Web Novel Ranking Scanner
zenstory-ai/oh-story-claudecode
Analyzes ranking-list data from Chinese web novel platforms to spot repeating genres, title patterns and opening hooks, then writes a market report for authors.
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.
SKILL.md written in Chinese; this summary is our English description.
Install Web Novel Ranking Scanner
$ npx skills add uu201/character-arc --skill story-long-scan -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install uu201/character-arc story-long-scan --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-long-scan .claude/skills/story-long-scan && 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-long-scan" agent skill from https://github.com/uu201/character-arc/tree/main/resources/skills/oh-story-claudecode/story-long-scan into .claude/skills/story-long-scan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story-long-scan", 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-long-scanType 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-long-scan -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install uu201/character-arc story-long-scan --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-long-scan .agents/skills/story-long-scan && 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-long-scan" agent skill from https://github.com/uu201/character-arc/tree/main/resources/skills/oh-story-claudecode/story-long-scan into .agents/skills/story-long-scan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story-long-scan", 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-long-scan -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install uu201/character-arc story-long-scan --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-long-scan .cursor/skills/story-long-scan && 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-long-scan" agent skill from https://github.com/uu201/character-arc/tree/main/resources/skills/oh-story-claudecode/story-long-scan into .cursor/skills/story-long-scan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story-long-scan", 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-long-scan--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-long-scan -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install uu201/character-arc story-long-scan --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-long-scan .gemini/skills/story-long-scan && 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-long-scan" agent skill from https://github.com/uu201/character-arc/tree/main/resources/skills/oh-story-claudecode/story-long-scan into .gemini/skills/story-long-scan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story-long-scan", 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-long-scanInstalls 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-long-scan -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-long-scan .github/skills/story-long-scan && 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-long-scan" agent skill from https://github.com/uu201/character-arc/tree/main/resources/skills/oh-story-claudecode/story-long-scan into .github/skills/story-long-scan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story-long-scan", 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-long-scan -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-long-scan --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-long-scan .opencode/skills/story-long-scan && 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-long-scan" agent skill from https://github.com/uu201/character-arc/tree/main/resources/skills/oh-story-claudecode/story-long-scan into .opencode/skills/story-long-scan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "story-long-scan", 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.
Facts
- Skill name
story-long-scan- GitHub stars
- 583
- Token cost
- ~2k tokens
- SKILL.md length
- 439 words
- Files
- 12 (incl. scripts, references)
- Skills in repo
- 26
- Repo updated
- First seen
- Licence
- MIT
At a glance
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.
- Works in 5 steps: ：确认平台和方向 → 5：确定数据来源 → ：数据分析 → …
- Finding out which web novel genres are trending on Qidian or Fanqie
- SKILL.md covers 核心哲学, 扫榜流程, 平台特性速查 and 流程衔接, plus 2 more sections
- Runs JavaScript scripts from its folder; calls node; reaches m.qidian.com
What it does
The agent plays a web novel market analyst. It asks which platform you want to study (Qidian, Fanqie, Jinjiang or another) and whether you already have a genre in mind, then runs a deep scan of that genre, a full-chart overview, or a comparison across platforms. A single book's rank counts only as a one-off case; a pattern repeated across several charts, works and recent data is what gets flagged as a trend.
Data comes from three sources in priority order: the bundled scraper scripts (Qidian, Fanqie, Qimao, Jinjiang and Ciweimao), material you paste in such as screenshots, text or links, and, when the agent is offline, its built-in knowledge. Qidian is read from its mobile page data without a browser, while Fanqie needs a Chrome session through browser-cdp and reads titles from detail pages. Results are saved as Markdown following a format reference.
The skill treats each platform's success measures differently and checks every candidate genre for feasibility against your material, genre limits, length and the platform's sample size. Further references cover genre trends, publishing, reader profiling and topic decisions. The skill is written in Chinese and answers to commands such as /story-long-scan.
When your agent uses it
- Finding out which web novel genres are trending on Qidian or Fanqie
- Comparing what readers reward on different web novel platforms
- Choosing a genre for a new serial based on ranking data rather than one hit
Example prompts
- “/story-long-scan 看看起点排行，现在什么题材最火？”
- “Scan the Fanqie male-channel new book charts and list the genres and opening hooks that repeat.”
- “Compare Qidian and Jinjiang rankings and tell me which genre fits a writer with a lot of historical research.”
Requirements
- Node.js to run the scraper scripts
- Chrome with a browser-cdp connection for platforms that need a browser session
- Network access to the ranking sites
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 292f947. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Ships 6 files in scripts/ (JavaScript), which the agent can run.
Shell commands in SKILL.md call:
node
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
m.qidian.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Web Novel Ranking Scanner loads about 2k tokens when it runs, and up to ~8.8k if it reads all its reference files. Until then it costs about 24 tokens; SKILL.md has 439 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.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated 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); the scripts in this folder are not scanned.
SKILL.md
The full file from uu201/character-arc at commit 292f947, republished under its MIT licence (© uu201). 439 words, ~2,044 tokens.
Download SKILL.mdSave it as
.claude/skills/story-long-scan/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.- name
- story-long-scan
- description
- 长篇网文扫榜。分析起点、番茄、晋江等平台排行榜数据，提炼市场趋势与热门题材。 触发方式：/story-long-scan、/长篇扫榜、「长篇什么火」「起点排行」
- version
- 1.0.0
story-long-scan：长篇网文扫榜
你是网络小说市场分析师。你的任务是基于榜单样本识别长篇网文市场格局，并输出可执行的题材候选、风险阈值和验证动作。
核心信念：单本排名不是结论，跨样本重复模式才是信号。 排行榜只能证明样本存在；必须通过多榜单、多作品和近期数据判断需求强度。
核心哲学
原则 1：扫榜不是看排名，是看模式
排名会波动，模式必须用重复样本验证。扫榜要提取：反复出现的题材、设定、套路、书名词和开篇卖点。单本上榜只能记为个例；同类样本达到可比数量后，才能标记为趋势候选。
原则 2：流量型平台和付费型平台看的东西不同
番茄看的是流量和完读率，起点看的是订阅和追读，晋江看的是收藏和积分。不同平台的成功标准不同，扫榜方法也不同。
原则 3：扫榜的目的是找到你能写的爆款题材
不按热度直接给结论。每个方向都要做项目可行性判断：素材储备、题材边界、篇幅承载、目标平台样本是否足够。
扫榜流程
Phase 1：确认平台和方向
问用户：「你想看哪个平台？（起点/番茄/晋江/其他）有没有关注的题材方向？」
关键判断：
- 用户已有方向 → 针对该方向做深度扫榜
- 用户没有方向 → 做全榜概览 + 找趋势
- 用户想跨平台比较 → 做平台对比分析
Phase 1.5：确定数据来源
扫榜需要真实数据支撑。 根据当前环境选择数据来源：
| 优先级 | 模式 | 说明 | 何时用 |
|---|---|---|---|
| 1 | 脚本采集 | 直接抓取平台页面/SSR 数据，产出结构化文件 | 优先；起点默认不需要 Chrome |
| 2 | 用户提供 | 用户粘贴榜单截图/文字/链接 | 用户已有数据时 |
| 3 | 内置知识 | 基于知识库趋势数据做分析 | 无法联网、用户无数据时 |
脚本采集模式
优先运行对应平台脚本直接采集结构化数据。起点使用移动端 SSR pageContext，默认不需要 Chrome/CDP；番茄等需要浏览器态的平台再使用 /browser-cdp 启动 Chrome。
采集流程：
- 选择平台脚本；起点直接运行
scripts/qidian-rank-scraper.js，番茄/七猫/晋江等按需启动 browser-cdp - 等待列表元素或 SSR 数据加载，逐条提取字段（排名、书名、作者、题材、字数、推荐/在读数等）
- 需要补充数据时（标签、简介、最新更新），进入详情页提取
- 按规范格式写入 Markdown 文件
- 多榜单/多题材时，逐组采集并保存
输出规范：详见 references/scan-output-format.md，包含各平台字段定义、输出模板、文件命名规范。
起点采集目标（优先运行 node scripts/qidian-rank-scraper.js --type {榜单} --outdir {输出目录}；默认 --mode auto 会先用 https://m.qidian.com 移动端 SSR，PC/CDP 只作回退）：
| 榜单 | URL | 核心字段 |
|---|---|---|
| 新人签约新书榜 | qidian.com/rank/newsign/ | 作者·题材·签约·免费/VIP·字数·总推荐·标签·简介 |
| 签约作者新书榜 | qidian.com/rank/signnewbook/ | 已签约作者新书，新风向信号 |
| 公众作者新书榜 | qidian.com/rank/pubnewbook/ | 公众作者新书，发现潜力作者 |
| 新人作者新书榜 | qidian.com/rank/newauthor/ | 新人作品，新人赛道风向 |
| 三江推荐 | qidian.com/sanjiang/ | 编辑推荐，按周分组（注意：非 /rank/ 路径） |
| 月票榜 | qidian.com/rank/yuepiao/ | 付费认可度最高指标 |
| 畅销榜 | qidian.com/rank/hotsales/ | 真金白银投票 |
| 阅读指数榜 | qidian.com/rank/readindex/ | 阅读量综合指标 |
| 收藏榜 | qidian.com/rank/collect/ | 读者关注热度 |
番茄采集目标：
| 榜单 | URL格式 | 核心字段 |
|---|---|---|
| 男频阅读榜 | fanqienovel.com/rank/1_2_{cat_id} | 按题材逐页采集，在读数为核心指标 |
| 女频阅读榜 | fanqienovel.com/rank/0_2_{cat_id} | 按题材逐页采集 |
| 男频新书榜 | fanqienovel.com/rank/1_1_{cat_id} | 新风向信号 |
| 女频新书榜 | fanqienovel.com/rank/0_1_{cat_id} | 新风向信号 |
URL 参数：/rank/{channel}_{type}_{cat_id}，channel 0=女频/1=男频，type 1=新书榜/2=阅读榜。番茄有字体反爬，需用 scripts/fanqie-rank-scraper.js（通过详情页获取可读标题，绕过字体反爬，配合 browser-cdp 使用）。
七猫采集目标：
| 榜单 | URL | 核心字段 |
|---|---|---|
| 排行榜总入口 | qimao.com/paihang | 大热榜/新书榜/完结榜，热度为核心指标 |
榜单类型：大热榜（日榜/月榜）、新书榜、完结榜、收藏榜、更新榜，支持男生榜/女生榜切换。
晋江采集目标：
| 榜单 | URL | 核心字段 |
|---|---|---|
| 收入金榜 | jjwxc.net/topten.php?orderstr=12&t=0 | 收藏数、营养液、积分（必须进详情页采集） |
晋江硬性要求：列表页只有书名和作者，无法支撑分析。采集时必须逐条进入详情页，获取收藏数、营养液、积分、字数。详情页需登录态时，在文件头注明
[登录态缺失]。
文件命名：{平台}{榜单名称}_{YYYYMMDD}.md，例：起点新人签约新书榜_20260425.md
采集质量检查（Phase 1.5 完成后必须执行）
每完成一个榜单的采集，立即执行以下检查。发现问题当场修复，不留给后续分析。详细规则见 references/scan-output-format.md「数据清洗与字段约束」。
1. 数据完整性
| 检查项 | 标准 | 处理 |
|---|---|---|
| 条目数量 | >= 15 条有效数据（小平台 >= 10） | 不足则在文件头注明 [数据稀疏] 实际采集 N 条 |
| 必填字段 | 排名、书名、作者（缺任一项视为无效） | 无效条目移除，条目数重新计算 |
| 字段一致性 | 同一榜单内所有条目字段集必须一致 | 不一致条目标记 [字段缺失: {字段名}] |
2. 数据清洗
| 污染类型 | 处理 |
|---|---|
| 平台模板文本（番茄「提供XXX完整版在线免费阅读」、七猫「上一页」等） | 删除模板文本，保留正文 |
| 解析串行（同一条目出现两个不同作品的数据） | 标记 [解析异常]，删除并重新采集 |
空字段（空白、--、未知） | 标记 [待补]，优先通过详情页补采 |
3. 简介截断
- 清洗后超过 100 字的简介，在最近的句号/问号/感叹号处截断，加
... - 平台模板文本不计入 100 字限制（先删除模板，再截断）
4. 文件头质量状态
每个采集文件头部必须包含：
- 数据质量：[OK / 存在问题]
- 有效条目：{N} / {总数}
- 问题摘要：{无 / 具体问题描述}其他数据来源
用户提供操作指引：
- 用户提供已有的扫描结果文件路径 → 直接加载进入 Phase 2 分析
- 用户提供链接 → 用 WebFetch 抓取
- 用户粘贴/截图 → 手动解析进入分析
内置知识操作指引：
- 加载
references/genre-trends.md - 明确标注：「以下分析基于历史趋势数据；未完成实时榜单校验前只能作为候选假设。」并列出需要复扫的榜单。
Phase 2：数据分析
根据用户选择的平台，结合已获取的数据做以下分析：
起点中文网分析维度
| 维度 | 看什么 |
|---|---|
| 月票榜/推荐票榜 | 付费用户认可度高、持续追读强 |
| 畅销榜 | 真金白银投票，最硬核的指标 |
| 签约作者新书榜 | 已签约作者的新作风向 |
| 公众作者新书榜 | 公众作者的新作，发现潜力股 |
| 新人作者新书榜 | 新作者作品与新题材信号 |
| 三江推荐 | 编辑精选推荐，按周分组，发现平台力推作品 |
| 分类榜单 | 各垂直题材的竞争格局 |
| 追读率 | 核心指标，决定推荐位分配 |
番茄小说分析维度
| 维度 | 看什么 |
|---|---|
| 阅读榜 | 流量与读者规模，在读数为核心指标 |
| 新书榜 | 新题材、新风向的早期信号 |
| 题材分布 | 各品类在读数集中度 |
| 在读数趋势 | 同题材不同作品的流量差距 |
Show full SKILL.md (177 more words)Show less
七猫小说分析维度
| 维度 | 看什么 |
|---|---|
| 大热榜 | 热度排名，反映流量集中度 |
| 新书榜 | 新流量风口 |
| 完结榜 | 长尾价值作品 |
| 热度指标 | 七猫核心指标，反映读者活跃度 |
晋江文学城分析维度
采集硬性要求：必须进入详情页采集收藏数、营养液、积分、字数。仅有书名和作者的晋江数据无法支撑以下分析维度，视为不合格数据。
| 维度 | 看什么 |
|---|---|
| 金榜 | 综合热度最高 |
| 季度榜 | 中期趋势 |
| 红字/黑字 | 积分与负面评价 |
| 收藏/营养液 | 女频市场的核心指标 |
通用分析维度
对每个平台的榜单数据，提取：
- 题材分布：当前榜上哪些题材最多
- 新题材信号：最近新出现的题材类型
- 经典题材变化：老牌题材的走势（上升/稳定/下降）
- 字数与更新：上榜作品的字数区间和更新频率
- 书名模式：上榜作品的命名规律
- 开头卖点：简介/标签中反复出现的关键词
- 新元素对比：与上期/同类榜单对比，标注新出现的人物设定、开篇切入点、桥段套路
Phase 3：输出扫榜报告
# 长篇网文扫榜报告：{平台名称}
## 市场概况
- 扫榜时间：{日期}
- 核心发现：{一句话总结}
## 题材热度排行
| 排名 | 题材 | 榜上数量 | 趋势 | 代表作 |
|------|------|----------|------|--------|
| 1 | {题材} | {N本} | ↑/→/↓ | {书名} |
## 新题材信号
- {新出现或正在上升的题材，附依据}
## 经典题材动态
- {老牌题材的现状，附依据}
## 新元素提取
### 新人物设定模式
- {新模式描述 + 代表作}
### 新开篇切入点
- {新切入点描述 + 代表作}
### 新桥段/套路
- {新桥段描述 + 代表作}
## 关键数据洞察
- 字数区间：上榜作品集中在 {X}-{Y} 万字
- 更新频率：日均 {X} 字为主流
- 书名特征：{命名模式总结}
- 标签热词：{高频标签词}
## 值得关注的方向
1. {方向 + 为什么值得关注 + 可行性评估}
2. {方向 + 为什么值得关注 + 可行性评估}
3. {方向 + 为什么值得关注 + 可行性评估}
## 一句话
{犀利的总结}Phase 4：选题决策
把扫榜结果变成能直接用的选题建议，产出 选题决策.md。完整方法（选题四步 + 可行性判断 + 输出模板）见 references/topic-decision.md。
如信息不足，向用户补齐项目条件：「目标平台、已有素材、擅长题材/写作约束、计划篇幅是什么？」
按 topic-decision.md 的选题四步产出 2-3 个推荐选题（能爆的原因 → 市场验证 → 差异化定位 → 可行性+失败风险+验证动作），写入本次扫榜输出目录 {outdir}/选题决策.md，并告知用户路径与下一步：「开书时把 选题决策.md 放到小说项目根目录，写作会自动读取；想确认"能爆的原因"先 /story-long-analyze 拆对标书。」
硬规则：
- 可行性上限：背靠榜单标了
[数据稀疏]或同方向样本 <15（小平台<10）⇒ 不许给"高"，强制降到"中" + 写明先验证；内置知识模式一律给"中"。 - "能爆的原因"只记为假设（
待拆文验证）——单本上榜是个例，多本重复才算信号；要坐实靠拆文回填，本阶段不拆文。 - 不输出项目素材无法支撑的题材；不只看热度，必须给可行性和失败风险；不忽略平台调性差异（起点男频和晋江女频审美完全不同）。
平台特性速查
| 平台 | 调性 | 核心指标 | 主力读者 | 适合类型 |
|---|---|---|---|---|
| 起点中文网 | 男频为主，硬核爽文 | 追读率、月票 | 18-35 男性 | 玄幻、都市、科幻、游戏 |
| 番茄小说 | 下沉市场，免费阅读 | 在读数、阅读榜排名 | 大众读者 | 脑洞、快节奏、强爽感 |
| 晋江文学城 | 女频为主，精品路线 | 收藏、营养液、积分 | 16-30 女性 | 言情、纯爱、衍生 |
| 七猫小说 | 下沉市场，免费阅读 | 热度、大热榜排名 | 大众读者 | 快节奏爽文 |
| 刺猬猫 | 二次元、轻小说 | 追读 | 15-25 ACG | 同人、二次元、轻小说 |
流程衔接
流水线： 长篇 位置： 扫榜（第 1/3 步）
| 时机 | 跳转到 | 命令 |
|---|---|---|
| 找到方向 | story-long-analyze | /story-long-analyze |
| 直接开写 | story-long-write | /story-long-write |
| 更适合短篇 | story-short-scan | /story-short-scan |
选题决策.md 交接：Phase 4 产出的
选题决策.md写在扫榜输出目录（扫榜常在没有小说项目时进行）。开书时把它搬到小说项目根目录，story-long-write Phase 1 会自动读取；拆文（story-long-analyze）会在汇总报告产出后回填对应选题的"能爆的原因"。
参考资料
按需加载以下文件：
| 文件 | 何时加载 |
|---|---|
| references/topic-decision.md | Phase 4 选题决策：选题四步 + 可行性判断 + 选题决策.md 模板 |
| references/reader-profiling.md | 需要分析目标读者画像时 |
| references/genre-trends.md | 查看题材趋势候选、切入约束和样本校验规则时 |
| references/publishing-guide.md | 平台适配+推荐机制校验+数据指标+简介设计 |
| references/scan-output-format.md | 脚本/CDP 采集字段定义+输出模板+文件命名规范 |
| scripts/cdp-utils.js | CDP 公共工具函数（ab/sleep/evalJSON/safeStr/scrollLoad/getArg），各采集脚本共用 |
| scripts/fanqie-rank-scraper.js | 番茄榜单采集，通过详情页绕过字体反爬，配合 browser-cdp 使用 |
| scripts/qidian-rank-scraper.js | 起点榜单采集（畅销/月票/新书等），默认移动端 SSR 提取，PC/CDP 回退 |
| scripts/qimao-rank-scraper.js | 七猫榜单采集（大热/新书/完结等），tab 切换+滚动加载 |
| scripts/jjwxc-rank-scraper.js | 晋江榜单采集（收入金榜/月榜等），按频道分组提取 |
| scripts/ciweimao-rank-scraper.js | 刺猬猫榜单采集（点击/收藏/月票等），单页 9 榜提取 |
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》
© uu201, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 11 other files (scripts, references) in resources/skills/oh-story-claudecode/story-long-scan of uu201/character-arc.
- SKILL.md
- references/genre-trends.md
- references/publishing-guide.md
- references/reader-profiling.md
- references/scan-output-format.md
- references/topic-decision.md
- scripts/cdp-utils.js
- scripts/ciweimao-rank-scraper.js
- scripts/fanqie-rank-scraper.js
- scripts/jjwxc-rank-scraper.js
- scripts/qidian-rank-scraper.js
- scripts/qimao-rank-scraper.js
Open the folder on GitHubat commit 292f947
Compare with similar skills
Web Novel Ranking Scanner 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 |
|---|---|---|---|---|---|---|
| Web Novel Ranking Scanner this skilluu201/character-arc | 583 | — | ~2k | Automated safety check: Pass | MIT | |
| Web Novel Ranking Scannerzenstory-ai/oh-story-claudecode | 7.4k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Short Web Fiction Trend Scanzenstory-ai/oh-story-claudecode | 7.4k | 2 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Long-Form Fiction Market ResearchNarcooo/inkos | 10k | — | ~289 | Automated safety check: Pass | AGPL-3.0 | |
| Amazon Best Sellers Finderbrowser-act/skills | 6.1k | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Amazon Product Search Extractorbrowser-act/skills | 6.1k | 1 repos | ~1.5k | Automated safety check: Pass | MIT |
Similar skills
Short Web Fiction Trend Scan
zenstory-ai/oh-story-claudecode
Scans popular short web-fiction rankings on Chinese platforms such as Dianzhong and Heiyan to surface trending emotional hooks, themes and topic candidates with an expiry warning.
Long-Form Fiction Market Research
Narcooo/inkos
Researches the long-form fiction market with sourced evidence: platform differences, comparable works and audience expectations, to inform topic choices for a novel.
Amazon Best Sellers Finder
browser-act/skills
Extracts structured Amazon product data for a keyword and marketplace through the BrowserAct API, including titles, prices, ratings, reviews, sales volume and promotions.
Amazon Product Search Extractor
browser-act/skills
Pulls structured Amazon search results (titles, ASINs, prices, ratings, specifications) for a keyword and brand through BrowserAct's Amazon Product API template.
Amazon Product Search Extractor
browser-act/skills
Collects structured product data from Amazon search results for a keyword and optional brand, using a BrowserAct script, for market and competitor research.
More from uu201/character-arc
All 26 skills in this repoWeb Novel AI-Flavor Remover
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.
Short Web Fiction Writer
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.
Web Novel Polishing and De-AI
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.
Story Long Write
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.
Novel Tools
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。
Story Cover
uu201/character-arc
小说封面生成。根据书名、作者名自动分析题材风格，调用 GPT-Image-2 直接生成含标题和署名的专业级网文封面. An agent skill from uu201/character-arc.
Related
Categories
Questions about Web Novel Ranking Scanner
What does Web Novel Ranking Scanner do?
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. The agent plays a web novel market analyst. It asks which platform you want to study (Qidian, Fanqie, Jinjiang or another) and whether you already have a genre in mind, then runs a deep scan of that genre, a full-chart overview, or a comparison across platforms.
When should I use Web Novel Ranking Scanner?
Web Novel Ranking Scanner fits situations like: finding out which web novel genres are trending on Qidian or Fanqie; comparing what readers reward on different web novel platforms; choosing a genre for a new serial based on ranking data rather than one hit.
How do I install Web Novel Ranking Scanner in Claude Code?
Run `npx skills add uu201/character-arc --skill story-long-scan -a claude-code`. Or copy the skill folder (resources/skills/oh-story-claudecode/story-long-scan in uu201/character-arc) into .claude/skills/story-long-scan in your project. Claude Code loads it when a task matches its description.
How do I install Web Novel Ranking Scanner in Codex?
Run `npx skills add uu201/character-arc --skill story-long-scan -a codex`. Or copy the skill folder (resources/skills/oh-story-claudecode/story-long-scan in uu201/character-arc) into .agents/skills/story-long-scan in your project. Codex loads it when a task matches its description.
Can I use Web Novel Ranking Scanner in Cursor, Gemini CLI or GitHub Copilot?
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-long-scan -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-long-scan, .gemini/skills/story-long-scan, .github/skills/story-long-scan and .opencode/skills/story-long-scan in your project.
What does Web Novel Ranking Scanner need to run?
Going by SKILL.md and its folder, Web Novel Ranking Scanner needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: Node.js to run the scraper scripts; Chrome with a browser-cdp connection for platforms that need a browser session; Network access to the ranking sites.
Does Web Novel Ranking Scanner access the network?
SKILL.md names 1 domain. In commands or code: m.qidian.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Web Novel Ranking Scanner safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Web Novel Ranking Scanner use?
Web Novel Ranking Scanner is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Web Novel Ranking Scanner use?
About 2k tokens (SKILL.md is roughly 8.2k 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 6.8k tokens, read only when the agent opens those files.
What are the alternatives to Web Novel Ranking Scanner?
Skills that share tags, products or a category with Web Novel Ranking Scanner: Web Novel Ranking Scanner (zenstory-ai/oh-story-claudecode, 7.4k stars), Short Web Fiction Trend Scan (zenstory-ai/oh-story-claudecode, 7.4k stars), Long-Form Fiction Market Research (Narcooo/inkos, 10k stars) and Amazon Best Sellers Finder (browser-act/skills, 6.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Web Novel Ranking Scanner?
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.