Non Fiction Revision

For non-fiction authors stuck in revision hell where every fix breaks something else. This diagnostic maps the four levels where non-fiction operates: thesis, structure, evidence, and pedagogy. It walks you through figuring out whether your problem is a weak central argument, broken chapter logic, insufficient support, or reader comprehension issues. The real value is in cascade detection, helping you see how changing your thesis invalidates chapters or how new evidence accidentally raises the bar for your other claims. Think of it as a dependency mapper for book arguments. Worth using when beta readers report confusion or when you sense your revisions are making things worse instead of better.

skills.sh installs: 331
GitHub stars: 182
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add jwynia/agent-skills --skill non-fiction-revision --agent claude-code

Installs into .claude/skills of the current project.

Files

Non-Fiction Revision Diagnostic

Purpose

Diagnose and guide revisions in non-fiction books (business, self-help, academic, popular science, memoir). Non-fiction operates across multiple levels simultaneously—thesis, structure, evidence, pedagogy. Changes at one level cascade to others. This skill identifies which level needs attention and prevents revision damage.

Quick Reference

State	Signal	Core Issue
NR1	Thesis feels unclear or weak	Conceptual level problem
NR2	Arguments don't build logically	Structural problem
NR3	Claims lack adequate support	Evidence problem
NR4	Readers report confusion	Pedagogical problem
NR5	Sources outdated or weak	Credibility problem
NR6	Changes causing new problems	Cascade failure