cs-product-analyst

Product analytics agent for KPI definition, dashboard setup, experiment design, and test result interpretation. Use when a product question needs numbers — e.g., defining activation/retention KPIs and a dashboard spec for a new feature, or sizing an A/B test and judging whether the result is significant enough to ship.

Quality

91%

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

Quality

Content

82%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.

The body is a well-structured orchestration overview with executable commands and clearly sequenced workflows. It loses a little to duplicated references and the absence of explicit validation feedback loops, but it is concise and actionable.

Suggestions

Remove the duplicate References section at the bottom (the same links already appear under Skill Integration) or consolidate them into one labeled block.

Add an explicit validation/verification checkpoint in Workflow 2 (e.g., confirm the CSV has the expected user_id/timestamp/event columns and sanity-check retention numbers before annotating).

Deduplicate the Purpose paragraph against the frontmatter description so the body does not restate the same capability list.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows, but the References section duplicates the Skill Integration links and the Purpose sentence restates some description content, leaving minor trimmable redundancy.	4 / 5
Actionability	Provides copy-paste-ready commands with real flags (e.g. 'sample_size_calculator.py --baseline-rate 0.12 --mde 0.02 --mde-type absolute --daily-samples 800') and concrete 'metrics_calculator.py retention\|cohort\|funnel' subcommands covering the common cases.	5 / 5
Workflow Clarity	Three workflows are clearly sequenced with Goal/Steps/Expected Output, and Workflow 3 includes a ship/iterate/kill decision checkpoint, but there are no explicit validate→fix→retry feedback loops (acceptable for a non-destructive analysis skill, so it stays above the cap but below a 5).	4 / 5
Progressive Disclosure	Well-organized sections point one level deep to external skill SKILL.md files via clearly signaled markdown links, with the body acting as an orchestration overview; minor gaps are the duplicated reference links and no separate bundle files to verify against.	4 / 5
	Total	17 / 20 Passed

Description

100%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.

The description is strong: it states concrete capabilities, gives a natural 'Use when' trigger with realistic examples, and carves out a distinct quantitative-measurement niche. It is concise rather than padded and uses appropriate third-person voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'KPI definition, dashboard setup, experiment design, and test result interpretation' — plus concrete worked examples (defining activation/retention KPIs, sizing an A/B test), giving comprehensive capability coverage.	5 / 5
Completeness	Explicitly answers both 'what' (analytics agent for KPI/dashboard/experiment work) and 'when' ('Use when a product question needs numbers') with concrete trigger phrases and examples.	5 / 5
Trigger Term Quality	Natural product terms a user would actually say are well covered with synonyms — 'KPI', 'activation/retention', 'dashboard', 'A/B test', 'significant enough to ship' — and tied to an explicit 'Use when a product question needs numbers' trigger.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (quantitative product measurement) with distinct triggers like A/B-test sizing and significance judgment, minimizing overlap with adjacent skills; the body even disambiguates from cs-product-manager.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing, 4 suspicious	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/cs-product-analyst/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.