ev-adversarial-audit

Run this skill for Phase 3 of the evidence verification pipeline — the adversarial audit step. Use when you need to check the evidence data lake for bad data before ingestion: dead links, wrong URL formats (tree/ vs blob/), subjective wording ("elite", "high-quality"), stale migration notes, or skills whose star tier doesn't match their classified evidence level. Triggers on phrases like: "audit the data lake", "adversarial check", "ev-adversarial-audit", "check for noise in evidence", "flag bad evidence", "run the audit phase", "quality check the tier files", or any reference to Phase 3 of the pipeline. Deploys 4 parallel adversarial reviewer subagents across the tier files, then a 5th synthesis subagent to merge findings, and appends results to the daily source report.