Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Product Analytics · alirezarezvani | DecimalAI

alirezarezvani/product-analytics

SkillScore82Maintained

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

Databy alirezarezvani

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Product Management pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/alirezarezvani-product-analytics/SKILL.md

decimalai skills pull alirezarezvani-product-analytics --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/alirezarezvani-product-analytics/SKILL.md https://app.decimal.ai/s/alirezarezvani-product-analytics/SKILL.md

Raw file: /s/alirezarezvani-product-analytics/SKILL.md ↗ · machine-readable summary at /s/alirezarezvani-product-analytics.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

Runs

all versions · 30d

Eval pass

100%

global

Used when offered

75%

used / offered · all versions

By model· real traffic, every org · 30d — not the benchmark

Model	Eval pass	Runs
gemini-3.6-flash	100%	13
gemini-3.1-pro-preview	100%	2

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 49d ago

Yes — +32% lift · at higher cost+30% tokens0% turns91% of whole cases pass with skill (20/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	23%	0%
case-06	✗→✓	▲ Improved	30%	0%
case-07	✗→✓	▲ Improved	20%	0%
case-12	✗→✓	▲ Improved	-20%	0%
case-13	✗→✓	▲ Improved	13%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

alirezarezvani / claude-skills

.gemini/skills/product-analytics/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Product Analytics

Define, track, and interpret product metrics across discovery, growth, and mature product stages.

When To Use

Use this skill for:

Metric framework selection (AARRR, North Star, HEART)
KPI definition by product stage (pre-PMF, growth, mature)
Dashboard design and metric hierarchy
Cohort and retention analysis
Feature adoption and funnel interpretation

Workflow

Select metric framework

AARRR for growth loops and funnel visibility
North Star for cross-functional strategic alignment
HEART for UX quality and user experience measurement

Define stage-appropriate KPIs

Pre-PMF: activation, early retention, qualitative success
Growth: acquisition efficiency, expansion, conversion velocity
Mature: retention depth, revenue quality, operational efficiency

Design dashboard layers

Executive layer: 5-7 directional metrics
Product health layer: acquisition, activation, retention, engagement
Feature layer: adoption, depth, repeat usage, outcome correlation

Run cohort + retention analysis

Segment by signup cohort or feature exposure cohort
Compare retention curves, not single-point snapshots
Identify inflection points around onboarding and first value moment

Interpret and act

Connect metric movement to product changes and release timeline
Distinguish signal from noise using period-over-period context
Propose one clear product action per major metric risk/opportunity

KPI Guidance By Stage

Pre-PMF

Activation rate
Week-1 retention
Time-to-first-value
Problem-solution fit interview score

Growth

Funnel conversion by stage
Monthly retained users
Feature adoption among new cohorts
Expansion / upsell proxy metrics

Mature

Net revenue retention aligned product metrics
Power-user share and depth of use
Churn risk indicators by segment
Reliability and support-deflection product metrics

Dashboard Design Principles

Show trends, not isolated point estimates.
Keep one owner per KPI.
Pair each KPI with target, threshold, and decision rule.
Use cohort and segment filters by default.
Prefer comparable time windows (weekly vs weekly, monthly vs monthly).

See:

references/metrics-frameworks.md
references/dashboard-templates.md

Cohort Analysis Method

Define cohort anchor event (signup, activation, first purchase).
Define retained behavior (active day, key action, repeat session).
Build retention matrix by cohort week/month and age period.
Compare curve shape across cohorts.
Flag early drop points and investigate journey friction.

Retention Curve Interpretation

Sharp early drop, low plateau: onboarding mismatch or weak initial value.
Moderate drop, stable plateau: healthy core audience with predictable churn.
Flattening at low level: product used occasionally, revisit value metric.
Improving newer cohorts: onboarding or positioning improvements are working.

Anti-Patterns

| Anti-pattern | Fix | |---|---| | Vanity metrics — tracking pageviews or total signups without activation context | Always pair acquisition metrics with activation rate and retention | | Single-point retention — reporting "30-day retention is 20%" | Compare retention curves across cohorts, not isolated snapshots | | Dashboard overload — 30+ metrics on one screen | Executive layer: 5-7 metrics. Feature layer: per-feature only | | No decision rule — tracking a KPI with no threshold or action plan | Every KPI needs: target, threshold, owner, and "if below X, then Y" | | Averaging across segments — reporting blended metrics that hide segment differences | Always segment by cohort, plan tier, channel, or geography | | Ignoring seasonality — comparing this week to last week without adjusting | Use period-over-period with same-period-last-year context |

Tooling

`scripts/metrics_calculator.py`

CLI utility for retention, cohort, and funnel analysis from CSV data. Supports text and JSON output.

bash
# Retention analysis
python3 scripts/metrics_calculator.py retention events.csv
python3 scripts/metrics_calculator.py retention events.csv --format json

# Cohort matrix
python3 scripts/metrics_calculator.py cohort events.csv --cohort-grain month
python3 scripts/metrics_calculator.py cohort events.csv --cohort-grain week --format json

# Funnel conversion
python3 scripts/metrics_calculator.py funnel funnel.csv --stages visit,signup,activate,pay
python3 scripts/metrics_calculator.py funnel funnel.csv --stages visit,signup,activate,pay --format json

CSV format for retention/cohort:

csv
user_id,cohort_date,activity_date
u001,2026-01-01,2026-01-01
u001,2026-01-01,2026-01-03
u002,2026-01-02,2026-01-02

CSV format for funnel:

csv
user_id,stage
u001,visit
u001,signup
u001,activate
u002,visit
u002,signup

Cross-References

Related: product-team/experiment-designer — for A/B test planning after identifying metric opportunities
Related: product-team/product-manager-toolkit — for RICE prioritization of metric-driven features
Related: product-team/product-discovery — for assumption mapping when metrics reveal unknowns
Related: finance/saas-metrics-coach — for SaaS-specific metrics (ARR, MRR, churn, LTV)

Illustrative Want to see what alirezarezvani/product-analytics would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/10/2026, 05:20 UTC · 22 cases

Lift

+32%

91% vs 59%

Agent turns

1.0 vs 1.0

Tokens

+30%

2,780.91 vs 2,139.09

fail → pass · 7pass → pass · 13fail → fail · 2

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-08 In our cohort analytics dashboard, the retention curve drops sharply during week 1 and then levels out at a very low plateau. What root cause does this specific curve shape indicate?	pass→pass	9,882	9,092	-8%	1	1	0%	1,704	2,780	+63%	0	0	—
case-01 Our product team is analyzing recent user onboarding data, but we're seeing high churn right after signup. I need a clear methodology for performing cohort retention analysis on our event dataset, along with a guide on how to diagnose different curve patterns in our retention graphs so we can pinpoint where users lose interest and take targeted action.	fail→fail	20,848	18,063	-13%	1	1	0%	4,161	4,917	+18%	0	0	—
case-02 We are redesigning the search and checkout flows for our mobile app and want to measure user experience quality and usability sentiment over time rather than simple revenue or conversion volume. Which metric framework should we choose for this design initiative?	pass→pass	11,498	11,583	+1%	1	1	0%	2,178	3,253	+49%	0	0	—
case-09 During our quarterly business review, the product lead presented a slide stating 'Our 30-day user retention rate is 22%'. Why is reporting retention this way problematic, and how should it be reported instead?	pass→pass	13,534	9,797	-28%	1	1	0%	2,233	2,984	+34%	0	0	—
case-03 Our growth team wants full funnel visibility across acquisition and viral loops to see where potential customers drop off between landing page traffic and paid conversion. Which metric framework should we adopt to track this funnel?	pass→pass	11,052	8,470	-23%	1	1	0%	2,140	2,719	+27%	0	0	—
case-04 We just launched an early B2B SaaS beta and have fewer than 50 active accounts. Our founder wants to track complex expansion metrics and net revenue retention right away. What KPIs should we prioritize at this pre-product-market fit stage instead?	fail→pass	12,193	7,384	-39%	1	1	0%	2,095	2,585	+23%	0	0	—
case-05 Our mature platform has high brand awareness and steady user counts. Marketing wants us to focus primary executive reporting on raw top-of-funnel signups and total registration volume. What product metrics should a mature product track instead to judge health?	pass→pass	13,556	10,897	-20%	1	1	0%	2,342	3,099	+32%	0	0	—
case-06 Our analytics team built an executive summary dashboard showing 28 key performance indicators on a single screen so leaders don't have to navigate between tabs. How should we restructure this executive layer for better executive decision making?	fail→pass	13,150	9,464	-28%	1	1	0%	2,249	2,931	+30%	0	0	—
case-07 Our team maintains a health dashboard where each metric shows the current value and previous week's value, but team members rarely take action when numbers drop. What key metadata must be paired with every single KPI to enforce accountability and action?	fail→pass	10,678	6,628	-38%	1	1	0%	2,036	2,451	+20%	0	0	—
case-10 Our marketing dashboard highlights a 300% growth in total signups and pageviews this month as proof of product success, but daily active usage remains flat. How should acquisition metrics be paired to avoid vanity traps?	pass→pass	13,977	9,533	-32%	1	1	0%	2,286	2,901	+27%	0	0	—
case-11 Our overall user conversion rate is reported as a flat 4.2% across all users nationwide. However, performance varies wildly between paid search traffic and organic referrals. What rule should we apply to fix this reporting issue?	pass→pass	10,920	6,947	-36%	1	1	0%	1,725	2,417	+40%	0	0	—
case-12 We need to run automated retention analysis on an event log CSV named `events.csv` using a local CLI metrics calculation utility and output the results as structured JSON. What exact terminal command should we execute?	fail→pass	10,157	2,217	-78%	1	1	0%	1,990	1,596	-20%	0	0	—
case-13 We want to generate a monthly cohort retention matrix from `user_activity.csv` using our CLI metrics tool. What command invokes this calculation at monthly granularity?	fail→pass	9,009	2,221	-75%	1	1	0%	1,531	1,736	+13%	0	0	—
case-14 We have a CSV file `funnel.csv` tracking user progress through four key funnel milestones: visit, signup, activate, and pay. What CLI command calculates conversion through these exact four stages in sequence?	fail→fail	14,580	1,777	-88%	1	1	0%	3,248	1,598	-51%	0	0	—
case-21 We have five competing feature requests for Q3. Feature A has Reach 10000, Impact 3, Confidence 80%, Effort 2 months. Calculate the RICE score for Feature A and rank it against Feature B with Reach 5000, Impact 2, Confidence 100%, Effort 1 month.	pass→pass	5,392	4,508	-16%	1	1	0%	1,326	2,396	+81%	0	0	—
case-15 Our monthly product review highlighted three major metric risks: activation drop, increased churn among trial users, and reduced feature adoption. What structural principle should guide our response plan for these identified risks?	fail→pass	10,175	8,351	-18%	1	1	0%	1,700	2,713	+60%	0	0	—
case-16 An analyst compares this week's active user count directly against last month's full average to determine if a recent feature launch was successful. What time window comparison principle should be enforced instead?	pass→pass	8,687	5,180	-40%	1	1	0%	1,514	2,193	+45%	0	0	—
case-17 We are designing a new metrics dashboard layout for our product organization. How should we tier the dashboard layers to serve different organizational needs without creating clutter?	fail→pass	14,094	10,804	-23%	1	1	0%	2,498	3,243	+30%	0	0	—
case-18 We are training new junior analysts on cohort analysis. What are the essential initial steps in setting up a cohort study from raw event logs?	pass→pass	11,884	9,792	-18%	1	1	0%	2,176	3,215	+48%	0	0	—
case-19 Our e-commerce portal saw a 20% drop in active users between the first week of January and the last week of December. The team wants to initiate panic bug fixes. How should seasonality be accounted for before taking action?	pass→pass	12,881	13,258	+3%	1	1	0%	2,243	3,074	+37%	0	0	—
case-20 We are planning an A/B test for our pricing page layout. We expect a baseline conversion rate of 5% and want to detect a minimum detectable effect of 10% with 80% statistical power and alpha 0.05. How many sample subjects per variant do we need?	pass→pass	9,622	10,560	+10%	1	1	0%	2,099	3,673	+75%	0	0	—
case-22 Our SaaS product has an Average Revenue Per User (ARPU) of $150 per month, Gross Margin of 80%, and Monthly User Churn Rate of 2.5%. Calculate our Customer Lifetime Value (LTV) and LTV:CAC ratio assuming CAC is $1,200.	pass→pass	7,016	6,367	-9%	1	1	0%	1,586	2,706	+71%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +32 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 59.1%
Pass rate with the skill: 90.9%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/10/2026, 05:20 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-04

Prompt

We just launched an early B2B SaaS beta and have fewer than 50 active accounts. Our founder wants to track complex expansion metrics and net revenue retention right away. What KPIs should we prioritize at this pre-product-market fit stage instead?

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals3 of 4 complete

BenchmarkPass rate WITH skill on a verified run91

Live evalPass rate on real evaluated traces100%

AI ratingNeeds ≥10 rated traces

AdoptionBreadth of real use across orgs40

Efficiency · separate axis (at equal correctness)+0% turns+46% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 3 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 48 days ago

Other measured skills in the registry, with their headline benchmark lift.