Story Review

This runs a multi-agent adversarial review of your story drafts. It spawns four parallel agents (story-architect, character-designer, narrative-writer, consistency-checker) that each tear into your content from different angles, then synthesizes their findings into a single report with severity ratings. You get three modes: full runs all four agents, lean runs just architecture and consistency checks, solo does basic format validation without spawning anything. It's explicitly designed to find problems, not validate correctness, and it handles platform-specific rubrics for Chinese web fiction sites like Qidian and Fanqie. The agents don't inherit context, so each gets a self-contained prompt with file paths. If agents disagree, it surfaces the conflict instead of auto-resolving, which is honest but means you're the tiebreaker.