Foresight

Estimate likely outcomes before committing to a plan, change, or launch.

What This Skill Does

Foresight produces bounded forecasts with explicit uncertainty to guide decisions. It is NOT:

Preflight checks: Verifying prerequisites before executing a known action (disk space, backups, connection strings). Those are safety gates, not forecasts.
Diagnosis/Debugging: Finding what's broken right now (null pointers, deprecated APIs). Those are root-cause analyses, not predictions.
Monitoring: Watching real-time metrics or alerting on thresholds. Those are observability tasks, not forward-looking estimates.
Reconnaissance: Gathering facts about competitors or systems. Intelligence gathering feeds foresight but isn't foresight itself. Key distinction: If the user wants to know "what will likely happen if we choose X," use Foresight. If they want to know "is it safe to run X now," "what's broken," or "what are they doing," use a different spell. In this grimoire, Foresight is treated as a metaphorical spell with a shipping-now delivery profile. Canonical reference input: Foresight (spell).

Activate this spell when the user asks for a forward-looking, probability-weighted forecast to inform a decision. Look for:
Explicit choice between options ("should we X or Y?", "migrate vs stay", "build vs buy")
Time-bounded outcome requests ("over the next 12 months", "by Q3", "18-month trajectory")
Risk/uncertainty language ("risk-weighted", "confidence level", "probability", "best case/worst case", "weal or woe")
Decision frameworks with explicit unknowns ("what would change your recommendation?", "decisive unknowns")