What problem does it solve? When reviewing a pull request that claims to fix a bug in the LinkedIn MCP server, maintainers need proof the fix actually works against the real LinkedIn site, not just a code read. This Skill checks out the PR locally, restarts the MCP server on the PR branch, replays the exact tool call that failed on main, diffs the outputs, and audits the diff against the project's scraping rules. ## Core Features & Use Cases - Baseline Replay: Reads the on-main baseline and tool-call metadata written by /2-repro-issue from /tmp, then replays the identical MCP tools/call over streamable HTTP against the PR branch. - Verdict Classification: Classifies the PR as fixes, fixes with concerns, does not fix, cannot run, or cannot verify (skill limitation), with evidence lines from the output diff. - Scraping Rule Audit: Flags locale-dependent string matching, LinkedIn CSS-class selectors, multi-navigation section mappings, and missing tests per CLAUDE.md rules. - Use Case: A maintainer asks "does PR #498 fix issue #470?" — the Skill fetches the PR, runs the same get_person_profile call that failed on main, diffs the JSON responses, and reports a verdict with merge recommendation. ## Quick Start Verify whether PR #498 fixes the issue reproduced earlier by running this Skill with the PR number.