Skip to content
SkillScript-led4,732 tokens in use

story-long-write

Plans and writes a long web novel step by step: settings, volume outlines, chapter outlines, drafted chapters, daily batches and revisions with tracking.

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

131tokens idle
4,732tokens in use
7,943tokens, 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/author_memory_commit.py, scripts/build_architect_brief.py, scripts/build_writer_prompt.py, scripts/check-ai-patterns.js, scripts/check-degeneration.js, scripts/check-outline-contract.js, scripts/check-outline-copy.js, scripts/convert_outline_format.py, scripts/normalize-punctuation.js, scripts/outline_view.py, scripts/storyctl.py, scripts/style-whitelist.js, scripts/template_fence.py, 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 →
Fair
  • Frontmatter8/15
  • Structure8/25
  • Examples3/15
  • Output5/15
  • Size15/15
  • Resources6/15

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 →
Needs attention
  • Writes files−8

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

    scripts/author_memory_commit.py, line 188
  • Hidden characters−20

    characters that render as nothing or reorder the text

    scripts/build_architect_brief.py, line 79
  • Hidden characters−20

    characters that render as nothing or reorder the text

    scripts/build_writer_prompt.py, line 74
  • Runs shell commands−5

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

    scripts/build_writer_prompt.py, line 400
  • Hidden characters−20

    characters that render as nothing or reorder the text

    scripts/check-outline-contract.js, line 121
  • Hidden characters−20

    characters that render as nothing or reorder the text

    scripts/check-outline-copy.js, line 50
  • Hidden characters−20

    characters that render as nothing or reorder the text

    scripts/template_fence.py, line 34

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-long-write acts as a writing coach for a long web novel. It handles structure talks, outlines, chapter outlines, single chapters, daily batches of two or three chapters, and revisions, always stopping at the level you asked for.

Before writing it reads the reference files for the current moment, then drafts through a writer role, checks length and AI-style patterns with local scripts, and records every chapter in a tracking state with foreshadowing, character status and timelines.

What You Get

  • Genre positioning, characters and settings built through confirmation points
  • Volume outlines and chapter outlines that are validated by scripts
  • Drafted chapters with length, pattern and punctuation checks
  • A tracking state that regenerates context, foreshadowing, character and timeline files after each chapter
  • Revision flows for rewriting a chapter and an author memory file for your writing habits

Common Use Cases

  • Starting a new web novel and getting settings, a volume outline and the first ten chapter outlines
  • Writing the next chapter of a serial with the correct foreshadowing and character state
  • Running a daily batch of chapters and fixing one chapter after reader feedback

What Makes It Unique

The writing flow is gated: it reads a fixed list of method files per moment, refuses to write a chapter when its outline or the previous tracking is missing, and never moves past the level the author requested. Story decisions such as new main-plot events, golden finger rules or foreshadowing payoffs are put to the author. Tracking is committed through one script so state files stay consistent.

Under The Hood

The skill is a router over many reference files, loaded per moment, with writer and outline roles delegated to sub-agents when the host supports them. It runs local Python and Node scripts to build prompts and briefs, view volume outlines, count words, check AI patterns, repeated text and punctuation, convert outline formats, and commit tracking state. It reads and writes project files such as settings, outlines, chapters and tracking. 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