Not in the top 1,000 by GitHub stars
QQ-L-XX/novel-deconstruct
AI拆书技能 for Claude Code——输入番茄小说链接，自动字体解码→定量扫描→场景级深度拆解→18章结构化报告。融合麦基故事+许荣哲小说课+布兰德成为作家三书体系。
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
c75702bece3d → c75702bece3d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → c75702bece3d
No earlier version was observed for comparison.
17GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days
Heat
0.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
novel-deconstruct
When your agent uses it
拆书——对网络小说进行深度结构分析。输入番茄小说等平台的链接，自动抓取、解码、分析，输出七步骨架/冲突三层/人物弧光/对话技法/节奏控制等维度的拆书报告。触发词：拆书、拆解、分析这本小说、帮我看看这本书。
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
2,657 tokensWhen the skill is activated
Reference documents
1,528 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 检测流程
- Step 1: 获取元数据
- Step 2: 抓取正文
- Step 3: 定量扫描（必做，不可跳过）
- Step 4: 场景级深度拆解
- Step 5: 逐章价值变化追踪
- Step 6: 结构层分析
- Step 7: 输出报告
- 工具脚本
- 依赖
- 分析参照
Scripts executed separately
tools/decode_font.pytools/fetch_novel.py
Files
.gitignoreasset145 bytesLICENSEasset1,063 bytesREADME.mddoc4,861 bytesSKILL.mdcore8,209 bytesSKILL.mdcore8,209 bytestools/decode_font.pyruns4,197 bytestools/fetch_novel.pyruns7,243 bytes
Read SKILL.md
# Novel Deconstruct — 拆书技能
对网络小说进行系统性的写作技法分析。自动处理字体反爬、章节抓取、定量扫描、场景级深度拆解全流程。
## 检测流程
```
用户提供小说链接
├─ 番茄小说 (fanqienovel.com) → 字体解码 + API抓取
├─ 其他平台 → 通用网页抓取
└─ 用户直接粘贴文本 → 跳过抓取，直接分析
```
---Skills included
- novel-deconstruct
Repository facts
- License
- MIT
- Created
- Jun 9, 2026
- Last pushed
- Jun 9, 2026
- Forks
- 3
- Open issues
- 0
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1 note
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 18 network referencesin 3 files: README.md:5 tools/decode_font.py:19 tools/fetch_novel.py:32
- No hidden or obfuscated text
- No instruction overrides
- 2 executable scriptsin 2 files: tools/decode_font.py:1 tools/fetch_novel.py:1
- No access to secrets
- No requests to vote in Hot
Show all 20 signals by file
README.md
- Network accessline 5
[](LICENSE) - Network accessline 6
[](https://claude.ai/code) - Network accessline 7
[](https://python.org) - Network accessline 31
# 克隆到 Claude Code 技能目录 git clone https://github.com/QQ-L-XX/novel-deconstruct.git \ - Network accessline 32
git clone https://github.com/QQ-L-XX/novel-deconstruct.git \ - Network accessline 47
https://fanqienovel.com/page/7519389279345200152 帮我拆一下这本书 - Network accessline 111
- **[awesome-novel-skill](https://github.com/modoojunko/awesome-novel-skill)**：AI小说创作工作流。拆书分析出的技法规律，可以注入到 awesome-novel-skill 的写作风格设定中进行实战应用
tools/decode_font.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 19
with open(html_path, 'r', encoding='utf-8') as f: html = f.read() match = re.search(r'url\((https://[^)]*\.woff2)\)', html) - Network accessline 20
html = f.read() match = re.search(r'url\((https://[^)]*\.woff2)\)', html) if match: - Network accessline 21
match = re.search(r'url\((https://[^)]*\.woff2)\)', html) - Network accessline 29
resp = requests.get(font_url, headers={ - Network accessline 94
if len(sys.argv) < 2: print("Usage: python decode_font.py <font_url|html_file> [output_json]") print(" font_url: https://lf6-awef.bytetos.com/obj/awesome-font/c/xxx.woff2") - Network accessline 95
print("Usage: python decode_font.py <font_url|html_file> [output_json]") print(" font_url: https://lf6-awef.bytetos.com/obj/awesome-font/c/xxx.woff2") print(" html_file: path to fanqie novel page HTML (auto-extracts font - Network accessline 96
print(" font_url: https://lf6-awef.bytetos.com/obj/awesome-font/c/xxx.woff2")
tools/fetch_novel.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 32
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"} resp = requests.get(page_url, headers=headers, timeout=30) - Network accessline 33
resp = requests.get(page_url, headers=headers, timeout=30) - Network accessline 70
url = f"https://fanqienovel.com/reader/{item_id}" resp = requests.get(url, headers=headers, timeout=30) - Network accessline 71
resp = requests.get(url, headers=headers, timeout=30)
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Declared and executed: 1 fact
- Contacts lf6-awef.bytetos.com, which SKILL.md, the README and the plugin manifest do not mentiontools/decode_font.py:96High confidence
Signal confidence: 20 facts
- Network access in prose of documentationREADME.md:5Low confidence
- Network access in prose of documentationREADME.md:6Low confidence
- Network access in prose of documentationREADME.md:7Low confidence
- Network access in code of documentationREADME.md:31Low confidence
- Network access in code of documentationREADME.md:32Low confidence
- Network access in code of documentationREADME.md:47Low confidence
- Network access in prose of documentationREADME.md:111Low confidence
- Executable script in code of a file that runstools/decode_font.py:1High confidence
- Network access in code of a file that runstools/decode_font.py:19High confidence
- Network access in code of a file that runstools/decode_font.py:20High confidence
- Network access in code of a file that runstools/decode_font.py:21High confidence
- Network access in code of a file that runstools/decode_font.py:29High confidence
- Network access in code of a file that runstools/decode_font.py:94High confidence
- Network access in code of a file that runstools/decode_font.py:95High confidence
- Network access in code of a file that runstools/decode_font.py:96High confidence
- Executable script in code of a file that runstools/fetch_novel.py:1High confidence
- Network access in code of a file that runstools/fetch_novel.py:32High confidence
- Network access in code of a file that runstools/fetch_novel.py:33High confidence
- Network access in code of a file that runstools/fetch_novel.py:70High confidence
- Network access in code of a file that runstools/fetch_novel.py:71High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
