glendigity

Process review comments from portable html-collab files. Use when a user provides or mentions a `.review.html` file produced by `html-collab`, asks to summarize review feedback, revise the underlying report, merge reviewed copies, extract an agent brief, or unwrap final HTML.

Obtain a focused cold-oracle review from GPT-5.6 Sol with Intelligence set to Pro in standard ChatGPT Chat, preserve the exact exchange, and reconcile its advice against local evidence. Use when the user asks to consult, ask, review with, or get a second opinion from Sol Pro or ChatGPT Pro about code, architecture, plans, specifications, debugging, or project approach; also use by default instead of spawning a subagent whose only role would be analysis, critique, planning, counterreview, or a second opinion.

App evaluation methodology for web applications. Explore apps as a target user, classify findings across 5 categories (Broken, Confusing, Inconsistent, Rough, Observation), and suggest Playwright regression tests.