Writing Principles

Loads the fiction layer on top of the base LLM writing guidance. The core insight is that your helpfulness training actively works against fiction craft: you want to explain emotions, resolve tension, and clarify subtext, but readers get reward from doing that interpretive work themselves. It maps four reward channels (transportation, aesthetic, social simulation, flow) and diagnoses why passages feel flat by checking which channel broke. Includes a punctuation tells section warning against em dashes as AI residue. The failure modes doc has fix patterns for common issues. Use this when drafting prose, critiquing scenes, or figuring out why something reads as overexplained despite technically correct writing.

skills.sh installs: 1.1K
GitHub stars: 575
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add haowjy/creative-writing-skills --skill writing-principles --agent claude-code

Installs into .claude/skills of the current project.

Files

Writing Principles

Trust the Reader

The reader is an active collaborator. They reconstruct emotions from behavior, infer motives from action, hold tension across scenes, fill gaps the text leaves open, and make assumptions about what's coming next. That work is where the reward lives: reconstruction, inference, anticipation.

In conversation, explaining, resolving, clarifying and completing is what helps; it is what you were trained to do well. In fiction the same moves do work the reader wanted to do themselves, and the reading experience loses what they would have found. The failure modes below are all forms of this: not trusting the reader to interpret an emotion, hold an ambiguity, follow subtext, or tolerate unresolved tension.

Trust doesn't mean obscurity. Readers also need coherent narrative, stable geography, and enough access to model characters. The discipline is knowing when to leave space and when to orient.