What makes Novel Character Graph notable?

953 downloads. Trust evidence available

How should Novel Character Graph be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Novel Character Graph

Professional long-form novel analysis and character relationship mapping + theme song generation. Automatically handles GBK/UTF-8 encoding, multi-GB file chu... Skill: Novel Character Graph Owner: mengbin92 Summary: Professional long-form novel analysis and character relationship mapping + theme song generation. Automatically handles GBK/UTF-8 encoding, multi-GB file chu... Tags: character-relationship:1.0.0, latest:1.0.2, novel:1.0.0, visualization:1.0.0 Version history: v1.0.2 | 2026-04-26T13:54:42.076Z | auto - Initial release of version 1.0.2. - Added _meta.json file. v1

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

953

Updated

Oct 12, 2026

Version

1.0.2

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 953 downloads reported by the source. Last updated 10/12/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 12, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 12, 2026
Adoption signal: 953 downloadsadoption · observed Oct 12, 2026
Latest release: 1.0.2release · observed Apr 26, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 1.0.2release
- Initial release of version 1.0.2. - Added `_meta.json` file.
Observed Apr 26, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s17335d97qcgwk12m5ge52yg8s83g8z5:novel-character-graph

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-mengbin92-novel-character-graph/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

33,866 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: novel-character-graph
description: "Professional long-form novel analysis and character relationship mapping + theme song generation. Automatically handles GBK/UTF-8 encoding, multi-GB file chunking, chapter-by-chapter incremental parsing, supports TXT/EPUB/PDF/DOCX novel formats. Outputs complete character system, relationship maps, worldviews, weapon/item systems, interactive visualization HTML, and AI-generated theme songs (Suno). Use when users ask for: novel analysis, character mapping, relationship graphs, worldview architecture, story timeline organization, manga/comic adaptation settings, novel theme song, ending song, OST."
tags: [novel, analysis, character, relationship, graph, xianxia, wuxia, fantasy, song, music]
triggers:
  - 小说分析
  - 人物图谱
  - 人物关系
  - 关系图谱
  - 世界观
  - 小说人物
  - 角色设定
  - 主题曲
  - 片头曲
  - 片尾曲
  - OST
  - 小说配乐
required_commands:
  - iconv
  - ebook-convert
  - pdftotext
  - pandoc
usage_hint: >
  当用户提到「小说分析」「人物图谱」「关系图」「世界观」「角色设定」时使用本skill。
  当用户提到「主题曲」「片头曲」「片尾曲」「OST」「配乐」时也使用本skill（可独立使用，
  不需要先做完整人物分析，直接基于用户描述的小说类型/情绪生成即可）。
---

# 小说人物图谱专业分析Skill + 主题曲生成

## 核心能力

本Skill专业处理百万字级长篇小说深度分析，解决大文件无法一次性解析的问题，并能为小说生成专属主题曲。

---

## 第一步：文件预处理流程

### 1.1 文件格式检测与编码修复

```bash
# 1. 检测文件基本信息
file -i <小说文件>
wc -l <小说文件>
ls -lh <小说文件>

# 2. 编码自动修复（中文小说90%为GBK编码）
cat <小说文件> | iconv -f GBK -t UTF-8 2>/dev/null > decoded.tmp && mv decoded.tmp <小说文件>_utf8.txt

# 3. 编码失败备选方案
iconv -f GB18030 -t UTF-8 <小说文件> 2>/dev/null
iconv -f BIG5 -t UTF-8 <小说文件> 2>/dev/null
```

### 1.2 支持的主流小说格式

| 格式 | 处理方法 | 依赖命令 |
|------|---------|---------|
| ✅ `.txt` | 直接分段读取 | - |
| ✅ `.epub` | `ebook-convert file.epub file.txt` | `calibre-bin` |
| ✅ `.pdf` | `pdftotext -layout file.pdf output.txt` | `poppler-utils` |
| ✅ `.docx` | `pandoc -s file.docx -o output.txt` | `pandoc` |
| ✅ `.mobi` | `ebook-convert file.mobi file.txt` | `calibre-bin` |

> 安装依赖：`sudo apt install calibre-bin poppler-utils pandoc`

---

## 第二步：大文件智能分段解析

### 2.1 分段策略（>10万行强制分段）

```
文件大小 < 500KB  → 一次性读取
500KB - 2MB → 分2-4段
2MB - 10MB → 每500行一段增量解析
> 10MB → 每1000行一段增量解析
```

### 2.2 分段读取Shell模板

```bash
# 分段读取命令模板
cat <小说文件> | head -n +500          # 第1段
cat <小说文件> | tail -n +501 | head -n 500  # 第2段
cat <小说文件> | tail -n +1001 | head -n 500 # 第3段
# ... 以此类推
```

### 2.3 每段解析核心提取项

每段必须提取并增量更新：
- ✅ 新出场人物全名 + 别名 + 外号
- ✅ 人物关系变化（敌对/盟友/情侣/师徒/血缘）
- ✅ 关键剧情节点 + 时间线推进
- ✅ 武功/功法/神器/丹药系统更新
- ✅ 势力阵营/宗门/国家变化
- ✅ 重要伏笔 + 世界观补全

---

## 第三步：人物体系标准化建模

### 3.1 人物层级分类体系

| 层级 | 定义标准 | 详细程度 |
|------|---------|---------|
| S级核心人物 | 主角团 + 最终BOSS + 关键导师 | 深度解析：性格/成长线/经典场景/漫画设定 |
| A级重要人物 | 主要反派 + 主要盟友 + 主要女主 | 完整人物卡 |
| B级次要人物 | 重要配角 + 各门派掌门 | 基础信息 + 立场 |
| C级NPC | 路人甲 + 一次性炮灰 | 只计数不展开 |

### 3.2 标准人物卡模板

```markdown
### 🎭 人物名称
- **身份**：详细身份定位
- **修为/境界**：
- **性格特质**：3-5个核心关键词
- **核心能力/功法**：
- **人物关系网**：
  - ❤️ 恋人：xxx
  - 👨‍🏫 师父：xxx
  - ⚔️ 死敌：xxx
  - 👬 兄弟：xxx
- **经典分镜/漫画设定**：
```

---

## 第四步：关系图谱构建规范

### 4.1 四大核心关系类型

使用标准Emoji统一标记：
| 关系类型 | Emoji标记 |
|---------|-----------|
| 爱情/道侣 | ❤️ 💕 |

_meta.json

{
  "ownerId": "kn73pfccc8e95j989m8js0x9zx82p86q",
  "slug": "novel-character-graph",
  "version": "1.0.2",
  "publishedAt": 1777211682076
}

references/format_handbook.md

# 小说格式处理手册

## 编码问题终极解决方案

### 中文小说编码问题诊断

99%的中文TXT小说编码问题：
- 老小说：GBK / GB18030 编码（起点/纵横等老站）
- 新小说：UTF-8 编码
- 台湾小说：BIG5 编码

### 批量编码转换脚本

```bash
# 批量转换GBK→UTF-8
for f in *.txt; do
    iconv -f GBK -t UTF-8 "$f" -o "${f%.txt}_utf8.txt" 2>/dev/null && mv "${f%.txt}_utf8.txt" "$f" && echo "OK: $f" || echo "FAIL: $f"
done
```

---

## 各格式转换工具安装

### EPUB/MOBI 处理

```bash
# Debian/Ubuntu
sudo apt install calibre-bin poppler-utils pandoc

# 转换命令
ebook-convert novel.epub novel.txt
ebook-convert novel.mobi novel.txt
```

### PDF 处理

```bash
# 最佳文本提取工具
pdftotext -layout novel.pdf output.txt
pdftotext -f 10 -l 100 novel.pdf output.txt  # 指定页码范围
```

### DOCX 处理

```bash
pandoc -s novel.docx -o output.txt
```

---

## 大文件分段Shell脚本

```bash
#!/bin/bash
# split_novel.sh - 智能分段脚本

FILE=$1
LINES_PER_CHUNK=500
TOTAL_LINES=$(wc -l < "$FILE")
CHUNKS=$(( (TOTAL_LINES + LINES_PER_CHUNK - 1) / LINES_PER_CHUNK ))

echo "Total: $TOTAL_LINES lines, split into $CHUNKS chunks"

for i in $(seq 1 $CHUNKS); do
    START=$(( (i-1) * LINES_PER_CHUNK + 1 ))
    echo "=== Chunk $i / $CHUNKS (lines $START - $((START + LINES_PER_CHUNK - 1))) ==="
    cat "$FILE" | tail -n +$START | head -n $LINES_PER_CHUNK
done
```

skill-card.md

## Description:

Analyzes long-form novels, maps characters and relationships, prepares worldview and timeline outputs, builds interactive HTML relationship graphs, and drafts theme-song prompts.

This skill is ready for commercial/non-commercial use.

## Publisher:

[mengbin92](https://clawhub.ai/user/mengbin92)

### License/Terms of Use:

MIT-0

## Use Case:

Developers, writers, and content teams use this skill to analyze novels in TXT, EPUB, PDF, DOCX, or MOBI form and produce character systems, relationship maps, timelines, worldview notes, interactive graph reports, and song-generation prompts.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The security evidence reports that the skill explicitly allows dependency installation without user approval.

Mitigation: Require explicit user approval before any apt, sudo, pip, media conversion, or package-installation command is run.

Risk: Generated HTML reports can expose users to unsafe content if untrusted novel data is inserted without escaping or if remote scripts are loaded.

Mitigation: Open generated reports only after reviewing the template and escaping behavior, and avoid remote script loading for untrusted inputs.

Risk: Preprocessing and conversion commands can overwrite or transform source novel files.

Mitigation: Keep backups of source novels and write converted files, split chapters, Markdown reports, and HTML outputs to a separate working directory.

## Reference(s):

- [Format Handbook](references/format_handbook.md)
- [ClawHub Skill Page](https://clawhub.ai/mengbin92/skills/novel-character-graph)

## Skill Output:

**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance, files]

**Output Format:** [Markdown, shell commands, Python-generated HTML, and Suno-style song prompt text]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Can create novel analysis Markdown files and an interactive HTML relationship graph; users should review commands and generated HTML before use.]

## Skill Version(s):

1.0.2 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 4d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular