Skip to content
Get packs

Story Review Editor

Reviews fiction chapters for plot, character, consistency and prose problems, with quotes from the text.

Source Download skill
Repository
zenstory-ai/oh-story-claudecode
Stars
8,255
Licence
MIT
Files
15 files

What it does

Once installed, the agent acts as a fiction editor. When you ask it to review a chapter, it checks structure, character motivation, dialogue, consistency with the story's established facts, and prose quality against written rubrics, then reports problems ranked by severity with quotes from your text. It can coordinate several sub-reviewer agents in parallel, or fall back to a single-pass review if those helpers are missing.

Great for

  • Web-novel authors who want a structured second read before publishing
  • Writers checking consistency across chapters of a long serial
  • Authors who prefer suggestions with quoted evidence rather than rewrites

Skip it if

  • Final judgement of literary quality: the rubrics are checklists and can flag stylistic choices that are intentional
  • Fully automatic rewriting: the skill is written to report and suggest, not to silently change the manuscript

Try asking

  • “/story-review lean review chapter 12 for consistency with the earlier timeline”
  • “审查一下这一章的对话和角色动机”
  • “/story-review solo check the opening three chapters for genre clichés”
Step-by-step guide: how to use Story Review EditorInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the MIT licence and an attribution note.

    story-review.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip story-review.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip story-review.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the agent the chapter text and, if available, the story bible or earlier chapters so consistency checks have evidence
  • Use solo mode for a quick pass and full or lean mode when you have the multi-agent setup installed
  • Treat severity labels as advice; you decide which findings to act on

What's inside

  • references/agent-prompts.md
  • references/banned-words.md
  • references/batch-review.md
  • references/expression.md
  • references/narrative-focus.md
  • references/quality-rubric.md
  • references/review-tracking.md
  • references/rubrics/fanqie.md
  • references/rubrics/qidian.md
  • references/rubrics/zhihu.md
  • references/solo.md
  • references/story-logic.md
  • references/style-resolution.md
  • references/tracking-initialization.md
  • SKILL.md

Redistributed unmodified from zenstory-ai/oh-story-claudecode under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.