Data

Competitive Teardown produces systematic competitor analyses with scoring rubrics, feature matrices, SWOTs, pricing deconstruction, UX audits, and action plans. Use it for roadmap reviews, battle cards, or new-market research.

Customer Success Manager analyzes customer health, churn risk, and expansion opportunities from JSON inputs using deterministic scoring models. Use it for SaaS customer success reviews, renewal prioritization, and executive reporting.

Marketing Data Analysis turns raw marketing and commerce data into descriptive, diagnostic, predictive, and prescriptive insight. Use it for GA4, ads platforms, Shopify, CRM exports, or spreadsheets when you need to understand what changed and what to do next.

Performance Evaluation diagnoses poor marketing results by tracing issues across tracking, delivery, creative, landing pages, offer, and audience quality. Use it when CPA rises, ROAS drops, or a screenshot of metrics needs a root-cause review and 48-hour action plan.

Revenue Operations analyzes pipeline coverage, forecast accuracy, and GTM efficiency for SaaS revenue teams. Use it to review sales health, forecast performance, and revenue efficiency metrics.

Social Listening monitors brand, competitor, and category mentions across key channels and tracks sentiment, trends, and early warning signals. Use it to produce weekly or monthly listening reports and spot content opportunities from real conversations.

Competitive Analysis helps you compare direct, indirect, and emerging competitors across features, UX, users, business, and technology. Use it during product planning or iteration to find gaps and differentiation opportunities.

Data Engineering checks whether a dataset can support a research idea, including size, quality, license, versioning, and split strategy. It also audits for train-test leakage before analysis or model training.

Light Figure plans and renders publication-ready scientific figures that support specific claims. It is used when turning analysis results into paper figures, checking visual honesty, and reviewing rendered charts for layout issues.

Result Analysis interprets experiment outputs with significance tests, effect sizes, confidence intervals, and multiple-comparison correction. It is used when results need to be tied to claims, evidence strength, and reproducibility without p-hacking.

Data Analysis & Statistics helps explain statistical concepts, test selection, regression, and data visualization using real datasets. It focuses on statistical reasoning, assumptions, and interpretation across tools like Python, R, SPSS, and Stata.

Session Deep Dive analyzes high-signal sessions identified by /session-scan, using subagents and precomputed metrics to produce qualitative reports and cross-session synthesis. Use it after scanning sessions to compare patterns against known findings.