why

Use this Skill with a target file, symbol, or design decision. It anchors the investigation in git history, then spawns parallel investigators across available MCP sources—tickets, docs, chat, observability, error tracking, and analytics—and returns a cited, confidence-calibrated answer.

It covers seven categories: source control history via git and gh, issue trackers, long-form documents, team chat, infrastructure observability, error tracking, and product analytics warehouses. Source control always runs; the others run only when a matching MCP is available.

Partially. The source control investigator always runs using git and gh, but the other six categories require matching MCP servers. Missing categories are reported as explicit gaps in the Sources Consulted section rather than silently skipped.

The how skill explains what code does and how it works at runtime. The why skill explains the forces that shaped it—design rationale, business constraints, incidents, and rejected alternatives—using historical evidence rather than code reading.

Hedged phrasing is deliberate confidence calibration. Direct claims with citations use confident language, while inferences must be hedged so readers can distinguish documented facts from interpretation and avoid acting on guesses.