards"), but these are topic nouns rather than concrete verb-actions like 'extract', 'fill', 'merge', so it does not reach the multiple-concrete-actions anchor of 3.	2 / 3
Completeness	Clearly answers 'what' (analytics de produto with listed tools and concepts) but provides no explicit 'when'/'Use when...' trigger clause; per the guidelines a missing Use-when clause caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant natural terms users would say (PostHog, Mixpanel, funnels, cohort, retencao, north star metric, OKRs, dashboards) but lacks an explicit 'Use when...' phrasing and common variations, so it matches 'some relevant keywords but missing common variations' rather than the full coverage of 3.	2 / 3
Distinctiveness Conflict Risk	Named tools (PostHog, Mixpanel) give it a clearer niche than generic analytics, but the topic-list framing could still overlap with growth or marketing analytics skills, matching 'somewhat specific but could still overlap' rather than the clearly-distinct-niche anchor of 3.	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Commit: 6b7501e

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.