Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tance-mang/chinese-webnovel-skills --skill scriptgit clone --depth 1 https://github.com/tance-mang/chinese-webnovel-skillsWrote 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/tance-mang/chinese-webnovel-skills/script)<a href="https://agentmods.dev/skills/tance-mang/chinese-webnovel-skills/script"><img src="https://agentmods.dev/badge/skills/tance-mang/chinese-webnovel-skills/script/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/tance-mang/chinese-webnovel-skills/script"><img src="https://agentmods.dev/badge/skills/tance-mang/chinese-webnovel-skills/script.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 | $0.00097 | $0.00814 |
| Opus 5 | $0.00048 | $0.00407 |
| Sonnet 5 | $0.00019 | $0.00163 |
| Haiku 4.5 | $0.00010 | $0.00081 |
Grade A, and why
script 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 12d 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.
What it actually says
剧本写作（script）
剧本和小说是两套语言。铁律：只写镜头能拍到的，看得见、听得见。不写心理活动、不写"他想起三年前"，情绪靠动作、表情、台词演出来。一切格式调 references/script-format.md。
何时用
- 写剧本 / 短剧 / 分集剧本 / 台词本
- 把小说（网文）改成剧本
- 问剧本格式怎么排
默认：竖屏短剧（当下最火）
不特别说明就按竖屏短剧写：约 80–100 集，单集 1–2 分钟（剧本约 300–600 字），黄金 3 秒抓人，爽点密集，每集结尾强卡点。
四种用法
A. 写短剧剧本
- 先定题材/频道/主线爽点（调
trope-library.md、hook-library.md）。 - 按标准格式写（场景标题 + 客观动作描述 + 人物台词 + 表演提示），见
script-format.md。 - 单集结构：开场钩子（前 3 句立冲突）→ 冲突升级 → 小反转/爽点 → 集尾卡点。
- 每集结尾在最炸的前一秒切断，留钩子。
B. 小说改剧本
砍心理描写、留动作和对白；按地点/时间拆场景；把叙述信息变成可拍的动作或说出口的台词；按短剧密度重排节奏，爽点提前、卡点压集尾。
C. 影视/长剧本
标准剧本格式（场景标题/动作行/人物台词），节奏可比短剧缓，重人物和结构。投正规渠道可用好莱坞格式（INT./EXT.）。
D. 格式校验
检查：是否有非镜头内容（心理/旁白解释）、场景标题是否规范、台词是否能演、每集有没有卡点。
格式要点（速记）
第 N 集
场景 N 地点 日／夜 内／外
客观动作描述，只写能拍的。
人物名（表演提示）：台词。
（集尾卡点：一行动作或台词制造悬念。）
- 表演提示用圆括号（），不用【】。
- 画外音标（V.O.），闪回标 闪回：。
原则
- 只写能拍的：删一切心理描写和作者解释。
- 台词能演：短、口语、一句一意思（调
dialogue-library.md）。 - 一场一冲突，没戏就删。
- 去 AI 味同样适用：台词别书面别工整，动作别堆形容词。
下一步
剧本写完 → 用 deslop/dialogue 打磨台词；要导出 Word 可配合 draft 思路。
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.
- 12d ago First seen · 58 lines · 97 tokens per session scan A 592f53009558
script is a skill published in the GitHub repository tance-mang/chinese-webnovel-skills (58 stars, last pushed 3mo ago), licensed MIT. It adds 97 tokens to every session and 814 once invoked, about $0.0005 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
fec-svg-animation
A workflow for creating or reviewing animated SVG graphics, which are scalable vector images such as icons, logos, illustrations, and diagrams. It covers CSS, SMIL, Framer Motion, GSAP, accessibility, and reduced-motion behavior.
fec-web-video-presentation
A method for turning articles, talks, courses, product demonstrations, or spoken scripts into a recordable 16:9 web presentation. Each screen is designed around one part of the spoken explanation and can include visual changes, diagrams, data, or media.
extract-y2b-insights
Extract the most controversial or genuinely-novel insights from a YouTube video and output them both as a .txt file and printed in the terminal. Use when the user provides a YouTube URL and wants the key ideas, hot takes, or original thinking — NOT video clips. Optionally cross-checks ideas against the web to judge…
html-slides
Used when the user asks to "create HTML slides", "generate an HTML presentation", "make animated slides", "build interactive slides", "create web slides", "GSAP presentation", "browser-based slides", "convert PPTX to HTML", "animated deck", "reveal.js slides", or when the output format is HTML for any presentation…
mono-color
A design tool for generating original one-colour or limited two-colour editorial images from themes, text, objects, or reference photos. It supports visual styles such as risograph printing and zine posters.
add-subtitles
Add burned-in subtitles to a video the user uploads or points to on disk. Use when the user provides a local video file (mp4/mov/etc.) and wants captions/subtitles added to it. Transcribes the audio with Whisper and burns styled captions directly into the video.