SuperAPI AI Directory

story-short-scan

General & other

View repository

Updated 10-16 09:45

About this skill

story-short-scan: Short-form web fiction ranking scan

Analyze the short-form market based on real ranking samples, and give authors writable emotional directions, topic candidates, and validation methods.


Core Philosophy

Principle 1: The short-form market is an emotion market

The ranking scan extracts the target emotion, trigger scenes, and emotional climax points from the topic and synopsis, and explains how this content attracts readers. The specific emotional experience cannot be judged from the topic name alone.

Principle 2: The vitality of short fiction lies in spread

When the rankings provide completion, sharing, collection, or like data, compare them according to their respective criteria. Rankings and interaction volume only indicate the attention a sample has received; they cannot be used to conclude story quality or emotional pull effect.

Principle 3: Short-form trends come fast and go fast

The report states the sample date, coverage, credibility of conclusions, and rescan date. Topic signals may become invalid within weeks; after expiration, they serve only as candidate references.


Ranking Scan Process

Phase 1: Confirm platform and direction

When the user has already given a platform or direction, use it directly and ask only about what is missing:"Which platform and what type of short fiction do you want to see? Dianzhong can be collected directly; Heiyan requires logging in to the author backend first; for Zhihu Yanyan, Tomato, and Qimao short fiction, please provide ranking screenshots, text, or links."

Key judgments:

  • User already has a direction → do an in-depth ranking scan for that direction
  • User has no direction → do a full-ranking overview + find trends
  • User wants cross-platform comparison → do a platform comparison analysis

Phase 2: Determine data sources

The ranking scan needs real data support. Choose the data source according to the current environment:

Priority Mode Description When to use
1 Script collection Dianzhong, Heiyan: directly scrape platform pages and produce structured files When a Chrome environment is available (preferred)
2 Provided by author Platforms without scripts, or the author already has rankings Zhihu Yanyan/Tomato short fiction/Qimao short fiction, etc.
3 Built-in knowledge Use historical materials to propose topics to be verified When there is no internet access and the author also has no data
  1. Read only the one for the selected platform:Dianzhong / Heiyan / Platforms without scripts. It contains URLs, commands, fields, troubleshooting, platform analysis dimensions, and how to organize author-provided rankings into files.
  2. Create a new output directory for each ranking scan 扫榜/{YYYYMMDD}/(if scanning again on the same day, add -2) to store this ranking scan, and do not append to old directories; file name {平台}{类型}_{YYYYMMDD}.md, skip if a platform fails. For comparison, read the previous date directory's 扫榜聚合.md。
  3. When there are ranking files, run aggregation:node scripts/aggregate-rank.js {输出目录} --out {输出目录}/扫榜聚合.md --sparse 10 --scale short。The main session reads only this aggregation, and when raw synopsis and character-setting information is needed, sample again:node scripts/aggregate-rank.js {输出目录} --sample {题材/标签/书名词} --n 5. When using only built-in knowledge, skip aggregation.

Built-in knowledge: Load references/real-market-data.md(Cross-platform writing differences comparison), explicitly note "The following analysis is based on historical trend data; until real-time ranking verification is completed, it can only serve as candidate hypotheses." and list the platform pages that need to be re-scanned.


Phase 3: Data Analysis

When real samples are available, use the aggregated results and the platform reference's "analysis dimensions" as the basis, and extract the following information. Trends must be compared across multiple periods of samples using the same methodology; when using only built-in knowledge, provide only candidates to be verified, and do not fill in current counts, proportions, or rises and falls.

  1. Emotion type distribution: Merge types such as angsty romance, twists, suspense, healing, and face-slapping from themes and tags, and compare by sample count
  2. Theme hotspots: What specific settings/scenarios appear repeatedly
  3. Length distribution: Word count distribution and median word count for each theme
  4. Opening patterns: When sampled content includes the beginning of the main text, analyze the first sentence; when only the synopsis is available, judge only the synopsis's writing style
  5. Ending types: The proportion of HE (happy ending)/BE (bad ending)/open ending (when visible in the sample)
  6. Title patterns: Common words in book titles + representative work titles
  7. Character archetype models: Protagonist types that appear repeatedly

Phase 4: Output the ranking scan report

The report discusses market conclusions and directions that can be written. Script names, commands, and collection states such as SKIP do not go into the report; for platforms not collected, explain the reason in one sentence. In the template, directly omit items lacking data; do not fill in rises and falls for a single period of samples, and do not fill in the current popularity ranking based on historical materials.

The report is shown to the author and also written into the output directory's 短篇扫榜结论.md: If the file does not exist, first follow the references/topic-match.md template to write the file header, then write the report as the "Ranking Scan Conclusions" section (if it already exists, replace the entire section).

## 扫榜结论:{平台名称}

### 市场概况
- 扫榜时间:{日期}
- 核心发现:{一句话总结}
- 可信度:{样本多少篇、来自哪几个榜};建议 {日期} 前后再扫一次

### 情绪热度排行
| 排名 | 情绪类型 | 榜上数量 | 趋势 | 代表作 |
|------|----------|----------|------|--------|
| 1 | {类型} | {N篇} | ↑/→/↓ | {标题} |

### 题材热点
| 题材 | 热度 | 竞争程度 | 门槛 | 代表作 |
|------|------|----------|------|--------|
| {题材} | 高/中/低 | 激烈/一般/蓝海 | 高/中/低 | {标题} |

### 关键数据洞察
- 篇幅区间:热门短篇集中在 {X}-{Y} 字
- 开头模式:{高频开头模式}
- 结尾偏好:{HE/BE/开放式的比例}
- 标题特征:{命名规律}
- 人设热词:{高频主角类型}

### 风口预警
- 🔥 正在爆发:{题材} — {依据}
- ⚡ 即将起风:{题材} — {依据}
- ⚠️ 即将饱和:{题材} — {依据}

### 值得写的方向
1. {方向 + 情绪拉扯方式 + 可行性}
2. {方向 + 情绪拉扯方式 + 可行性}
3. {方向 + 情绪拉扯方式 + 可行性}

### 一句话
{犀利总结}

Phase 5: Topic Matching

First read 短篇扫榜结论.md 's "Ranking Scan Conclusions" and the same directory's 扫榜聚合.md; in built-in knowledge mode there is no aggregation table, so read only historical candidates. Combine the project materials and the author's capabilities, and write into the same file's "Topic Matching" section according to references/topic-match.md :

  • Low-complexity candidates: twist type, face-slapping type (clear structure, low validation cost)
  • High-complexity candidates: suspense type, angsty romance type (high technical barriers, requiring evidence of foreshadowing, twists, and emotional control)
  • Priority candidates: directions with clear sample signals and that can be supported by the project materials and the author's capabilities

Key judgments:

  • First explain the emotional experience the topic provides, then explain how theme innovation supports it
  • The first 3 sentences of the opening are a high-risk area for retention, and must establish conflict, identity gap, or an emotional hook
  • Twists are a common传播 engine for short stories; if twists are not used, strong resonance, strong topicality, or a strong aftertaste must be used to compensate for the传播 risk

Platform feature quick reference

The table below is used to locate historical writing styles; the current theme distribution and length are based on this sample; for charging rules, check the platform description.

Platform Historical sample characteristics Comparable types and writing styles
Zhihu Yanyan Story Emotional and cognitive changes, more restrained expression Angsty romance, twists, suspense, realistic
Qimao Short Story Rebirth correction, relationship conflict, advancement in short chapters CEO, realistic, family intrigue, period, suspense
Heiyan Short Story Intense stimulation, angsty romance, and fast-paced conflict Angsty romance, revenge, identity reversal
Dianzhong short stories Concentrated events, direct emotional payoff Family revenge, fake heiress, bullet-comment style

Process linkage

Assembly line: Short stories Position: Scan rankings (Step 1/3)

Timing Jump to Command
Find direction story-short-analyze /story-short-analyze
Start writing directly story-short-write /story-short-write
Better suited for long-form story-long-scan /story-long-scan

Reference materials

Load the following files as needed:

File When to load
Three platform references (links in Phase 2 Step 1) "Determine data source": read only the selected platform's copy
references/topic-match.md Phase 4/5:短篇扫榜结论.md Templates, feasibility limits, and deliverables
scripts/aggregate-rank.js Aggregate the raw rankings in the output directory into a short table (--out saved to disk,--sample extract raw entries), the main session only reads it
references/real-market-data.md Core references: Cross-platform writing differences comparison table, platform intro formula quick reference, popular genre formula quick reference, platform writing characteristics
scripts/cdp-utils.js CDP common utility functions (ab/sleep/evalJSON/safeStr/scrollLoad/getArg), shared by all collection scripts
scripts/dz-browse-scraper.js Dianzhong short story collection (male/female channel), see Dianzhong reference for usage
scripts/heiyan-booklist-scraper.js Heiyan library list collection (login required), see Heiyan reference for usage