shuohao-skills is a collection of agent skills for turning a novel into production materials for an AI short-drama pipeline, including character profiles, outlines, art references, scripts, and storyboards. It is for creators using Claude Code or Codex to plan and prepare AI-generated short videos. The catalogue add-ons implement the separate stages of this workflow and can also assemble their reports.
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 eternityspring/shuohao-skills --skill novel-scriptgit clone --depth 1 https://github.com/eternityspring/shuohao-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/eternityspring/shuohao-skills/novel-script)<a href="https://agentmods.dev/skills/eternityspring/shuohao-skills/novel-script"><img src="https://agentmods.dev/badge/skills/eternityspring/shuohao-skills/novel-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/eternityspring/shuohao-skills/novel-script"><img src="https://agentmods.dev/badge/skills/eternityspring/shuohao-skills/novel-script.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00308 | $0.02818 |
| Opus 5 | $0.00154 | $0.01409 |
| Sonnet 5 | $0.00062 | $0.00564 |
| Haiku 4.5 | $0.00031 | $0.00282 |
Grade A, and why
novel-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 9d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
novel-script
给 AI 短剧写剧本。前提刻在骨子里：剧本管戏，分镜管拍——「爽不爽」和「怎么拍」是两种迭代节奏，台词要反复推翻重写，绑上镜头分解每改一句都得重排镜头。所以这层只有集、场次、节拍流，没有镜号；镜头、首帧提示词、生成批次都是下一层分镜 skill 的活。
但有一条底线：台词必须是结构化数据，不能写成散文。每句台词是独立条目（说话人 + 台词 + 语气），动作是独立节拍——这是全部确定性检查的地基：
| 交付 | 解决什么 |
|---|---|
| 逐集时长预算 | 一集三分钟就是三分钟：台词按语速折算、动作按节拍估时，写超写欠当场拦下，不流到生成环节才发现 |
| 节拍流（动作 ⇄ 台词） | 台词直接对接 TTS 逐句生成；动作节拍就是画面要发生的事。混成散文两头都喂不进管线 |
| 每场至少一个动作节拍 | 纯对白的场是广播剧——AI 生成时没有画面可写 |
| 开场钩子 + 结尾悬念 | 短剧的生死线，每集都要落在纸面；钩子不是标签是第一拍——hookBeat 认领具象位置，必须落在全集前 3 拍内（冷开场） |
| 爽点认领 | 大纲说这一集有大爆点，剧本必须有戏认领它——防止改着改着把爆点改丢 |
| 上游对账 | 场景/光照/道具对 art.json、角色对 outline.json，写了美术没登记的光照状态当场报 |
{baseDir} = 本文件所在目录。脚本 {baseDir}/scripts/novel-script.mjs，零依赖，node 直接跑。
边界（不做的事）：不分镜头、无镜号、不写画面生成提示词、不出图、不配乐——分镜层的活一件不碰。不改大纲结构（砍线合人是 novel-outline 的活）；不做角色和场景设定（novel-characters / novel-art 的活）。
Step 0 — 定输入与范围
outline.json 是剧本的直接上游（分集梗概、爽点落点、单集时长都在里面），标准流程从它开始。没有的话先问用户是否跑 novel-outline；用户坚持直接写，就问清集数与单集分钟数，手建骨架，对账门会明说跳过。
一次写几集：默认一批 ≤ 3 集。剧本是全管线改得最凶的一层，小批量出、快拍板、再往下写。用户明确要全剧也分批产出，每批过一次校验。
顺手带上（都可选，给了才对账/显示名字）：
--outline：角色引用对账 + 爽点认领检查 + 报告里 C01 显示成人名--art：场景/光照状态/道具对账 + 报告里 S01 显示成场景名
Step 1 — seed 骨架
node {baseDir}/scripts/novel-script.mjs seed <outline.json> --eps 1-3 > <workdir>/script.json
确定性搬运：目标秒数（单集分钟 × 60）、钩子、悬念、该集爽点认领、候选场景与人物（进 seedNote）。这些事实不要让模型重新想一遍。 scenes 留空，那才是写戏的活。
Step 2 — 逐集写戏
每集一份任务，能并发就并发。每份任务拿到：
{baseDir}/references/script-pass.md和{baseDir}/references/schema.md（读它们，照着做）- 该集的 seed 骨架 + 大纲里这一集的梗概/爽点/人群方案
- 该集用到的场景卡（art.json 里的锚点、光照状态）与角色信息（性情、说话方式——有 cast.json 更好）
- 前一集的结尾悬念（这一集的开场要接得上）
核心要求都在 script-pass.md 里，最重的四条：动作节拍只写常见动作（挑担上船、搭手卸担这种 AI 见过千万次的；伸篙一挡、睫毛颤这种精巧动作生成必崩）；时长预算先于一切（三分钟一集约 50 个节拍，写完自己跑一遍 validate 看秒数）；台词口语、单句一口气、谁的话像谁（有 cast.json 就吃角色的性情与说话方式）；每集第 1 拍冷开场给钩子的具象（hookBeat 认领，门查位置），结尾一拍必须是悬念。
写完把 seedNote 删掉。
Step 3 — 校验 ⛔ 不能跳
node {baseDir}/scripts/novel-script.mjs validate <script.json> \
--outline <outline.json> --art <art.json>
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 160 lines · 308 tokens per session scan A 5e653561304e
novel-script is a skill published in the GitHub repository eternityspring/shuohao-skills (3,123 stars, last pushed 13d ago), licensed Apache-2.0. It adds 308 tokens to every session and 2,818 once invoked, about $0.0015 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.