story-review coordinates an adversarial review of a web novel manuscript. In full mode it starts four reviewer roles for structure, characters, prose and consistency; lean mode uses two; solo mode has the current session do a basic review when the roles are missing.
It loads a general quality rubric plus a platform table for Fanqie, Qidian or short-story platforms, runs local checks for punctuation, AI-style phrasing and repeated text, and writes a report in author language: must fix, should fix, optional. It never edits the manuscript.
What You Get
- A report with must-fix, should-fix and optional sections, each point backed by a quote from the chapter
- Platform-aware criteria for Fanqie, Qidian and short-story platforms
- Local check results for punctuation, AI-style phrases and repeated or cut-off text
- A one-line technical note recording the mode used and any fallback
- Batch review state for multi-chapter or whole-volume reviews
Common Use Cases
- Reviewing a freshly written chapter for pacing, motive and continuity problems
- Checking a first-three-chapters opening against platform expectations
- Reviewing a whole volume in batches and tracking issues across batches
What Makes It Unique
Reviewers are told to find problems and to stay away from endorsing the draft. Findings use a fixed severity schema, and disagreements between reviewers are shown in the report so the author sees both views. The skill degrades safely when agents are missing and ships an embedded rubric, so reviews always run with standards.
Under The Hood
The skill reads your manuscript, settings, outlines and tracking files, and may start sub-agents that read files by path. It runs three bundled Node scripts locally that check punctuation, AI-style patterns and degeneration in chapter files and only report. It does not change the manuscript; in full or lean mode it may revise tracking files, and batch reviews write a state file in a review folder. It makes no web requests.