What problem does it solve? Code rarely explains why it exists. This Skill answers "why does this code work this way" questions by investigating the historical record—commits, PRs, tickets, design docs, chat threads, and production telemetry—instead of guessing from the code itself. ## Core Features & Use Cases - Parallel Evidence Gathering: Spawns one investigator per evidence category (source control, issue tracker, long-form docs, team chat, observability, error tracking, analytics warehouse), each mapped to an available MCP. - Confidence-Tiered Synthesis: A synthesizer agent classifies every claim as Direct, Supported, Inferred, Speculative, or Unknown, with citations and an explicit "What We Don't Know" section. - Use Case: Ask "why is this API response clamped to 100 items?" and receive a cited answer tracing the threshold to a PR discussion, a customer ticket, or a Datadog monitor—plus an honest note when no evidence exists. ## Quick Start Ask why the retry logic in the payment service was added and have the skill investigate the code's history across all available sources.
