Prose and voice
30%Precision, clarity, rhythm, dialogue, imagery and tonal control across the complete book.
Two rankings, two different questions
Literary assessment and reader response remain separate.
The default shelf ranks books by an automated assessment of the complete manuscript. Readers can instead choose the reader ranking, built from private questionnaires by people who show credible knowledge of the book.
Story craft
20%Conflict, development, emotional effect and whether the story fulfils its own intentions.
Characterisation
15%Distinctiveness, depth, consistency and credible change.
Structure and pacing
15%Shape, momentum, balance and control from beginning to end.
Originality
10%Freshness of conception, treatment and authorial choices.
Coherence and execution
10%Internal consistency and the technical control needed for an uninterrupted read.
The literary ranking
Every complete book is assessed under the same genre-aware rubric. AI-assisted and entirely human-written books are treated identically. Popularity, sales, advertising and the author’s identity do not affect the result. A low rating does not itself disqualify a complete, readable book.
The reader ranking
Readers never enter a number. They answer questions based on how much they actually read. Specific memories, character observations and internally consistent answers establish reading confidence; liking the book is never evidence of having read it. A thoughtful negative response counts exactly as a positive one.
Private answers, public aggregates
Reader answers and email addresses are never published. A public reader score appears only after at least three credible questionnaires, limiting the influence of any single response.