Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-teamnpx agentmods add skills/supreme-ultimate/novel-to-script-team/hit-script-retrieval-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/hit-script-retrieval-skill)<a href="https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/hit-script-retrieval-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/hit-script-retrieval-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/hit-script-retrieval-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/hit-script-retrieval-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.03651 |
| Opus 5 | $0.00020 | $0.01826 |
| Sonnet 5 | $0.00008 | $0.00730 |
| Haiku 4.5 | $0.00004 | $0.00365 |
Grade A, and why
hit-script-retrieval-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
爆款剧本检索技能
必读
../../references/00-first-principles.md— 第一性原则(可拍性、留存性、一致性)../../references/03-script-writing-standard.md— 剧本写作标准(对话比、视觉标记、网文感)../../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:
# 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:
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
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
1. 《封总的复仇娇妻》(相似度:0.892)
[内容节选...]
2. 《...》(相似度:0.856)
[内容节选...]
...
【当前任务】
根据以上参考,创作第N集剧本...
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 402 lines · 40 tokens per session scan A d42ea411e1d0
hit-script-retrieval-skill is a skill published in the GitHub repository Supreme-Ultimate/novel-to-script-team (163 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 3,651 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.