Story
Route fuzzy Chinese web-novel intents to the right Oh-Story skill for scanning rankings, outlining, writing, deslop, or covers.
Overview
Story is a journey-wide agent skill that routes Chinese web-novel requests to specialized Oh-Story skills whenever a solo builder needs to start or steer a fiction project before picking a single workflow.
Install
npx skills add https://github.com/worldwonderer/oh-story-claudecode --skill storyWhat is this skill?
- Central router for /story and 网文 with a keyword table mapping to long-write, short-write, scan, analyze, deslop, cover,
- Checks project state (追踪/, 设定/, .story-deployed) and steers new writers to /story-setup before drafting
- Supports multi-book switching by listing directories with tracking or setting folders
- Spawns story-explorer for structured lore queries and story-researcher for external research without a sub-skill handoff
Adoption & trust: 2.1k installs on skills.sh; 2.1k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You opened Claude with a vague “help me write web fiction” request and do not know which scan, write, or analyze skill to invoke.
Who is it for?
Solo authors using Oh-Story in Claude Code who speak in natural Chinese or /story and want automatic dispatch to the correct fiction workflow.
Skip if: English-only SaaS builders with no fiction workflow, or users who already invoked a specific sub-skill with explicit commands and do not need routing.
When should I use this skill?
/story, /网文, or phrases like “我想写小说”, “帮我写书”, “写网文” when intent is unclear and should dispatch to a specific Oh-Story skill.
What do I get? / Deliverables
The agent matches your intent to the right Oh-Story skill—or asks long vs short—after checking project setup and spawning explorer/research agents when those fit better.
- Invocation of the matched downstream story skill or explorer/researcher agent
- Clarifying questions when long/short or intent is ambiguous
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
User says “我想写小说” without format; router asks long vs short then calls story-long-write or story-short-write.
User asks what niche is hot; router sends them to story-long-scan for ranking and topic decisions.
User continues an existing book; router verifies 追踪/设定 exists or runs story-setup before writing skills.
User needs a cover; router invokes story-cover instead of a generic image prompt.
User says prose feels too AI; router routes to story-deslop for tone cleanup.
How it compares
Meta workflow router for a fiction skill pack—not a single drafting or SEO tool.
Common Questions / FAQ
Who is story for?
Independent writers and hobbyist serial authors using the Oh-Story Claude plugin who need one entry point for 网文 tooling.
When should I use story?
At Idea when exploring what to write; at Validate when picking topics via long-scan; at Build when continuing drafts; at Grow when researching trends—anytime intent is vague and needs the routing table.
Is story safe to install?
It orchestrates other local fiction skills and may spawn sub-agents; review the Security Audits panel on this page and your project files before browser or import flows.
SKILL.md
READMESKILL.md - Story
# story：网文工具箱路由 你是网文工具箱的路由入口。用户的请求模糊时由你分发到具体 skill。 ## 路由表 | 用户意图 | 关键词示例 | 路由到 | |---|---|---| | 写长篇 | 开书、写大纲、长篇、连载 | `/story-long-write` | | 写短篇 | 短篇、盐言、一万字 | `/story-short-write` | | 长篇拆文 | 拆文、分析这本书、黄金三章 | `/story-long-analyze` | | 短篇拆文 | 拆短篇、分析这个故事 | `/story-short-analyze` | | 长篇扫榜 | 长篇排行、什么火、起点/番茄/晋江 | `/story-long-scan` | | 选题决策 | 写什么能爆、帮我选题、选题方向 | `/story-long-scan` | | 短篇扫榜 | 短篇排行、知乎盐言排行 | `/story-short-scan` | | 去 AI 味 | 去 AI 味、太 AI、去味 | `/story-deslop` | | 封面 | 封面、封面图 | `/story-cover` | | 环境部署 | 准备写书、搭环境、初始化 | `/story-setup` | | 浏览器操控 | 浏览器、抓取、登录态 | `/browser-cdp` | | 导入小说 | 导入、反向解析、导入小说、把我的书导进来 | `/story-import` | | 切换/列出书目 | 切书、换书、列出我的书、我在写哪几本、切换项目 | 见下方「多书切换」 | | 查故事资料 | 查角色、查伏笔、查进度、查设定、什么状态、写到哪了 | 直接 spawn `story-explorer` agent（使用结构化 prompt：`项目目录：{dir}\n查询类型：{根据意图选择}\n查询参数：{用户查询}`） | | 查资料 | 查资料、帮我查资料、调研、搜索一下、搜一下 | 直接 spawn `story-researcher` agent | ## 路由流程 1. 分析用户请求，提取意图关键词 2. 匹配上表，找到对应的 skill 3. 如果能明确匹配，直接调用对应 skill（`Skill("skill-name")`） 4. 如果无法匹配，询问用户想做什么（从上表中选择） 5. 如果用户说"我想写小说"但未指定长篇/短篇，询问篇幅类型后再路由 ## 项目状态感知 路由前先检查当前项目状态： - **无项目目录**（没有包含 `追踪/` 或 `设定/` 的书名目录）： - 如果用户要写作，下一步是先运行 `/story-setup` 初始化环境 - 如果用户要扫榜/拆文，直接路由 - **已有项目**：检查 `.story-deployed` 标记，如未部署则先运行 `/story-setup` ## 多书切换 用户想切换或查看在写的书时（一个项目可同时有多本）： 1. 在项目根查找所有书目录：包含 `追踪/` 或 `设定/` 子目录的目录（含 `长篇/`、`短篇/` 下的子目录）。 2. 列出书名，并标出当前 `.active-book` 指向的那本。 3. 让用户选择，把所选书的相对路径写入项目根 `.active-book`（覆盖原内容）。 4. 只发现一本时直接确认为活跃书，无需询问。