inkos-story-deslop

Diagnose and revise generic, template-like AI prose while preserving author voice.

9.4k|1.8k|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/Narcooo/inkos --skill inkos-story-deslop
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: inkos-story-deslop
Source: https://github.com/Narcooo/inkos/tree/main/packages/core/skills/inkos-story-deslop
Command: npx skills add https://github.com/Narcooo/inkos --skill inkos-story-deslop

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AI-assisted fiction often reads as generic, mechanical, or over-explained, and naive fixes like deleting banned words destroy legitimate stylistic choices. This Skill identifies real prose defects—unsupported conclusions, emotion labels without scene evidence, canned transitions, summary replacing scenes—while protecting the author's voice, rhythm, and intentional repetition.

Core Features & Use Cases

  • Semantic Diagnosis: Evaluates passages by story function and effect rather than keyword counting, distinguishing genuine defects from deliberate voice choices.
  • Voice-Preserving Revision: Repairs prose by restoring concrete cause and character-specific behavior while keeping plot facts, viewpoint, pacing, and strong original lines intact.
  • Audit-First Workflow: In an active book project, audits unclear scope before rewriting and routes authorized rewrites through the reviser instead of pasting unsaved replacements.
  • Use Case: A chapter feels flat and AI-generated. The Skill audits each suspect passage against a rubric (function, evidence, dialogue motivation, rhythm), then produces a revision brief that fixes summary-style narration without flattening the narrator's voice.

Quick Start

Ask the agent to review this chapter for generic or AI-sounding prose and revise the weak passages while keeping my voice and plot facts unchanged.

Frequently Asked Questions about inkos-story-deslop

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I remove AI-sounding prose from my novel without losing my voice?

Diagnose each suspect passage by its story function and evidence rather than deleting flagged words. Repair by restoring concrete cause and character-specific behavior while preserving plot facts, viewpoint, pacing, and strong original lines.

What are the signs of AI-generated writing in fiction?

Common signs include unsupported conclusions, emotion labels without scene evidence, generic transitions, symmetrical canned phrasing, repeated interpretation, decorative detail, summary replacing scenes, and dialogue that only transfers information.

Should I delete repeated words and transitions to fix AI writing?

No. Repetition can be rhythm, abstraction can be intentional, and short sentences can create pressure. Mechanical deletion of transitions, metaphors, or flagged words damages legitimate voice choices without fixing the underlying defect.

When should I audit instead of rewriting a chapter directly?

Audit first whenever the revision scope is unclear in an active book project. Authorized rewrites should go through the reviser; pasting a replacement chapter into chat does not save it to the book.

What are the limitations of semantic prose cleanup?

It targets semantic defects, not grammar or spelling, and it cannot decide voice questions for the author. Judgments about intentional repetition or abstraction still require reading the passage in the context of the whole story.