Name: product-analytics
Rating: 64 (1 reviews)
Author: alirezarezvani

product-analytics

Use when defining product KPIs, building metric dashboards, running cohort or retention analysis, or interpreting feature adoption trends across product stages.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is product-analytics in alirezarezvani/claude-skills

Quality

Content

72%Weight 40%Scale 1-5

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

A well-structured, highly actionable skill body with concrete CLI tooling and stage-specific KPI guidance. Its weaknesses are missing validation checkpoints in the batch analysis workflow and broken references to bundle files that are not actually shipped.

Suggestions

Add explicit validation/feedback steps to the analysis workflow — e.g., verify CSV schema before running, and sanity-check retention outputs (no values > 100%, cohort sizes sane) before interpreting.

Ship the referenced bundle files (references/metrics-frameworks.md, references/dashboard-templates.md, scripts/metrics_calculator.py) or remove the dangling references so navigation is not broken.

Consolidate the "Dashboard Design Principles" section with Workflow step 3 to remove the redundancy and tighten token use.

Dimension	Reasoning	Score
Conciseness	The body is dense and practical with no basic-concept padding, but the "Dashboard Design Principles" section partially restates Workflow step 3 ("Design dashboard layers"), so it is efficient with minor redundancy rather than fully lean.	4 / 5
Actionability	The Tooling section provides copy-paste-ready CLI commands with exact flags and full CSV input formats for retention, cohort, and funnel analysis, and the KPI/cohort guidance names specific frameworks and metrics — fully executable coverage of common cases.	5 / 5
Workflow Clarity	The main Workflow and Cohort Analysis Method are clearly sequenced into numbered steps, but the analysis-over-CSV batch operation lacks explicit validation/verification checkpoints (e.g., verify CSV columns, sanity-check outputs); per the batch-operation cap this cannot exceed 3, and checkpoints are only implicit via "distinguish signal from noise" and "flag drop points".	3 / 5
Progressive Disclosure	Sections are well organized and references are clearly signaled (a "See:" block plus a Tooling script), but the referenced bundle files (references/metrics-frameworks.md, references/dashboard-templates.md, scripts/metrics_calculator.py) do not exist in the bundle, so navigation is broken, and detailed KPI/dashboard content that belongs in those references is inlined.	3 / 5
	Total	15 / 20 Passed

Description

80%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, third-person description with concrete actions and an explicit trigger clause that clearly establishes the product-analytics niche. Its main limitation is structural: the capability statement is embedded in the "Use when" clause rather than standing alone, and a few natural synonyms are absent.

Suggestions

Lead with a standalone "what" clause (e.g., "Define, track, and interpret product metrics across product stages.") before the "Use when" trigger to make both halves explicit.

Add common synonyms a user would actually say — "metrics", "funnel analysis", "North Star / AARRR" — to broaden trigger-term coverage.

Add a brief disambiguating phrase distinguishing product KPIs from SaaS financial metrics to reduce overlap with finance/saas-metrics-coach.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions ("defining product KPIs", "building metric dashboards", "running cohort or retention analysis", "interpreting feature adoption trends") with comprehensive coverage of the product-analytics domain, matching the anchor-5 example's breadth.	5 / 5
Completeness	A strong explicit "Use when" trigger is present and the listed actions double as the "what", but the what is fused into the when clause rather than stated as a separate declarative capability, so it falls short of the anchor-5 structure.	4 / 5
Trigger Term Quality	Natural terms ("product KPIs", "metric dashboards", "cohort or retention analysis", "feature adoption trends") are present, but common synonyms such as "metrics", "funnel analysis", or framework names a user might say are missing, landing it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The product-analytics framing (KPIs, cohorts, retention, adoption by stage) carves a clear niche, but there is minor overlap risk with closely related skills like finance/saas-metrics-coach, keeping it at mostly-distinct rather than minimal-conflict.	4 / 5
	Total	17 / 20 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
referenced_paths_exist	Referenced path issues: 9 missing	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/product-analytics/SKILL.md
Commit: 19392f7

Reviewed: ~3 hours 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.