Skills

Automate finance reporting

Google

Use to connect a number source, map an export into the finance ledger, or QA a sheet: the column mapping, the dedupe key, the load summary, and the checks that must pass before a read ships.

Deal economics and pricing guardrails

Use for the money side of a deal: the deal P&L, margin floors and discount bands, approval routing, the concession log, and the mix impact of a price change.

SaaS and GTM finance

Use for the ARR bridge, MRR movement, retention and churn math, renewal base, pipeline coverage, and go-to-market efficiency reads; payback questions go to the unit economics skill.

65 installedView

Unit economics and ROI

Use for customer acquisition cost, lifetime value, payback, contribution margin, net present value, internal rate of return, and fund-or-kill calls on a bet.

Cash, treasury and FX

Google

Use for cash-flow forecasts, runway, the 13-week cash view, working capital, vendor commitments in their renewal window, currency exposure, and covenant headroom.

Budget vs actuals and reforecast

Google

Use when the user asks about budgets, pacing against plan, forecasts, re-forecasts, annual plans, or where a period lands at the current run rate.

Getting started

Google, HubSpot, Notion, Slack, and Stripe

Use on the first conversation with Daniel, or whenever no finance preferences are saved yet: learn the revenue model, the books, the thresholds that count as too far, and where the numbers live, then get to a first read.

by AutoGPTFrom phuryn/pm-skills/pm-data-analytics/skills/cohort-analysis

User cohort analysis

Perform cohort analysis on user engagement data — retention curves, feature adoption trends, and segment-level insights. Use when analyzing user retention by cohort, studying feature adoption over time, investigating churn patterns, or identifying engagement trends.

47 installedView

by AutoGPTFrom anthropics/knowledge-work-plugins/data/skills/data-visualization

Data visualization

Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.

Experiment readout

Write an experiment readout with assignment checks, metric definitions, sample sizes, uncertainty, practical effect, and limits.

51 installedView

Funnel conversion analysis

Measure funnel conversion with explicit eligibility, event order, windows, identity rules, drop-off checks, and segment evidence.

Cohort and retention analysis

Build cohort and retention views with explicit entry events, return events, windows, eligibility, censoring, and sample sizes.

49 installedView

Metric movement analysis

Explain why a metric moved by decomposing its definition, population, segments, timing, and data pipeline into testable hypotheses.

Metric anomaly detection

Flag metric anomalies against declared baselines while separating data faults, expected seasonality, and real business changes.

49 installedView

Weekly KPI digest

Turn approved weekly metrics into a short digest of material movements, evidence, hypotheses, owners, and next checks.

Metric definition and data quality

Test metric definitions and source data for freshness, coverage, duplicates, missing values, impossible values, and drift.

50 installedView

KPI analysis getting started

Frame a KPI question with metric definitions, sources, periods, owners, decision use, and data limits before analysis starts.

Content

Spokesperson briefing

Prepare a spokesperson with the outlet, reporter, messages, likely questions, and lines to avoid.

14 installedView

Content

Holding statement draft