Skip to content
Agentmart
Submit a tool

hit-script-retrieval-skill

爆款剧本检索技能。使用混合搜索(语义+关键词)检索最相关的爆款剧本,为生成提供参考。

Skill by Supreme-Ultimate

IndexedMIT★ 179
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/supreme-ultimate-hit-script-retrieval-skill

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

爆款剧本检索技能。使用混合搜索(语义+关键词)检索最相关的爆款剧本,为生成提供参考。

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/hit-script-retrieval-skill

What's inside

Skill name
hit-script-retrieval-skill
Description
爆款剧本检索技能。使用混合搜索(语义+关键词)检索最相关的爆款剧本,为生成提供参考。
License
MIT
Instructions
398 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# 爆款剧本检索技能

## 必读

1. `../../references/00-first-principles.md` — 第一性原则(可拍性、留存性、一致性)
2. `../../references/03-script-writing-standard.md` — 剧本写作标准(对话比、视觉标记、网文感)
3. `../../references/12-genre-specific-techniques.md` — 类型化技巧(男频/女频特征)

## 功能

从117部爆款短剧剧本中检索最相关的剧本,为剧本生成提供参考。

## 检索方法

使用**混合搜索**(Chroma语义搜索 + TF-IDF关键词搜索):
- 语义搜索权重:60%(理解深层含义)
- 关键词搜索权重:40%(精确匹配)

## 使用场景

### 1. 剧本生成前检索

在生成剧本前,根据以下信息检索相关剧本:
- 剧本类型(复仇/逆袭/穿越/重生等)
- 情绪基调(愤怒/悲伤/爽感/紧张等)
- 主要情节(打脸/揭秘/对抗/和解等)
- 人物关系(主角vs反派/主角vs配角等)
- 场景类型(豪门/古代/现代/职场等)

**示例查询**:
```
"复仇女主霸总豪门打脸"
"穿越古代逆袭当皇后"
"重生复仇虐恋"
```

### 2. 检索结果使用

检索返回Top 5最相关的剧本,包含:
- 剧本文件名
- 相似度得分
- 内容预览(前200字符)
- 完整文件路径

**注入到context**:
```
参考以下爆款剧本的风格和节奏:

【参考剧本1】《封总的复仇娇妻》
- 相似度:0.892
- 特点:复仇女主、霸总、豪门恩怨、打脸爽剧
- 节奏:快节奏、高冲突密度、强情绪冲击
- 对话风格:短句、高对话比、视觉标记丰富

【参考剧本2】...
```

## 执行步骤

### Step 1: 构建检索查询

从当前剧本需求中提取关键信息:
```python
# 示例:从分集规划中提取
query_parts = []
if "类型" in episode_plan:
    query_parts.append(episode_plan["类型"])
if "情绪" in episode_plan:
    query_parts.append(episode_plan["情绪"])
if "主要情节" in episode_plan:
    query_parts.append(episode_plan["主要情节"])

query = " ".join(query_parts)
# 结果:query = "复仇 愤怒 打脸揭秘"
```

### Step 2: 执行检索

使用混合搜索引擎:
```python
from hybrid_search import HybridSearchEngine

# 初始化(只需一次)
engine = HybridSearchEngine("../../knowledge/hit-scripts-md")

# 检索Top 5
results = engine.hybrid_search(
    query=query,
    n_results=5,
    semantic_weight=0.6,
    keyword_weight=0.4
)
```

### Step 3: 读取完整内容

```python
reference_scripts = []
for result in results:
    with open(result['path'], 'r', encoding='utf-8') as f:
        content = f.read()
        reference_scripts.append({
            'filename': result['filename'],
            'score': result['score'],
            'content': content[:5000]  # 取前5000字符
        })
```

### Step 4: 注入到生成提示词

```
你是一名短剧编剧,现在需要创作第N集剧本。

【参考爆款剧本】
以下是5个最相关的爆款剧本,请参考它们的:
- 节奏:场景数、冲突密度、时长分布
- 对话:句长、对话比、视觉标记
- 情绪:情绪强度、情感极性摆动
- 框架:开局-发展-高潮-反转-结局

From Supreme-Ultimate/novel-to-script-team, MIT.

More from Supreme-Ultimate/novel-to-script-team

Signals

Stars
179
Forks
35
Open issues
0
Last commit (this folder)
May 2, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Supreme-Ultimate

Cite this page

hit-script-retrieval-skill. Agent Mart. https://agentmart.dev/skills/supreme-ultimate-hit-script-retrieval-skill (last updated 2026-10-24)