What problem does it solve? Code reviews often miss breakage that grep and diff inspection cannot reveal, such as library behavior, timing, wire formats, and downstream consumers. This Skill finds the hidden impact of a change before it ships and replaces confident-sounding writeups with proof obtained by executing real code. ## Core Features & Use Cases - Hidden Impact Analysis: Traces risks that symbol search misses, including library internals, pinned versions, microtask timing, DB columns, API payloads, and code several hops downstream. - Evidence-Ranked Safety Facts: Identifies the single fact a change's safety depends on and escalates it through a five-level confidence ladder, from assertion to reproduction in the running app. - Executable Proof: Writes and runs a small script or test that calls the real shipped code and fails loudly if the safety claim is wrong. - Use Case: Before merging a diff that touches a shared cache-invalidation call, ask for its blast radius to get the one safety fact proven by a runnable script, a list of confirmed risks with file:line citations, and the cheapest pre-merge test. ## Quick Start Ask the AI to analyze the blast radius of your current diff and prove the key safety assumption by running the real code.
