Remote OpenClaw
Menu
SkillsMCPPluginsFree guideDigestSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise
Remote OpenClaw
SkillsMCPPluginsFree guideDigestSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise

Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Skills/worldwonderer/oh-story-claudecode/story-long-analyze
story-long-analyze logo

story-long-analyze

worldwonderer/oh-story-claudecode
5K installs3K stars
Run it on Hostinger →up to 70% off + an extra 10% with code ZACAARON10Free API →

Installation

npx skills add https://github.com/worldwonderer/oh-story-claudecode --skill story-long-analyze

Summary

|

SKILL.md

story-long-analyze:长篇网文拆文

你是网络小说结构分析师。

核心信念:看懂别人的爆款,才能写出自己的爆款。

---

Phase 1:确认拆解对象 + 进入管道

问用户:「你要拆哪本书?(书名+平台)有原文文件路径吗?」

如果没有明确目标,按题材或用户想写的类型推荐 2-3 本对标作品。

统一入口

确认拆解对象后直接进入拆解管道(Phase 2)。没有快速/深度分叉——只有一条深度拆解管道,跑到 Stage 1(黄金三章)后自动停靠产出快速预览报告。

无文本路径时:如果用户没有提供原文文件路径、也没有在对话中贴出原文,引导用户提供原文——「请提供这本书的原文文件路径,或直接把原文贴给我,我从黄金三章开始拆。」拿到原文后进入管道。

---

Phase 2:深度拆解管道

输出目录

默认输出到 拆文库/{书名}/(项目根目录下)。用户指定了其他路径时按用户指定路径输出。

已有分析利用

深度拆解开始前,检查是否已有部分拆解结果:

  1. 检查 拆文库/{书名}/ 目录下是否存在已有的拆文文件
  2. 如果存在 _progress.md,读取断点信息,从断点恢复(已有恢复机制)
  3. 如果存在 角色/.md 或 设定/.md,读取已有的角色和设定数据
  4. 将已有数据作为交叉验证基线:
  • 新提取的角色信息与已有角色数据对比,检查一致性
  • 新发现的设定细节与已有设定合并,标注信息来源(新提取 vs 已有)
  • 如有冲突(如同角色已有文件中名字不同),在输出中标注冲突让用户裁定
  1. 避免重复提取已有信息,提升处理效率

原文备份(管道前置步骤)

拆解开始前,必须先备份原文:

  1. 检查 拆文库/{书名}/原文/ 目录是否已存在
  2. 如果不存在,从用户提供的源路径复制原文文件到 拆文库/{书名}/原文/
  3. 如果用户未提供源文件路径(直接在对话中贴文本),将原始文本保存到 拆文库/{书名}/原文/原文.md
  4. 备份完成后验证:
  • 源文件路径模式:确认 原文/ 目录下的文件数量和大小与源文件一致
  • 对话贴文本模式:确认 原文.md 文件非空(>0 bytes)
  1. 此步骤确保即使拆文过程中出现异常,原始材料不会丢失

输出目录结构

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2章_深度拆解.md
│   ├── 第3章_深度拆解.md
│   ├── 第1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
└── _progress.md

管道主体:Stage 0-5

这是 story-long-analyze 唯一的执行管道。Stage 0-1 跑完后自动停靠产出快速预览报告(见下「Stage 1 停靠点」),用户确认后从 Stage 2 续跑。

预期耗时提示:开始前根据章节数给用户一个粗估:<50 章通常 30-60 分钟;50-200 章通常 1-3 小时;>200 章可能需要多轮会话。Stage 2 可并行提取,但 Stage 3-5 仍依赖前序产物,需按阶段推进。

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(每章一个文件)。非人形反派(灵气复苏/末世/国运等抽象对抗型)出现在前三章时,在本阶段一并按抽象对抗型路由分析(核心对抗面/紧迫感来源/升级机制/叙事替代)。3章拆解完成 → 停靠产出快速预览.md
2逐章摘要分块章节文本章节摘要.md(含情节点+角色)。角色过滤(龙套不提取、别名归类)。每章3-40情节点(密度150-200字/个,按字数动态调节)。并行模式:每章 spawn chapter-extractor agent。计数验证:摘要数 == 章节数,不等则标记失败章节。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,决定聚合策略)。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(阈值详见 material-decomposition.md 质量阈值体系)。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(Stage 2 轻量提及→Stage 4 完整档案)。别名解析(置信度≥0.85自动合并)。角色关系提取(从情节点提取,不从原文;含演变追踪+最终状态合并+隐含推断)。非人形反派在此阶段做完整抽象对抗型分析。设定和关系提取完成
5汇总报告全部输出拆文报告.md(含「写法技巧」清单,覆盖一笔两用/延迟揭示/视角欺骗/对比锚点/行为循环/身体反应替代心理描写/跨章回扣——物品/意象在不同章节承担不同功能)报告生成完成

Stage 1 停靠点

Stage 0+1 完成后,管道自动停靠,产出快速预览报告并询问用户是否继续全量拆解:

  1. 生成停靠交付物:写 拆文库/{书名}/快速预览.md(模板见 output-templates.md 的「快速预览报告」)。此时 概要.md、章节/第1章_深度拆解.md、章节/第2章_深度拆解.md、章节/第3章_深度拆解.md、原文/ 均已落盘。
  2. 写停靠状态:_progress.md 的「最终状态」字段写 paused_after_stage1,「断点」段记录「下一操作:Stage 2 逐章摘要」。
  3. 询问用户(用 AskUserQuestion 风格的明确二选一):

「黄金三章已拆完,快速预览报告见 快速预览.md。是否继续全量拆解(Stage 2-5:逐章摘要 / 聚合分析 / 设定关系 / 汇总报告)?预计耗时 {基于章节数粗估}。」

  • 选「继续全量拆解」→ 读 _progress.md,从 Stage 2 续跑,不重跑 Stage 0/1。
  • 选「就到这里」→ 管道结束,_progress.md 状态保持 paused_after_stage1,告知用户「之后可随时 /story-long-analyze 同一本书,会自动从 Stage 2 续跑」。
  1. 跳过询问的情形:用户在一开始就明确说「完整拆解 / 一次跑完 / 系统拆解 / 别问」时,仍生成 快速预览.md(保留早期判断快照),但不停下询问,直接从 Stage 2 续跑到 Stage 5。

Stage 3-4 并行执行

并行执行图:

Stage 3A(剧情聚合)──┐
                       ├── 可并行执行
Stage 4前半(角色构建)─┘
         │
         ▼(两者完成后)
Stage 4后半(角色关系提取)— 串行,依赖角色实体存在

部分失败容忍

单章/单阶段失败不阻断管线。失败记录到 _progress.md 的「失败记录」表(| 类型 | 章节/阶段 | 错误信息 | 重试状态 |)。最终状态可为 completed_with_errors(在拆文报告中注明失败详情)。

与 material-decomposition.md 的对应关系:Stage 0 含 Material 阶段1(章节解析);Stage 1、5 为新增;Stage 2 = Material 阶段2;Stage 3 = Material 阶段3;Stage 4 合并 Material 阶段4+5。

详细模板见 output-templates.md,方法论见 material-decomposition.md。

---

质量门控概要

Stage 3-4 完成前需通过质量检查(置信度、覆盖率、重叠率)。阈值、计算方式与自检清单的唯一权威定义见 material-decomposition.md 质量阈值体系。

---

Stage 2 并行 Agent 策略

Stage 2 使用 chapter-extractor agent 并行处理每章,替代原来的串行分块。

调用方式

Agent(
  subagent_type: "chapter-extractor",
  prompt: "章节编号:第{N}章\n章节标题:{标题}\n章节字数:{字数}\n\n章节原文:\n{原文文本}"
)

批量策略

  • 每次 spawn 5-8 个 agent(避免并发限制)
  • 等待当前批次全部完成后,再 spawn 下一批
  • 每批完成后更新 _progress.md 记录已处理章节

Agent 输出收集

  • 每个 agent 返回 markdown 格式的提取结果
  • 主线程将 agent 输出写入 章节/第{N}章_摘要.md
  • 收集所有 agent 的出场人物表,供 Stage 3 合并使用

失败处理

  • 单章 agent 失败不阻断管道
  • 失败章节记录到 _progress.md 的「失败记录」表
  • 全部批次完成后,对失败章节重试一次
  • 重试仍失败的章节标记为 ⚠️ 跳过,在拆文报告中注明

Agent 不可用降级

以下任一情况,Stage 2 自动退回串行模式,由主线程按 chapter-extractor 方法论逐章处理(结果同样套 output-templates.md 的章节摘要模板,质量不受影响,只是改为串行、速度略慢):

  • agent 未部署:.claude/agents/chapter-extractor.md 不存在。.claude/agents/ 通常不随仓库提交,由 /story-setup 部署;模板源在 skills/story-setup/references/templates/agents/chapter-extractor.md,必要时可手动复制部署。
  • 环境不支持 spawn 子代理:本 skill 正运行在某个子代理上下文中,无法再起下一层 agent。

---

分块策略

路由级说明:Stage 2 使用 chapter-extractor agent 按章节并行,不分块。

Stage 3-5 的分块策略(规模分级、智能分块、跨块合并、输出长度上限)的唯一权威定义见 material-decomposition.md。

---

恢复机制

  1. 管道启动时检查输出目录是否已有 _progress.md
  2. 如有,读取断点信息(最后处理章节 + 当前阶段 + 最终状态)
  3. 断点状态为 paused_after_stage1(Stage 1 停靠点)→ 跳过 Stage 0/1,直接从 Stage 2 续跑逐章摘要,不重跑已完成的概要与黄金三章。
  4. 其他断点状态 → 从断点所在块的起始章节恢复,覆盖该块已有输出。

_progress.md 模板与各状态值说明见 pipeline-ops.md。

---

流程衔接

流水线: 长篇 位置: 拆文(长篇流水线第 2 步,在 story-long-scan 之后、story-long-write 之前)

时机跳转到命令
准备开写story-long-write/story-long-write
需要市场数据story-long-scan/story-long-scan
更适合短篇story-short-scan → story-short-analyze/story-short-scan

---

参考资料

文件何时加载
references/output-templates.md管道全程:各 Stage 输出模板 + 快速预览报告模板 + 通用速查表
references/material-decomposition.mdStage 2-5:5阶段方法论 + 质量阈值 + 分块策略
references/pipeline-ops.md管道运维:_progress.md 模板、错误处理、恢复机制操作步骤
references/deconstruction-notes.md拆书方法+影视拆解+抽象拆解法+题材实战

---

语言

  • 跟随用户的语言回复,用户用什么语言就用什么语言回复
  • 中文回复遵循《中文文案排版指北》

Score

0–100
63/ 100

Grade

C

Popularity23/30

4,515 installs — solid traction. Source repo has 2,614 GitHub stars.

Completeness19/30

Documented: full SKILL.md body, one-line install. Missing: description, category/license metadata.

Trust15/25

Community skill with a public GitHub source repository you can review.

Freshness6/15

No update timestamp is tracked for this skill in our catalog.

Scored automatically from popularity, completeness, trust, and freshness — computed only from data in our catalog, never fabricated.

Proud of your score? Add this badge to your README.

Paste a snippet into your GitHub README. The badge updates automatically and links back to this page.

Story Long Analyze skill score badge previewScore badge

Markdown

[![Story Long Analyze skill](https://www.remoteopenclaw.com/skills/worldwonderer/oh-story-claudecode/story-long-analyze/badges/score.svg)](https://www.remoteopenclaw.com/skills/worldwonderer/oh-story-claudecode/story-long-analyze)

HTML

<a href="https://www.remoteopenclaw.com/skills/worldwonderer/oh-story-claudecode/story-long-analyze"><img src="https://www.remoteopenclaw.com/skills/worldwonderer/oh-story-claudecode/story-long-analyze/badges/score.svg" alt="Story Long Analyze skill"/></a>

Story Long Analyze FAQ

How do I install the Story Long Analyze skill?

Run “npx skills add https://github.com/worldwonderer/oh-story-claudecode --skill story-long-analyze” in your terminal. The skill is added to your agent's skills directory and picked up automatically on the next run — no restart or extra configuration needed.

What does the Story Long Analyze skill do?

| The full SKILL.md on this page shows the exact instructions the skill gives your agent.

Is the Story Long Analyze skill free?

Yes. Story Long Analyze is a free, open-source skill published from worldwonderer/oh-story-claudecode. As with any third-party skill, review the source repository before installing it into an agent with sensitive access.

Does Story Long Analyze work with Claude Code and OpenClaw?

Yes. Skills use the portable SKILL.md format, so Story Long Analyze works with Claude Code, OpenClaw, Codex, Hermes, and any other agent that reads SKILL.md skills.

Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →

Categories

Prompt InjectionCommand Execution
View on GitHub

Recommended skills

Browse all →
find-skills logo

find-skills

vercel-labs/skills

2.7M installsInstall
frontend-design logo

frontend-design

anthropics/skills

720K installsInstall
grill-me logo

grill-me

mattpocock/skills

701K installsInstall
agent-browser logo

agent-browser

vercel-labs/agent-browser

596K installsInstall
grill-with-docs logo

grill-with-docs

mattpocock/skills

594K installsInstall
vercel-react-best-practices logo

vercel-react-best-practices

vercel-labs/agent-skills

591K installsInstall

Browse

Skills by category

Frontend250Git198Data154Testing120Design105Docs103Security96Automation87Backend76Devops37Productivity29Mcp23

Related guides

Hand-picked reading to help you choose, install, and use agent skills.

GuideBest Openclaw Skills 2026GuideHow To Evaluate Openclaw Skill Before InstallingGuideOpenclaw Skills Complete Guide

Remote OpenClaw

AI agent skills directory, marketplace, and workflow hub for OpenClaw, Hermes Agent, Claude Code, Codex, and MCP-powered operator stacks.

The Agent Stack: weekly agent tooling digest, free.

Explore

  • Home
  • Skills Directory
  • Claude Code Skills
  • Codex Skills
  • MCP Clients
  • Marketplace
  • Hermes Ecosystem
  • Free guide
  • Learn
  • OpenClaw for Creators
  • OpenClaw for Founders
  • Blog
  • The Agent Stack (Digest)

More

  • Submit a Tool
  • Advertise
  • Playbook
  • Free Tools
  • API
  • Shipping
  • Contact
  • Terms
  • Privacy

Know a company that should advertise here? Refer them and earn 10% — up to $300 per referral.

© 2026 Remote OpenClaw
Fazier badgeFeatured on Twelve ToolsFeatured on Wired BusinessRemote OpenClaw - Featured on AI Agents DirectoryListed on Turbo0Featured on Uneed