tech-book-extractor-skills 1.0.9 → 1.0.10
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "tech-book-extractor-skills",
|
|
3
|
-
"version": "1.0.
|
|
3
|
+
"version": "1.0.10",
|
|
4
4
|
"description": "Claude Code skills for deep technical book reading — structure parsing (Stage 1) and chapter extraction (Stage 2).",
|
|
5
5
|
"bin": {
|
|
6
6
|
"tech-book-extractor-skills": "bin/install.js"
|
|
@@ -8,6 +8,21 @@ description: "技术书章节深度萃取——把一章钻透。自动生成骨
|
|
|
8
8
|
|
|
9
9
|
---
|
|
10
10
|
|
|
11
|
+
## ⛔ 硬约束：骨架必须先于萃取
|
|
12
|
+
|
|
13
|
+
**本章 skill 的执行前提是 Stage 1 骨架（`stage1-skeleton.json`）已存在。**
|
|
14
|
+
|
|
15
|
+
执行前必须检查：`{output_dir}/{书名}/stage1-skeleton.json` 是否存在。
|
|
16
|
+
|
|
17
|
+
| 骨架状态 | 行为 |
|
|
18
|
+
|---------|------|
|
|
19
|
+
| 存在 | ✅ 读取骨架，进入萃取流程 |
|
|
20
|
+
| 不存在 | 🚫 **中止本章萃取**，提示用户先运行 `/book-map` 生成骨架 |
|
|
21
|
+
|
|
22
|
+
> **绝对禁止**：在骨架缺失时跳过骨架直接萃取。骨架是萃取的导航系统，没有骨架的萃取等于盲飞。
|
|
23
|
+
|
|
24
|
+
---
|
|
25
|
+
|
|
11
26
|
## 前置步骤：从 PDF 提取单章文本
|
|
12
27
|
|
|
13
28
|
如果章节原文在 PDF 里，先用提取脚本拿到文字：
|