Skip to content
SkillScript-led6,858 tokens in use

story-review

Reviews novel chapters from several angles at once and returns a prioritized fix list with quoted evidence, in full, lean or solo mode.

8,793 stars on the repository MIT Licensezenstory-ai/oh-story-claudecode · skills/story-review
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-review costs

91tokens idle
6,858tokens in use
15,944tokens, 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, scripts/tracking_commit.py, scripts/wordcount_core.py.

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
  • Output7/15
  • Size13/15
  • Resources12/15

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 146
  • 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-review coordinates an adversarial review of a web novel manuscript. In full mode it starts four reviewer roles for structure, characters, prose and consistency; lean mode uses two; solo mode has the current session do a basic review when the roles are missing.

It loads a general quality rubric plus a platform table for Fanqie, Qidian or short-story platforms, runs local checks for punctuation, AI-style phrasing and repeated text, and writes a report in author language: must fix, should fix, optional. It never edits the manuscript.

What You Get

  • A report with must-fix, should-fix and optional sections, each point backed by a quote from the chapter
  • Platform-aware criteria for Fanqie, Qidian and short-story platforms
  • Local check results for punctuation, AI-style phrases and repeated or cut-off text
  • A one-line technical note recording the mode used and any fallback
  • Batch review state for multi-chapter or whole-volume reviews

Common Use Cases

  • Reviewing a freshly written chapter for pacing, motive and continuity problems
  • Checking a first-three-chapters opening against platform expectations
  • Reviewing a whole volume in batches and tracking issues across batches

What Makes It Unique

Reviewers are told to find problems and to stay away from endorsing the draft. Findings use a fixed severity schema, and disagreements between reviewers are shown in the report so the author sees both views. The skill degrades safely when agents are missing and ships an embedded rubric, so reviews always run with standards.

Under The Hood

The skill reads your manuscript, settings, outlines and tracking files, and may start sub-agents that read files by path. It runs three bundled Node scripts locally that check punctuation, AI-style patterns and degeneration in chapter files and only report. It does not change the manuscript; in full or lean mode it may revise tracking files, and batch reviews write a state file in a review folder. It makes no web requests.

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