KPI Review
Turns a current KPI snapshot into variances, drivers, evidence gaps, decisions, owners, and the next measurement plan.
Reporting, metric review, anomaly detection, maintenance, and system health.
Turns a current KPI snapshot into variances, drivers, evidence gaps, decisions, owners, and the next measurement plan.
Investigate a metric anomaly from data the user supplies by confirming it is real before explaining it. Checks measurement and instrumentation first, sizes the move against a robust same-weekday baseline, localizes it by segment (splitting a rate change into mix and rate effects), lines it up against a timeline of releases, campaigns, outages and calendar events, ranks competing hypotheses with supporting and refuting evidence, and orders the cheapest discriminating next checks with a severity and escalation call. Use when someone asks why a metric spiked or dropped, whether a change is real or noise, which segment drove it, or what to check next. Do not use for a recurring weekly review (use weekly-analytics-insight-report), a deep funnel step diagnosis (use diagnose-conversion-funnel), or a live outage (use coordinate-production-incident).
Investigates metric anomalies with hypotheses, impacted segments, likely causes, and next checks.
Audit dependency health, upgrade risk, security alerts, and maintenance load from the manifests, lock files, advisory reports, and release history the user supplies. Separates direct from transitive and runtime from build or dev exposure, classifies the version gap by semver jump, checks each advisory against the resolved version and its fix path, rates maintenance signals (active, slow, stale, abandoned), applies hard gates before a points score, batches upgrades by risk, estimates ongoing maintenance load, and recommends patch now, schedule, pin, replace, remove, or accept with an expiry. Use when someone asks for a dependency audit, whether packages are outdated or abandoned, how risky an upgrade is, what to do about a pile of security alerts, or how much upkeep dependencies cost. Do not use for turning findings into a ranked backlog (use maintenance-backlog), a cloud infrastructure review (use audit-cloud-infrastructure), or vetting an imported skill's source (use import-provenance-checker).
Audits dependency health, upgrade risk, security alerts, maintenance load, and recommended actions.
Classifies bounded HouseManager transactions and bills into the household finance taxonomy using only the category and tag IDs supplied with each run.
Researches current real-world prices for a described household project and returns a structured ballpark budget with low/likely/high totals, line items, assumptions, questions, and cited sources.
Turn system health findings (audit output, incident reviews, dependency or security alerts, cost and performance reports, recurring support pain) into a prioritized maintenance backlog with owners and acceptance criteria. Normalizes findings into one record, merges duplicates by root cause, assigns a priority band through hard gates before scoring, ranks within bands by value per effort, splits oversized items, writes testable acceptance criteria, names an owner role and review date, fits a stated capacity, and records risk-accepted items with an expiry. Use when someone asks to turn an audit or health check into a backlog, rank technical debt or upkeep work, decide what maintenance to do first, or write acceptance criteria for maintenance tickets. Do not use for one library upgrade (use dependency-health), a metric that moved unexpectedly (use anomaly-triage), a cloud infrastructure review (use audit-cloud-infrastructure), or a live incident (use coordinate-production-incident).
Turns system health findings into a prioritized maintenance backlog with owners and acceptance criteria.
Post-run Retrospective workflow that groups context collection, production, review, and packaging tasks into one deliverable.
Plans and summarizes retention/cohort analysis with segments, lifecycle stages, and intervention ideas.
Plans and summarizes retention/cohort analysis with segments, lifecycle stages, and intervention ideas.
Produce a weekly insight report from product or marketing analytics the user supplies. Fixes a small metric set with definitions and owners, compares each metric with last week and with a usual range built from prior weeks so noise is not reported as news, ranks three to five insights by impact, confidence and actionability, hands anomalies to a first check, assigns owner-and-date actions, closes out last week's actions, and states data-quality caveats. Every claim is labeled observation, interpretation, or recommendation. Use when someone asks for a weekly analytics report, a Monday metrics summary, weekly insights and actions from a dashboard export, or a recurring product or marketing performance review. Do not use for digging into one metric anomaly (use anomaly-triage), a communications or media performance report (use report-communications-performance), or designing an experiment (use ab-test-setup).
Reviews product or marketing analytics and produces weekly insights, anomalies, and actions.
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
Turns a minimized, privacy-filtered HouseManager timeline into a concise evidence-backed week or month family briefing.