lifesight

lifesight-anomaly-watch

Use when the user wants to find what changed, broke, spiked, or dipped in their marketing recently — "what moved last week", "what should I act on", "anything weird in the data", "what's up/down", "what moved more than 2 standard deviations", "surface opportunities", "what needs my attention". Produces a ranked, act-vs-noise triage of anomalies with a recommended action for each. Routed to from the `lifesight` router after the workspace is calibrated.

lifesight-board-briefing

Use when the user wants a board-ready or executive summary of marketing impact from Lifesight — "brief the board", "draft the marketing slide for the board", "exec summary of what's working", "what do I present to leadership", "board deck using last month's iROAS", "the QBR marketing section". Produces a tight, strategic, proof-led narrative (or slide-ready text) for a CMO / marketing leader. Routed to from the `lifesight` router after the workspace is calibrated.

lifesight-calibration

Use the FIRST time you operate a Lifesight workspace, when no lifesight-workspace-profile exists yet, or when the user asks to "set up", "calibrate", "onboard", "configure for my account", or "recalibrate" Lifesight. Also use when the active workspace changed, when channel names or models look unfamiliar, or when the user wants to set guardrails (iROAS floor, max per-channel change, locked channels). Produces the per-workspace profile that every other Lifesight skill reads.

lifesight-cfo-translation

Use when the user needs to translate marketing measurement into finance / P&L language, or defend marketing spend to finance — "what do I tell the CFO", "prove our ROI to finance", "is our spend defensible", "translate this into business terms", "build the finance case for the budget", "marketing's contribution to the P&L". Also the right spoke when the user IS the CFO / VP Finance asking whether marketing spend is working. Routed to from the `lifesight` router after the workspace is calibrated.

lifesight-channel-deep-dive

Use when the user wants to go deep on ONE channel — saturation, marginal ROI, response curve, headroom, or a what-if: "should I increase TikTok", "where's the headroom on Meta", "is Linear TV saturated", "what happens if I cut Google by 20%", "how efficient is this channel really". The analyst's home spoke — tightest data guardrails. Routed to from the `lifesight` router after the workspace is calibrated.

lifesight-core

Use at the start of ANY conversation that will call a Lifesight MCP tool (ask_mia, query_ad_data, search_knowledge_base, get_current_budget, list_models, set_active_workspace). Load this BEFORE the first data call. Triggers: budget optimization, iROAS / iRevenue, marketing measurement, incrementality, MMM, channel performance, "what's working", board prep, CFO reporting, anomaly detection, scenario planning — any request that touches Lifesight measurement data. Also load whenever a Lifesight tool errored, returned a wall of data, stalled mid-question, or leaked internal field names.

Web & Frontend Listed

lifesight-experiment-design

Use when the user wants to prove or validate causality with an experiment — "is X actually incremental", "prove this channel works", "design a geo-lift test", "set up a holdout", "run an incrementality test", "what should I test next", "read my experiment results", "did the test work", "validate the optimization before we commit". Covers both designing tests and interpreting results. Routed to from the `lifesight` router after the workspace is calibrated.

lifesight-forecast-scenario

Use when the user wants to project outcomes or compare paths forward — "forecast my revenue", "what will next quarter look like", "what budget do I need to hit $4M", "compare current vs +15% spend", "what if I shift budget to TikTok", "model this scenario", "target KPI planning", "project the impact before I commit". Routed to from the `lifesight` router after the workspace is calibrated.

lifesight-measurement-coach

Use when the user wants to understand a measurement concept or methodology rather than run their data — "how does incrementality work", "what is MMM", "explain saturation / marginal ROI", "why causal instead of attribution", "what's a geo-lift test", "how do the methodologies calibrate each other", or any "what does X mean" about marketing measurement. Educational, knowledge-base-led. Routed to from the `lifesight` router.

lifesight-rendering

Use when presenting ANY Lifesight measurement output to a user — budget allocations, iROAS / iRevenue, channel performance, optimizations, forecasts, saturation, anomalies, board or CFO summaries, or any numbers, tables, or charts that came from the Lifesight MCP. Load it in parallel with whatever Lifesight skill is doing the work. Triggers: any moment you are about to show the user a result with channel names, percentages, currency, or a recommendation.

lifesight

Use at the start of any Lifesight measurement conversation, or whenever a user asks a marketing-measurement question without a clear job in mind — "what's working", "help me with my budget", "what does Lifesight say about…", "where do I start". Establishes who the user is, what decision they're making, and which workspace + model to use, then routes to the right Lifesight skill. Also the entry point when the user names a Lifesight job (board briefing, budget optimization, CFO summary, anomaly check, channel deep-dive) — it resolves context, then hands off.