Skip to content
SkillScript-led3,987 tokens in use

Story Deslop

Find and fix AI-sounding passages in web novel chapters across wording, scene focus and story logic, while keeping the author's style and plot facts.

8,793 stars on the repository MIT Licensezenstory-ai/oh-story-claudecode · skills/story-deslop
npx skills add zenstory-ai/oh-story-claudecode -y -g
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Story Deslop costs

90tokens idle
3,987tokens in use
20,579tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/check-ai-patterns.js, scripts/check-degeneration.js, scripts/normalize-punctuation.js, scripts/style-whitelist.js.

Touches

shelldetectedwrites filesdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure16/25
  • Examples12/15
  • Output0/15
  • Size15/15
  • Resources13/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 45
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/normalize-punctuation.js, line 82

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity28
  • Momentum40

Story Deslop cleans AI flavor out of Chinese web novel text. It first runs local scripts that flag stock AI phrasing, dash overuse, repeated or cut-off text and placeholder leaks, and reports line numbers and fragments. Then it reads the chapter in three layers: expression (word choice, sentence shape, voice), narrative focus (what each scene spends its words on) and story logic (motive, cause, who knows what and when).

It can only diagnose, or it can rewrite. Wording and emphasis are fixed directly, while changes to events, motives or outcomes are proposed as options until you approve them. Before editing a file it saves a copy of the original, and afterwards it rescans, normalizes punctuation and reports what changed.

What You Get

  • A diagnosis in three layers with each issue tied to the original text and a suggested fix
  • A rewritten chapter that keeps events, foreshadowing and information order
  • A backup of the original under the book’s work folder, so an edit can be undone
  • A before and after sample list and any open story gaps that need your decision

Common Use Cases

  • Polishing a chapter that reads like an AI summary
  • Checking a draft before publishing without changing the plot
  • Fixing repeated phrases, cut-off endings and dash overuse
  • Reviewing only specific paragraphs or problem types

What Makes It Unique

It treats AI flavor as a problem of wording, emphasis and story cause, not a list of banned words. The scripts only locate blocking issues. A zero-hit result never counts as a pass, and plot changes need your approval and go through the tracked long-form flow.

Under The Hood

The skill runs bundled Node scripts on your chapter files from the shell: a pattern checker, a degeneration checker and a punctuation normalizer that rewrites the file in place. It copies the original chapter into a backup folder inside the book before editing, and it may hand the editing to a narrative-writer helper agent. It reads a per-book whitelist file for phrases you chose to keep. It makes no network calls. It reads the book’s style, setting and outline files for context and writes the revised chapter back to the same path.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers