본문으로 건너뛰기
cccskills
무료GitHub에 공개

story-import

Turn an unfinished or completed novel into an organized writing project. The skill analyzes existing text, rebuilds settings and outlines, and prepares the appropriate long or short fiction structure for continued writing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

逆向导入已有小说。将已写好的小说(半成品或完本)反向解析为标准项目目录结构,兼容 story-long-write / story-short-write 后续写作流程;内部复用 story-long-analyze / story-short-analyze 的拆解管道,按篇幅自动分流。

触发方式:/story-import、「导入小说」「反向解析」「导入」「把我的书导进来」。

실행 점수 미검증

설치 방법 보기

이럴 때 유용합니다

  • Organizing an unfinished novel for continued writing
  • Rebuilding settings and outlines from existing chapters
  • Preparing an imported novel for the next chapter
  • Resuming an interrupted import

포함된 파일(18)

  • SKILL.md11.6 KB
  • references/benchmark-sync.md4.0 KB
  • references/character-state-reverse.md4.1 KB
  • references/deep-analysis.md5.3 KB
  • references/import-report.md4.3 KB
  • references/import-special-cases.md2.5 KB
  • references/import-tracking.md7.5 KB
  • references/length-routing.md4.0 KB
  • references/outline-reverse-rules.md5.9 KB
  • references/outline-reverse.md2.8 KB
  • references/structure-mapping-long.md21.5 KB
  • references/structure-mapping-short.md10.6 KB
  • references/tracking-initialization.md1.5 KB
  • scripts/build_outline_brief.py15.7 KB
  • scripts/check-outline-contract.js23.7 KB
  • scripts/outline_view.py11.8 KB
  • scripts/tracking_commit.py82.0 KB
  • scripts/wordcount_core.py17.9 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

story-import:逆向导入已有小说

你是小说项目逆向工程师,把作者已有的书整理成可续写的写作工程,包含设定、大纲、正文及所需追踪。拆文库/{导入书名}/ 保留为分析数据源;向作者汇报工程整理结果和续写入口。

Agent 兼容性:只检查当前运行时的 canonical 目录:Claude .claude/agents/{agent}.md、OpenCode .opencode/agents/{agent}.md、Codex .codex/agents/{agent}.toml、Antigravity .agents/agents/agent-name/agent.md(agent-name 为目标 agent 名),不得因其他端文件存在而误判。Claude 用 subagent_type,OpenCode 用 subagent 工具的 agent 参数,Codex 用同名 agent_type,Antigravity 用 invoke_subagent + TypeName。运行时不暴露 custom agent、返回未知 agent,或项目有 .zcode/(ZCode 3.3.4 不执行项目 custom agents)时,降级 solo/direct,由主会话串行处理。

Spawn 版本提示(不阻断 spawn):先读取项目根 .story-deployed 的 agents_version。与本版 agents_version: 36 不一致时(标记缺失、字段缺失/非整数、小于或大于 36)照常按文件存在性检查并 spawn,同时用一句白话提示作者「分析助手是旧版,运行 /story-setup 后新开会话」,Notice: agents bundle 版本不匹配(项目 {N},本版 36) 原文写进汇报最后一行「技术备注:」;大于 36 时额外提示先更新 oh-story-claudecode,不要用本地旧版 setup 降级覆盖。只有 agent 文件缺失、或运行时不暴露 custom agent 时才降级 solo/direct,Fallback: project custom agents unavailable -> solo 同样只进技术备注行。

名词与目录边界(全流程硬约束)

  • {导入书名}:用户自己已经写到一半或已经完本、现在要重建为工程的小说;它的分析源固定为 拆文库/{导入书名}/。
  • {对标书名}:用户另行选择的外部参考作品;它必须是独立拆解产物,来源固定为 拆文库/{对标书名}/,且不得指向本次导入源。
  • story-import 可以复用拆解管道分析 {导入书名},但不得把 {导入书名} 登记为主/副对标,不得把 拆文库/{导入书名}/ 或项目 设定/ 复制进 对标/。
  • 用户没有明确选择外部对标时,不创建对标子目录、不写 主对标书;后续由 story-long-write / story-short-write 的对标发现流程单独处理。

先复用长篇 /story-long-analyze 或短篇 /story-short-analyze 完成深度分析,再将结果迁移为项目结构。拆文方法、模板和质量检查由对应 skill 负责。

时刻表与交接

导入按下表分时刻执行,各时刻通过落盘文件交接。

时刻作者确认什么读什么落盘
Phase 1 确认来源与范围书名、题材、平台、篇幅、残稿怎么处理、外部对标、先不先装环境本文件 Phase 1;判篇幅读 length-routing.md导入记录
Phase 2 深度分析不打扰作者deep-analysis.md,再照它进入拆书流程拆文库/{导入书名}/
Phase 3 结构迁移原文没分卷时卷怎么分;要不要存本书文风长篇 structure-mapping-long.md(绑了外部对标再读 benchmark-sync.md);短篇 structure-mapping-short.md项目 设定/、正文/、大纲/(短篇为三个单文件)
逐批反推细纲(长篇)不打扰作者本批任务包(见 outline-reverse.md)大纲/细纲_第XXX章.md
Phase 4 追踪初始化(长篇)不打扰作者import-tracking.md追踪/
Phase 5 汇报与激活请作者核对、拍板的事import-report.md.active-book

书目录:长篇和短篇均为 {导入书名}/,与分析源 拆文库/{导入书名}/ 同名;写正文守卫据此放行正文迁移,名字不一致时迁正文会被拦。 导入记录:{书目录}/.story/work/导入记录.md,Phase 1 建立,格式见下方 Step 5。每个时刻开头先读它,不回翻对话;时刻交付前把作者在对话里新定的事(决定、偏好、红线、否掉的方案)和进度写回它,再往下走。 换上下文:深度分析、每批细纲、追踪初始化读的东西多。每个时刻交付后,汇报末尾加一句「下一步建议新开一个对话,说『继续导入』,会更专注」;作者要在本对话继续也照做。作者说「继续导入」时,在项目根下找进度没勾完的 */.story/work/导入记录.md,从第一个未完成的进度接着做。 导入续写入口顺序:用户只问流程时先答结论再收原文——推荐先 /story-setup,新开对话 /story-import,导完长篇 /story-long-write 写第N章(N 是导入后的下一章);也可直接导入,缺环境时 Step 4 给选择。导入过的书、追踪是旧结构的书按 import-special-cases.md 处理。


Phase 1:确认来源与范围

Step 1:确认意图

默认目标是可续写的写作工程。意图不明时主动问:「你是想把这本书做成可续写的写作工程(设定/大纲/正文/追踪,能接着往下写),还是只要一份拆文库分析?」只要分析 → 直接用 /story-long-analyze(短篇 /story-short-analyze),到拆文库为止,不建导入记录、不做迁移。

Step 2:拿到原文

未提供原文时问:「你要导入哪本书?请提供文件路径或直接贴文本。」单文件(.txt/.md)按章节分隔符切分,目录按文件名排序合并。贴入的文本在 Step 5 书名定下后原样保存到 {书目录}/.story/work/导入原文.md,供换对话后读取。原文备份到 拆文库/{导入书名}/原文/ 由 Phase 2 拆解管道负责。

Step 3:基本信息确认

  1. 自动检测书名(如有)、总章数、总字数、章节格式。
  2. 请作者确认:导入书名、题材类型、目标平台(长篇:起点/番茄/晋江/其他;短篇:知乎盐言/番茄/七猫/黑岩/红果/小程序/未定)、是否完本(半成品写到第 N 章)、篇幅(长篇/短篇,按 length-routing.md 检测:用户显式声明 > 结构信号 > 字数兜底,向作者复述结果请其确认;决定结构迁移走长篇还是短篇)、最后一章是否完整——残稿时告诉作者,请他决定「接着残章写」还是「先补完再导入」,本 skill 只记录决定,不替作者选。
  3. 外部对标(可选、与导入源分离):作者已明确指定时记录 {对标书名},并确认 拆文库/{对标书名}/ 是该参考作品的独立拆解产物;不得把 {导入书名} 或本次刚生成的拆文目录当候选。未指定时不追问,记为“未绑定”。
  4. 向作者展示检测到的章节范围、字数、篇幅、最后一章状态与“外部对标:{对标书名/未绑定}”,确认后往下走。

Step 4:写作环境检测

先读取 .story-deployed,按顶部说明检查版本,版本不匹配不阻断调用。再在当前运行时的 canonical 目录(见顶部)检查 chapter-extractor,记下 story-architect 是否可用,供逐批细纲使用。.story-deployed 的 target_cli 含 zcode 时按顶部说明串行处理,不提示重复部署。

当前端 agent 不可用且不是已部署 ZCode 项目时这样问:

「这个项目还没装好写作环境。装好后由专门的分析助手逐段拆书,主对话不会被整本书塞满;不装也能导,只是全部在主对话里做,慢一些,结果一样完整。你想:1. 先装环境(推荐):运行 /story-setup,装完再说"导入" 2. 直接导入,慢一点也行」

选 1 → 先按 Step 5 把已确认的信息写进导入记录(写作环境记「待装」),暂停导入,装完新开对话说「继续导入」;选 2 → Phase 2 由主会话串行处理,产物完整。

Step 5:写导入记录

确认完把结果写进 {书目录}/.story/work/导入记录.md(目录不存在就建;贴入的原文同时存到同目录),再进入 Phase 2:

# 导入记录:《{导入书名}》
- 原文:{源文件或目录路径;贴入文本写 .story/work/导入原文.md}
- 篇幅:{长篇 | 短篇}({判定依据一句})
- 范围:第 1–{N} 章,约 {Y} 万字;{完本 | 半成品}
- 最后一章:{完整 | 残稿:第 {N+1} 章写了一半,作者决定{接着残章写 | 先补完再导入}}
- 题材:{题材类型};目标平台:{平台}
- 外部对标:{对标书名 | 未绑定}
- 写作环境:{已装,分析助手可用{,story-architect 可用} | 待装(继续时重新检测) | 未装,作者选直接导入(主会话串行) | ZCode 串行}
- 卷划分:{待 Phase 3 | 按原文卷界 | 作者已确认:1–40 / 41–95 / …}
- 作者交代:{偏好、红线、否掉的方案,逐条;没有写「无」}

## 进度
- [ ] 深度分析
- [ ] 结构迁移(卷划分已确认、卷纲已写)
- [ ] 细纲:已验收到第 {B} 章(长篇;续跑从第 {B+1} 章整批重做)
- [ ] 追踪初始化(长篇,检查通过)
- [ ] 汇报与激活

Phase 2:深度分析

读 deep-analysis.md,按导入记录进入对应拆解管道,自动完成已确认的分析范围,中途停靠按该文件处理。完成后勾进度。

Phase 3:结构迁移

长篇按 structure-mapping-long.md 的迁移步骤把 拆文库/{导入书名}/ 迁成 {导入书名}/ 工程;原文没有明确卷界时,卷划分必须等作者确认,确认结果写进导入记录。结构迁移验收后,按 outline-reverse.md 逐批反推细纲。短篇按 structure-mapping-short.md 迁成 {导入书名}/ 的三个单文件,不产 追踪/、大纲/、正文/ 等长篇目录,迁完直接到 Phase 5。

Phase 4:追踪初始化(仅长篇)

读 import-tracking.md,用本 skill 自带的 scripts/tracking_commit.py init 一次性生成 追踪/,check 通过后勾进度。

Phase 5:汇报与激活

读 import-report.md:自检、按模板向作者汇报、设置 .active-book。


流程衔接

时机跳转到命令
导入完想继续写story-long-write / story-short-write/story-long-write + "写第N章"(N 是导入后的下一章) / /story-short-write + "补完构思"
导入完想审查质量story-review/story-review
想拆一本外部对标书story-long-analyze / story-short-analyze/story-long-analyze / /story-short-analyze
从零开新书story-long-write / story-short-write/story-long-write + "开书" / /story-short-write
项目未装写作环境story-setup/story-setup

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Automate Chrome using an existing login session through CDP, Chrome’s remote control interface. Open pages, click elements, enter text, extract page content, run JavaScript, and inspect authentication tokens with agent-browser.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Automating tasks on sites where you are already signed in
  • Extracting text from web pages
  • Clicking buttons and filling in forms
zenstory-ai/oh-story-claudecode8천2026년 10월 23일 업데이트

story

무료

Route fiction requests to the appropriate writing, analysis, research, or cover skill. You can also switch between book projects and open a local dashboard to browse and edit manuscripts and project files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Starting or continuing a novel or short story
  • Finding character, setting, and foreshadowing details
  • Switching between several book projects
zenstory-ai/oh-story-claudecode8천2026년 10월 23일 업데이트

Create illustrated novel covers with the book title and pen name, tailored to the genre and publishing platform. Compare composition options, use reference images, export required dimensions, and refine colors, lettering, or layout.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Creating a novel cover with a title and pen name
  • Comparing cover compositions suited to a genre
  • Generating a cover using a reference image
zenstory-ai/oh-story-claudecode8천2026년 10월 23일 업데이트

Review and revise web fiction for mechanical phrasing, uneven narrative focus, and gaps in cause and effect. Preserve the author’s style and established plot, with diagnosis-only reviews or revisions limited to selected passages.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Revising mechanical phrasing in fiction
  • Balancing scene detail and narrative focus
  • Identifying gaps in character actions and story logic
zenstory-ai/oh-story-claudecode8천2026년 10월 23일 업데이트

Analyze a long novel through its opening chapters, chapter summaries, plot causality, reader emotions, pacing, relationships, settings, and prose style. Produce reusable writing references, continue partial analyses, or fill gaps in existing reports using available evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Studying how a novel's first three chapters engage readers
  • Mapping plot causality, timelines, and character relationships
  • Examining emotional effects, pacing, and prose style
zenstory-ai/oh-story-claudecode8천2026년 10월 23일 업데이트

Analyze Chinese novel rankings and new releases to find recurring genres, premises, title patterns, and emerging topic signals. Get a market report and two or three story proposals assessed against your material, writing constraints, and target platform.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Choosing a topic for a new serialized novel
  • Finding recurring ideas among new releases
  • Comparing genres and popularity measures across platforms
zenstory-ai/oh-story-claudecode8천2026년 10월 23일 업데이트

zenstory-ai의 스킬 모두 보기

이 스킬의 문제 신고