Social
coreyhaines31/marketingskills
When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, or Facebook, or wants to do social listening and engagement triage.
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。
The automated check flagged lines worth reading first. See the safety section below.
$ npx skills add uu201/character-arc --skill story-import -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install uu201/character-arc story-import --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/uu201/character-arc.git skills-src && mkdir -p .claude/skills && cp -r skills-src/resources/skills/oh-story-claudecode/story-import .claude/skills/story-import && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "story-import" agent skill from https://github.com/uu201/character-arc/tree/main/resources/skills/oh-story-claudecode/story-import into .claude/skills/story-import/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story-import", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/uu201/character-arc/tree/main/resources/skills/oh-story-claudecode/story-importType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add uu201/character-arc --skill story-import -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install uu201/character-arc story-import --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/uu201/character-arc.git skills-src && mkdir -p .agents/skills && cp -r skills-src/resources/skills/oh-story-claudecode/story-import .agents/skills/story-import && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "story-import" agent skill from https://github.com/uu201/character-arc/tree/main/resources/skills/oh-story-claudecode/story-import into .agents/skills/story-import/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story-import", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add uu201/character-arc --skill story-import -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install uu201/character-arc story-import --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/uu201/character-arc.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/resources/skills/oh-story-claudecode/story-import .cursor/skills/story-import && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "story-import" agent skill from https://github.com/uu201/character-arc/tree/main/resources/skills/oh-story-claudecode/story-import into .cursor/skills/story-import/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story-import", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/uu201/character-arc.git --path resources/skills/oh-story-claudecode/story-import--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add uu201/character-arc --skill story-import -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install uu201/character-arc story-import --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/uu201/character-arc.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/resources/skills/oh-story-claudecode/story-import .gemini/skills/story-import && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "story-import" agent skill from https://github.com/uu201/character-arc/tree/main/resources/skills/oh-story-claudecode/story-import into .gemini/skills/story-import/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story-import", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install uu201/character-arc story-importInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add uu201/character-arc --skill story-import -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/uu201/character-arc.git skills-src && mkdir -p .github/skills && cp -r skills-src/resources/skills/oh-story-claudecode/story-import .github/skills/story-import && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "story-import" agent skill from https://github.com/uu201/character-arc/tree/main/resources/skills/oh-story-claudecode/story-import into .github/skills/story-import/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story-import", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add uu201/character-arc --skill story-import -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install uu201/character-arc story-import --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/uu201/character-arc.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/resources/skills/oh-story-claudecode/story-import .opencode/skills/story-import && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "story-import" agent skill from https://github.com/uu201/character-arc/tree/main/resources/skills/oh-story-claudecode/story-import into .opencode/skills/story-import/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story-import", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
story-import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。
Story Import is an agent skill from uu201/character-arc. 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」
Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/character-state-reverse.md`, `references/format-and-structure.md` and `references/length-routing.md`).
It sits in Writing & Content. The repository describes itself as: CharacterArc(弧光) AI 小说创作应用,集项目设定、角色关系、剧情大纲、章节写作与多模型 AI 协作于一体. The licence is MIT.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 292f947. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and yaml).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Story Import loads about 3.9k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 51 tokens; SKILL.md has 834 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found patterns that need a careful read before installing.
tory-long-analyze 时**必须在一开始就以「完整拆解、一次跑完、不要停下询问」模式驱动管道**,命中其「跳过询问」路径(用户开头明确说「完整拆解 / 一次跑完 / 系统拆解 / 别问」时不停靠),让管道自动从 Stage 2Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from uu201/character-arc at commit 292f947, republished under its MIT licence (© uu201). 834 words, ~3,913 tokens.
.claude/skills/story-import/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.你是小说项目逆向工程师。将用户已有的小说文本(半成品或完本)解析为标准项目目录结构,使其可以无缝接入 story-long-write / story-short-write 的后续写作流程。导入流程按篇幅分流:长篇走长篇路径,短篇走短篇路径。
核心信念:好的工具不是从零开始,而是从你已有的东西开始。
交付物是写作工程:把作者已有的书重建为可续写的写作工程(项目结构 + 拆文库分析资产)。拆文库/ 是工程的一部分(喂给项目 对标/),不是用完即弃的中间产物、也不是交付物本身——交付物是作者能直接续写的项目。执行时以「建工程」为可见目标,别把「拆文」当成终点或对外标签。
先用拆解管道完整拆解小说(输出到 拆文库/),再将分析结果迁移为项目结构。拆文库/ 是写作工程的一部分(分析资产,喂给项目 对标/),保留不丢弃,不是用完即弃的中间产物。
深度分析阶段调用现成的拆解管道,不重新发明:长篇运行 /story-long-analyze 的完整拆解管道,短篇运行 /story-short-analyze 的拆解管道。拆解方法论与输出模板由对应 analyze skill 自带,story-import 不执行拆解方法论、不维护这些文件。
问用户:「你要导入哪本书?请提供文件路径或直接贴文本。」
默认目标是完整写作工程(可续写)。若用户意图不明确——是要可续写的工程,还是只要一份拆文库分析——主动询问,不要默认:
「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,能接着写第 N+1 章),还是只要一份拆文库分析?」
/story-long-analyze(短篇 /story-short-analyze),到拆文库为止,不进 Phase 3 迁移。用户提供路径?
├─ 单文件路径(.txt/.md)
│ └─ 按章节分隔符自动切分
├─ 目录路径
│ └─ 按文件名排序,合并处理
└─ 无路径 → 用户直接贴文本?
├─ 是 → 保存到临时文件后处理
└─ 否 → 提示用户提供源文件在进入 Phase 2 之前,先检测项目是否已部署 story-setup 基础设施:
.story-deployed 是否存在;.claude/agents/chapter-extractor.md 是否存在(Phase 2 长篇深度分析的并行 agent)。未部署时,提示用户:
「检测到当前项目尚未部署写作基础设施。建议先运行
/story-setup再回来导入,否则深度分析阶段无法使用并行 chapter-extractor agent。」
给用户两个选择:
/story-setup,部署完成后重新触发 /story-import;用户选择记入上下文,Phase 2 据此决定是否走并行模式。
原文备份由 Phase 2 调用的 analyze 拆解管道负责(analyze 管道前置步骤会把原文复制/保存到 拆文库/{书名}/原文/,对应 story-long-analyze 与 story-short-analyze 的「原文备份(管道前置步骤)」)。Phase 1 只需确认源文件就绪(路径有效或文本已拿到),不在此处单独备份,避免与 analyze 管道重复备份逻辑。
按 Phase 1 判定的篇幅类型,调用对应 analyze skill 的完整拆解管道(不是「复用方法论」式的半做,而是真正驱动整条管道跑完,拿到全套结构化产物)。
| 篇幅 | 调用的拆解管道 | 产物目录 |
|---|---|---|
| 长篇 | story-long-analyze 的 6 阶段管道(Stage 0-5) | 拆文库/{书名}/ |
| 短篇 | story-short-analyze 的拆解管道(Stage 2-6) | 拆文库/{书名}/ |
<!--
契约说明:story-import 依赖 story-long-analyze 的「跳过询问」机制
(对应 story-long-analyze「Stage 1 停靠点」的「跳过询问的情形」)。
若 story-long-analyze 后续重构改动了该机制的触发措辞,需同步检查并更新本契约。
-->
story-long-analyze 在 Stage 0+1(黄金三章)后会自动停靠并用 AskUserQuestion 询问是否继续全量拆解(对应 story-long-analyze 的「Stage 1 停靠点」)。但导入场景需要 Stage 2-6 的全套产物(逐章摘要 / 聚合分析 / 设定关系 / 汇总报告 / 文风),缺一不可——否则 Phase 3 迁移会拿到半成品。
因此调用 story-long-analyze 时必须在一开始就以「完整拆解、一次跑完、不要停下询问」模式驱动管道,命中其「跳过询问」路径(用户开头明确说「完整拆解 / 一次跑完 / 系统拆解 / 别问」时不停靠),让管道自动从 Stage 2 续跑到 Stage 6。
story-short-analyze 是单一全量拆解管道(Stage 2-6),无 Stage 1 停靠点,契约较简单:调用后让其跑完 Stage 2-6 即可,无需声明跳过询问。
长篇分析输出到 拆文库/{书名}/,与 story-long-analyze 拆解管道完全一致:
拆文库/{书名}/
├── 原文/
│ └── 原文.txt # 扩展名随源文件;对话直接贴入的文本存为 原文.md
├── 概要.md
├── 章节/
│ ├── 第1章_深度拆解.md
│ ├── 第1章_摘要.md
│ └── ... # 每章同时有 第N章_深度拆解.md 和 第N章_摘要.md
├── 快速预览.md
├── 角色/
│ ├── {角色名}.md
│ └── 角色关系.md
├── 剧情/
│ ├── {剧情标题}.md
│ ├── 故事线.md
│ └── 散落情节.md
├── 设定/
│ ├── 世界观.md
│ └── 金手指.md
├── 拆文报告.md
├── 文风.md # Stage 6 文风:写作技法视图 + 原文 few-shot 锚点
└── _progress.md短篇分析输出到 拆文库/{书名}/,与 story-short-analyze 拆解管道一致:
拆文库/{书名}/
├── 原文/
│ └── 原文.txt # 扩展名随源文件;对话直接贴入的文本存为 原文.md
├── 拆文报告.md
├── 情节节点.md
└── 写作手法.md管道详细说明见 story-long-analyze(运行
/story-long-analyze),此处仅列概要。
| 阶段 | 名称 | 输入 | 输出 | 完成标志 |
|---|---|---|---|---|
| 0 | 概要提取 | 原始文本 | 概要.md + 章节索引 | 章节结构识别完成 |
| 1 | 黄金三章 | 前 3 章原文 | 第1章_深度拆解.md / 第2章_深度拆解.md / 第3章_深度拆解.md → 停靠产出快速预览.md(导入场景自动续跑,不停下询问) | 3 章拆解完成 |
| 2 | 逐章摘要 | 分块章节文本 | 章节摘要.md(含情节点+角色)。每章3-40情节点(密度150-200字/个,按字数动态调节)。角色过滤(龙套不提取、别名归类)。并行 chapter-extractor agent 模式(未部署 agent 时降级串行)。计数验证:摘要数 == 章节数。 | 所有章节处理完成 |
| 3 | 聚合分析 | 全部章节摘要 | 剧情/*.md + 故事线.md。故事框架识别(前置)。两步法剧情聚合(先从摘要识别剧情大纲,再按大纲分配情节点)。角色合并(跨章节去重+别名归一)。角色分级(主角/反派/核心配角/功能角色)。孤立情节兜底(6步,含覆盖率验证)。质量门控(置信度>=0.85/覆盖率85%-95%/重叠率<=35%)。 | 质量检查通过 |
| 4 | 设定+关系 | 阶段 3 合并后角色数据+情节点 | 设定/.md + 角色/.md。两阶段角色模型。别名解析(置信度≥0.85自动合并)。 | 设定和关系提取完成 |
| 5 | 汇总报告 | 全部输出 | 拆文报告.md | 报告生成完成 |
| 6 | 文风 | 拆文报告.md + 章节/第1-3章_深度拆解.md + 章节/*_摘要.md + 原文/原文.txt | 文风.md(整书级写作技法视图,story-long-write 日更循环必读) | 文风落盘 拆文库/{书名}/文风.md |
管道详细说明见 story-short-analyze(运行
/story-short-analyze),此处仅列概要。
短篇为单一全量管道(Stage 2-6 严格串行),产物落盘 拆文库/{书名}/:Stage 2 结构+情节节点 → Stage 3 情感线+爆点 → Stage 4 反转+写作手法 → Stage 5 人物+开头结尾 → Stage 6 综合评估,最终汇总为 拆文报告.md、情节节点.md、写作手法.md。
沿用 story-long-analyze 的分块策略(Stage 2 使用 chapter-extractor agent 并行,其他阶段按以下策略分块):
| 规模 | 策略 | 块大小 |
|---|---|---|
| <50 章 | 按阶段整体处理 | 无需分块 |
| 50-100 章 | 按阶段整体处理 | 无需分块(可选智能分块) |
| 100-500 章 | 按章节分块 | 5-8 章/块 |
| >500 章 | 语义分块:按自然分界切分,无明确分界时按固定章节数均匀切分 | 50-200 章/块 |
长篇阶段 3-4 完成前执行质量检查(置信度 >= 0.85,覆盖率 85%-95%,重叠率 <= 35%),由 story-long-analyze 拆解管道自带的质量门控负责。短篇质量门控见 story-short-analyze 各阶段的完成标志。
将 拆文库/{书名}/ 的分析结果迁移为可被写作 skill 消费的项目结构。
按 Phase 1 判定的篇幅类型分流,两条路径产出的工程结构完全不同:
| 篇幅 | 迁移路径 | 映射规则 | 续写接手 |
|---|---|---|---|
| 长篇 | 3-L:长篇结构迁移 | references/structure-mapping-long.md | story-long-write 日更循环 |
| 短篇 | 3-S:短篇结构迁移 | references/structure-mapping-short.md | story-short-write Phase 3 逐场景写作 |
将 拆文库/{书名}/ 的分析结果迁移为 {书名}/ 长篇项目结构。迁移规则详见 references/structure-mapping-long.md。
{书名}/
├── 设定/
│ ├── 世界观/
│ ├── 角色/
│ └── 势力/
├── 大纲/
├── 正文/
├── 追踪/
└── 参考资料/将原文迁移到 正文/,统一命名格式:第XXX章_章名.md。
将 拆文库/{书名}/角色/{角色名}.md 迁移到 设定/角色/{角色名}.md。
迁移时增加 story-long-write 角色模板字段:
---
name: {角色名}
---
# {角色名}
## 基本信息
- 身份:{}
- 核心特质:{}
- 当前能力:{}
- 核心动机:{}
- 弱点/缺陷:{}
## 出场记录
| 章节 | 关键事件 | 状态变化 |
|------|---------|---------|角色分级(沿用 story-long-analyze 标准):
| 等级 | 标准 | 迁移策略 |
|---|---|---|
| 主角 | 出现章节 ≥50% + 推动主线 + 完整成长轨迹 | 完整迁移 |
| 反派 | 与主角对立 + 推动核心冲突 + 明确动机 | 完整迁移 |
| 核心配角 | 出现章节 ≥20% 或推动重要支线 | 完整迁移 |
| 功能角色 | 出现章节 <20% + 作用有限 | 简化迁移 |
将 拆文库/{书名}/角色/角色关系.md 转换为 设定/关系.md,按 structure-mapping-long.md「关系文件转换规则」的目标格式模板输出。
先检测拆文库形态,再决定路径:
| 拆文库形态 | 检测方法 | 处理 |
|---|---|---|
| 已按主题拆分 | 拆文库/{书名}/设定/世界观/ 子目录存在 + 至少含 背景设定.md 或 力量体系.md 之一 | pass-through:原样同步 设定/世界观/*.md 和 设定/势力/*.md 到项目,无需 re-split |
| 单文件版本 | 仅 拆文库/{书名}/设定/世界观.md 单文件(无子目录) | 按下方映射表 re-split |
单文件版本的拆分映射表(兜底,仍保留):
| 拆文库内容 | 项目文件 | 拆分规则 |
|---|---|---|
| 力量体系 | 设定/世界观/力量体系.md | 独立文件 |
| 地理 | 设定/世界观/地理.md | 独立文件(内容充足时) |
| 核心规则 | 设定/世界观/背景设定.md | 与其他无法独立的内容合并 |
| 特殊设定 | 设定/世界观/背景设定.md | 合并 |
| 金手指 | 设定/世界观/金手指.md | 独立文件 |
| 势力/组织 | 设定/势力/{势力名}.md | 内容 >= 200 字时独立为势力文件,不足则合并到 背景设定.md |
内容不足独立成文件时,合并到 背景设定.md。
大纲.md(卷级结构):从 剧情/故事线.md、剧情/*.md 和 快速预览.md 反推。卷划分采用用户确认制,规则见 structure-mapping-long.md「大纲反推规则」:
大纲/大纲.md 只记录候选方案。# 全书大纲
## 卷级大纲
### 第一卷:{卷名}(约 {X} 万字,{Y} 章)
- 功能:{从剧情分析推断}
- 核心事件:{一句话}
- 起始状态 → 结束状态:{从角色弧线推断}卷纲:卷划分确认后,从剧情文件聚合生成 大纲/卷纲_第X卷.md,按 structure-mapping-long.md「卷纲反推」模板格式。
细纲:从章节摘要反推生成 大纲/细纲_第XXX章.md:
## 细纲(第 N 章)
### 第 N 章:{章名}
- 核心事件:{从摘要中提取}
- 章首钩子:[待补充]
- 爽点:{从情节点推断}
- 章尾钩子:[待补充]
- 字数目标:{原文实际字数}钩子字段标记
[待补充],因为原文分析无法稳定判断钩子设计目标。
追踪目录共四个文件,必须按以下顺序生成(后一个文件依赖前一个的产出):
① 追踪/伏笔.md ← 先生成(角色状态反推的「待回收伏笔」字段依赖此文件)
② 追踪/时间线.md ← 与伏笔同步或紧随其后
③ 追踪/角色状态.md ← 依赖伏笔.md 已存在
④ 追踪/上下文.md ← 最后生成(其「角色状态:最近变更」字段依赖角色状态.md)① 追踪/伏笔.md:从情节点的「铺垫」类型情节点提取潜在伏笔:
# 伏笔追踪
## 伏笔状态表
| ID | 伏笔内容 | 埋设章节 | 预计回收章节 | 状态 | 重要度 |
|----|---------|---------|-------------|------|--------|
| F001 | {从铺垫情节点提取} | 第{N}章 | {如已回收则标注} | {已埋/已回收} | {中} |② 追踪/时间线.md:从时间标记提取:
# 故事时间线
## 关键事件时序
| 章节 | 故事时间 | 事件 | 涉及角色 | 与主线关系 |
|------|---------|------|---------|-----------|③ 追踪/角色状态.md:从拆书产物反推每个主要角色的当前状态。反推算法详见 references/character-state-reverse.md:
角色/{角色名}.md、角色/角色关系.md、章节/第N章_摘要.md 情节点、剧情/*.md)+ 已生成的 追踪/伏笔.md,不重读 原文/。角色状态.md 标准模板(当前身份 / 当前能力 / 关键关系 / 公众形象 / 待回收伏笔 / 状态变更记录)。追踪/伏笔.md 之后(步骤「待回收伏笔」依赖伏笔状态)。此文件不可遗漏。story-long-write 的日更准备层「状态筛选」依赖
追踪/角色状态.md;若缺失,导入书进入日更会永久走「从角色设定和前文推断」的兜底分支,长期降级。
④ 追踪/上下文.md:进度摘要(最后生成,「当前状态」中的角色状态变更引用 角色状态.md):
## 写作进度
- 最后完成章节:第 {N} 章
- 更新时间:{导入日期}
- 本期完成:导入 {N} 章,共 {X} 字
## 当前状态
- 活跃伏笔:{A} 条待回收
- 角色状态:最近变更见 `追踪/角色状态.md`
- 下一章细纲状态:已有
- 注意事项:最后一章为残稿时在此注明残稿到第 N 章及用户选定的续写策略从拆文报告中提取核心发现,生成 设定/题材定位.md(按 structure-mapping-long.md「题材定位生成」模板格式)。
设定/题材定位.md 必须包含「对标书清单 + 主对标书」段,格式:
主对标书: {书名} # 多本对标时日更默认用哪本的文风;缺失时 story-long-write 用字典序第一本并提示用户补
对标书列表:
- 书名: {书名 A}
引用强度: 主 # 主 / 辅 / 参考
- 书名: {书名 B}
引用强度: 辅把 拆文库/{书名}/文风.md 复制到 {项目}/对标/{书名}/文风.md。纯复制,不重新生成。
缺失处理:
/story-long-analyze 后再同步;日更前文风缺失会被 fail-fast 拦截将 拆文库/{书名}/ 的短篇拆文产物迁移为 {短篇标题}/ 短篇工程结构,供 story-short-write Phase 3 逐场景写作无缝接手。迁移规则详见 references/structure-mapping-short.md。
短篇工程与长篇完全不同:短篇正文是单文件
正文.md(不切章),不产追踪/、大纲/、正文/等长篇目录。迁移时严禁误建这些长篇专属目录。
{短篇标题}/
├── 设定.md ← 含核心框架 + 对标摘要
├── 小节大纲.md ← 按段-小节结构反推
├── 正文.md ← 单文件全文正文
└── 对标/{书名}/ ← 可选:拆文引用视图
├── 拆文报告.md
├── 情节节点.md
└── 写作手法.md将 拆文库/{书名}/原文/ 的全文迁移为单文件 {标题}/正文.md,按 format-and-structure.md 规范化格式(小节标记 ###1.、段间无空行、对话引号按项目/平台约定统一)。原文已是成稿,不重写内容,只规范格式。
从 拆文报告.md、写作手法.md 反推 {标题}/设定.md,含两个区块:
从 情节节点.md 的功能分段反推 {标题}/小节大纲.md,按开头段/铺垫段/升级段/反转段/结尾段映射;钩子字段标 [待补充]。
将 拆文库/{书名}/ 整体复制为 {标题}/对标/{书名}/,供续写阶段的对标上下文加载。默认生成。
按篇幅对照对应的质量检查清单:
追踪/角色状态.md 已生成且对齐标准模板、卷划分已经用户确认等)。正文.md 单文件存在且格式合规、设定.md 含核心框架+对标摘要、未误建长篇专属目录等)。输出导入结果摘要和待补充项,按篇幅分支。
长篇导入完成报告:
=== 导入完成报告(长篇)===
书名:{书名}
源文件:{X} 章,{Y} 万字
项目目录:{路径}
## 已生成文件
- 正文:{N} 章
- 角色文件:{M} 个
- 大纲:大纲.md + {V} 个卷纲 + {N} 个细纲
- 追踪:伏笔.md + 时间线.md + 角色状态.md + 上下文.md
- 设定:{世界观文件数} 个
## 待补充项
- [ ] 细纲中的章首/章尾钩子需要补充
- [ ] 题材定位的核心梗三分法需要确认
- [ ] 伏笔追踪中的伏笔已复核
- [ ] 角色状态.md 已复核(日更准备层依赖此文件)
- [ ] 卷划分已确认(原文无明确卷界时)
- [ ] 文风已从拆文库同步到 `对标/{书名}/`(日更前 fail-fast 依赖此文件)
- [ ] `设定/题材定位.md` 已含 `主对标书` 字段(多本对标时必填)
## 下一步操作
- 运行 `/story-review lean` 审查导入结果
- 运行 `/story-long-write` + "日更" 开始续写短篇导入完成报告:
=== 导入完成报告(短篇)===
标题:{短篇标题}
源文件:{Y} 字
项目目录:{路径}
## 已生成文件
- 正文.md(单文件,{Y} 字)
- 设定.md(核心框架 + 对标摘要)
- 小节大纲.md({N} 个小节)
- 对标/{书名}/(可选引用视图)
## 待补充项
- [ ] 所有 [待补充] 标记的文件已复核
- [ ] 小节大纲的章首/章尾钩子需要补充
- [ ] 核心反转的铺垫线索已确认
## 下一步操作
- 运行 `/story-short-write` Phase 3 开始续写.active-book 指向导入的书名/标题目录.claude/agents/story-explorer.md 是否存在),可 spawn Agent(subagent_type: "story-explorer", prompt: "项目目录:{dir}\n查询类型:progress\n查询参数:导入验证") 交叉验证迁移数据完整性setup 环境检测已在 Phase 1「环境检测前置」完成,此处不再重复检测。
本节仅适用于长篇导入。短篇为单文件全量迁移,无增量导入需求。
超过 200 章的作品,采用增量导入策略:
按阶段加载,不一次全部加载。
本 skill 自带的 reference 文件全部位于 references/,按场景加载。涉及别的 skill 的方法论/模板时,story-import 不直接加载文件,而是运行对应 /命令 由该 skill 自行加载。
| 场景 | 加载文件 |
|---|---|
| 篇幅分流判定 | references/length-routing.md |
| 章节格式识别 | 由 story-long-analyze 拆解管道(运行 /story-long-analyze)的阶段 1 负责 |
| 场景 | 加载文件 / 相关 skill |
|---|---|
| 长篇深度分析(方法论、质量门控、输出模板均自带) | 运行 /story-long-analyze 调用长篇拆解管道 |
| 短篇深度分析(方法论、质量门控、输出模板均自带) | 运行 /story-short-analyze 调用短篇拆解管道 |
| 场景 | 加载文件 |
|---|---|
| 长篇迁移映射规则 | references/structure-mapping-long.md |
| 短篇迁移映射规则 | references/structure-mapping-short.md |
| 角色状态反推规则(长篇) | references/character-state-reverse.md |
| 角色状态规则(character-state-reverse.md 依赖) | references/state-tracking.md |
| 短篇正文格式规范 | references/format-and-structure.md |
长篇细纲模板格式参见 story-long-write(Phase 3 细纲部分);短篇核心框架模板参见 story-short-write(核心框架部分)。这两项为纯文本指引,story-import 不加载对应 skill 的文件。
| 场景 | 说明 |
|---|---|
| 长篇项目结构规范 | 参见 story-long-write(Phase 4 项目文件结构) |
| 短篇项目结构规范 | 参见 story-short-write(Phase 3 项目结构) |
| 环境部署 | 部署模板由 /story-setup 提供,story-import 不负责部署 |
流水线: 长篇 / 短篇 位置: 导入(在开书之前)
| 时机 | 跳转到 | 命令 |
|---|---|---|
| 导入完想继续写(长篇) | story-long-write | /story-long-write + "日更" |
| 导入完想继续写(短篇) | story-short-write | /story-short-write |
| 导入完想审查质量 | story-review | /story-review |
| 想深入分析对标(长篇) | story-long-analyze | /story-long-analyze |
| 想深入分析对标(短篇) | story-short-analyze | /story-short-analyze |
| 从零开新书(长篇) | story-long-write | /story-long-write + "开书" |
| 从零开新书(短篇) | story-short-write | /story-short-write |
| 项目未部署环境 | story-setup | /story-setup |
© uu201, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 6 other files (references) in resources/skills/oh-story-claudecode/story-import of uu201/character-arc.
Open the folder on GitHubat commit 292f947
Story Import next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Story Import this skilluu201/character-arc | 583 | — | ~3.9k | Automated safety check: Warn | MIT | |
| Socialcoreyhaines31/marketingskills | 54k | 4 repos | ~4.5k | Automated safety check: Pass | MIT | |
| HumanizerAzure-Samples/interview-coach-agent-framework | 173 | 38 repos | ~5.8k | Automated safety check: Pass | MIT | |
| Avoid AI Writingconorbronsdon/avoid-ai-writing | 4.9k | 3 repos | ~8.1k | Automated safety check: Pass | MIT | |
| JavaScript Concept Fact Checkerleonardomso/33-js-concepts | 67k | 1 repos | ~5k | Automated safety check: Pass | MIT | |
| User-Facing Text Cleanupguillaumemeyer/watermarks-remover | 24k | — | ~3.5k | Automated safety check: Pass | MIT |
coreyhaines31/marketingskills
When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, or Facebook, or wants to do social listening and engagement triage.
Azure-Samples/interview-coach-agent-framework
Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.
conorbronsdon/avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms").
leonardomso/33-js-concepts
Verifies the technical accuracy of JavaScript concept pages by checking code examples, MDN and ECMAScript claims and external links through a five-phase method.
guillaumemeyer/watermarks-remover
Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.
trycompai/crm
Install and configure the anti-slop Oxlint plugin in a local TypeScript or JavaScript repository.
uu201/character-arc
Finds and rewrites AI-sounding passages in Chinese web novel text, changing as few words as possible while keeping plot, characters and names intact.
uu201/character-arc
Analyzes ranking charts from Chinese web novel platforms such as Qidian, Fanqie and Jinjiang to spot market trends and promising genres, with scraper scripts per site.
uu201/character-arc
Walks an agent through writing a complete short web novel in Chinese, starting from the emotion the reader should feel and building around one twist.
uu201/character-arc
Polishes AI-generated web novel text to remove machine-sounding patterns, with rewriting strategies, instruction templates, style techniques and before-and-after examples.
uu201/character-arc
长篇网文写作。从大纲到正文,辅助长篇网络小说的创作,包括世界观、人物、情节线管理. An agent skill from uu201/character-arc.
uu201/character-arc
网文创作工具与生产流程。当用户需要使用AI辅助写作工具、设计提示词模板、规划写作工作流、选择码字工具、制定发布与数据分析策略时触发。覆盖DeepSeek/ChatGPT/Claude/豆包等AI工具应用、提示词工程、工作流设计、发布运营。
Categories
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。. Story Import is an agent skill from uu201/character-arc.
Story Import fits situations like: writing & Content work in your project.
Run `npx skills add uu201/character-arc --skill story-import -a claude-code`. Or copy the skill folder (resources/skills/oh-story-claudecode/story-import in uu201/character-arc) into .claude/skills/story-import in your project. Claude Code loads it when a task matches its description.
Run `npx skills add uu201/character-arc --skill story-import -a codex`. Or copy the skill folder (resources/skills/oh-story-claudecode/story-import in uu201/character-arc) into .agents/skills/story-import in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add uu201/character-arc --skill story-import -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/story-import, .gemini/skills/story-import, .github/skills/story-import and .opencode/skills/story-import in your project.
SKILL.md names no scripts, command-line tools or credentials: Story Import is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md flagged 1 warning(s): tells the agent its actions are pre-authorized / not to stop for confirmation. Read the flagged lines before installing; the check is not a guarantee either way.
Story Import is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.9k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 10k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Story Import: Social (coreyhaines31/marketingskills, 54k stars), Humanizer (Azure-Samples/interview-coach-agent-framework, 173 stars), Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars) and JavaScript Concept Fact Checker (leonardomso/33-js-concepts, 67k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
uu201 (a GitHub user) maintains it in uu201/character-arc, which has 583 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 9, 2026.
Source: uu201/character-arc on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.