Claude Skills by Evil-Bane

Universal, multi-agent, VISION-VERIFIED audit that makes any app, website, tool, CLI, API, or MCP server genuinely great. Fans out one agent per surface and exercises EVERY single control (button, field, toggle, menu, tab, swipe, long-press, drag) for real — screenshotting before/after and looking at the result — across every lens: does each control actually work + persist + sync, the "does the UI lie?" trust audit, UI/interaction craft & motion, fresh-eyes customer journeys, competitive tear...

Autonomous, long-running loop that drives a goal to completion while the user is away. Repeats AUDIT -> FIX -> VERIFY -> COMMIT (calling the /audit skill each round) until "nothing left to do" or the user interrupts, keeping a durable backlog + journal so nothing is ever lost, scheduling its own wake-ups for true overnight cadence, and pinging the user on blockers (device unplugged, build red, a decision needed). Trigger when the user says "work overnight", "keep going until I wake up / until...