Agent Skills › Narcooo/inkos › inkos-story-import

inkos-story-import

GitHub

用于将已有小说手稿导入为可编辑的 InkOS 项目，支持章节导入、素材摄取及参考管理。自动重构设定与续写工程，区分母本参考，确保内容安全且保留不确定性标记。

packages/core/skills/inkos-story-import/SKILL.md Narcooo/inkos

Trigger Scenarios

用户希望导入已有小说文本需要逆向重建设定与续写工程区分母本参考或管理书籍引用

Install

npx skills add Narcooo/inkos --skill inkos-story-import -g -y

More Options

Non-standard path

npx skills add https://github.com/Narcooo/inkos/tree/master/packages/core/skills/inkos-story-import -g -y

Use without installing

npx skills use Narcooo/inkos@inkos-story-import

指定 Agent (Claude Code)

npx skills add Narcooo/inkos --skill inkos-story-import -a claude-code -g -y

安装 repo 全部 skill

npx skills add Narcooo/inkos --all -g -y

预览 repo 内 skill

npx skills add Narcooo/inkos --list

SKILL.md

Frontmatter

{
    "name": "inkos-story-import",
    "description": "导入已有小说、逆向重建设定与续写工程，并区分母本参考。Use for importing manuscripts or attaching external canon safely."
}

Story import and reconstruction

Use this skill when the user wants an existing manuscript to become an editable, continuable InkOS project.

Determine the user's intent before acting:
- import_chapters: the text becomes real chapters in the active book and InkOS reconstructs state.
- ingest_material: the text remains reference material only.
- manage_book_reference: an archived source should guide future chapters for user-stated purposes.
Preserve chapter order with natural chapter-number ordering. Confirm the continuation point when the active book already has chapters.
Never treat a user's own manuscript as an imitation target by default.
After import, report imported chapter count, detected gaps, reconstructed facts, uncertainties, and the next safe continuation point.
Do not invent missing canon to make the project look complete. Mark uncertainty for later confirmation.
For fan-fiction canon extraction, preserve world rules, character identity and voice evidence, key-event order, information boundaries, capability limits, and observable style traits. Cite only supplied evidence; mark absent material as unknown instead of inferring it.
Respond in the user's language.