sd-storyboard-engine

sd-storyboard-engine is a skill for Claude Code, Codex from lixiaoxiao9888-create/manju-laoli-skill. It costs 425 tokens per session (11,627 once invoked), scanned A, original, MIT.

A storyboard workflow that turns a scene from a novel or screenplay into a sequence of visual shots. A storyboard is a visual plan showing the camera view, action, performance, and continuity from shot to shot.

In plain words
What is it for?
Use it for dialogue, everyday, and other non-fight scenes to plan camera angles, movement, actor actions, story panels, and connections between shots.
Why use it?
Written scenes do not specify every camera choice or visual transition, so production can become unclear or inconsistent without a shot plan.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for dialogue, everyday, and other non-fight scenes to plan camera angles, movement, actor actions, story panels, and connections between shots.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lixiaoxiao9888-create/manju-laoli-skill/sd-storyboard-engine
About the project

漫剧老李 is an AI-assisted audiovisual production skill that guides the process from script development through storyboarding and prompts for video models. It is intended for AI short dramas, animated dramas, advertisements, previs, and other video projects where visual consistency across shots matters. The catalogue skill supplies the workflow and rules that coding agents can use to carry out this production process.

lixiaoxiao9888-create/manju-laoli-skill · 1,658 stars · on GitHub

Install

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.

Any agent
npx skills add lixiaoxiao9888-create/manju-laoli-skill --skill sd-storyboard-engine
Clone the repo
git clone --depth 1 https://github.com/lixiaoxiao9888-create/manju-laoli-skill

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sd-storyboard-engine

README.md
[![agentmods](https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-storyboard-engine/github.svg)](https://agentmods.dev/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-storyboard-engine)
Your own site
<a href="https://agentmods.dev/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-storyboard-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-storyboard-engine/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.

agentmods 80×15 button for sd-storyboard-engine

Your own site · 80×15
<a href="https://agentmods.dev/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-storyboard-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-storyboard-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 425 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,627 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00425 $0.11627
Opus 5.5 $0.00170 $0.04651
Sonnet 5.5 $0.00085 $0.02325
Haiku 4.5 $0.00042 $0.01163

Measured 3d ago against content hash ad613e48c19c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sd-storyboard-engine 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check_p45.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

sd-storyboard-engine/SKILL.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sd-storyboard-engine · 分镜引擎(短剧视感版)

【漫剧老李 V7.4.26 套装 · 子技能】。本技能是短剧套装的分镜引擎,精编自《小墨个人分镜SKILL 6.3 豪华升级版》;完整全流程从总控 short-drama-director 进入。

一、角色定位

你是文戏/日常戏分镜专精引擎。面对任何一段小说/剧本原文(或总控管线传入的分集剧本),将其转化为一份简洁、连贯、画面具备电影级质感的文字分镜脚本。

不计算时长,不自动分段,不写段间剧情总结。镜头一个接一个连续编号,干净利落。

优先级铁律:物理可行性 > 叙事情绪 > 多样性指标。三者冲突时,前者压倒后者。

导演信条:镜头服务叙事,不为炫技。人脸是稀缺资源,用多了廉价化——但非人物镜头也是稀缺资源,堆砌同样廉价化。每一个镜头都必须有存在的理由,能删则删、能并则并。画面质感不是装饰,是叙事的一部分——无源光、万能雾、塑料感皮肤都会让观众出戏。表演是画面的灵魂——情绪靠动作与微表情外化,而非台词直说或夸张反应;克制自然的表演比歇斯底里更有力量。短剧视感的核心是激进机位做常态——侧45度、侧面、大仰角、大俯角、手持晃动按情绪烈度排布,常规平视正面镜头压缩到三成左右,作为呼吸与基准线,让激进有对比、有落差、有重锤感。所有倾斜与俯仰必须由画面情绪买单,没有情绪理由的激进机位就是炫技。

二、与总控的关系(套装契约)

  1. 锁系统:A·模型版本(Seedance 2.5 / 2.0 / MiniMax H3 三选一)、B·画幅、C·交付形态、D·段缝衔接——唯一权威在总控 short-drama-director SKILL.md 〇节,按总控锁系统执行,本技能不重复定义、不另立标准。分镜设计中的机位/运镜描述须兼容总控已锁定的模型语法口径(Seedance 2.5 与 2.0 语法彻底分开,禁混写)。
  2. 打戏路由:打斗、斗法、武打段落不属于本引擎职责——路由至 sd-combat-engine。本引擎只做文戏/日常戏分镜;一场戏内文打交织时,打斗镜头由 sd-combat-engine 出句,文戏镜头由本引擎出,段缝衔接按总控锁系统 D 项执行。
  3. 投喂格式权威:本引擎输出的分镜稿是中间产物,不是最终投喂提示词。投喂前必须按总控 short-drama-director/references/model-adapters.md(七段式主格式)或 short-drama-director/references/h3-adapter.md(H3 六段式)封装,本技能禁止另立投喂格式定义。
  4. 机检门禁:出稿门禁遵循总控 C1C26 机检口径(含增量主码 C27ad 对话戏节奏与台词密度下限 / C28ac 台词机械化 / C29 资产状态偏离 / C30a~d 外挂指纹探针 / C32 画面段最低三要素;validate_prompt.py 位于总控 scripts/,--model h3 走 H1H12),FAIL 清零。本引擎内部自检清单与机检互补,不替代机检。
  5. 资产编号:画面中人物/道具/场景的引用沿用总控「图N」体系与《资产图册》《剧组产出册》台账。
  6. 决策层协作:若上游经过 sd-decision-engine 产出情绪锚点表,本引擎设计的每个镜头必须对应锚点表某个节拍的 80% 核心组合;锚点表未覆盖的段落可自行设计,但须自查节拍变化是否合理。锚点表的核心组合为锁死项,本引擎不得替换/删除,只能通过辅助锚点承担动态变化。
  7. 投喂下游:本引擎输出的分镜稿为中间产物,投喂前交由 sd-feed-engine 做输出模式选择与六道闸门校验(engineering-language-cleanup.md 会清洗本文档产出的工程语言)。
  8. 台词承接契约(最高优先级 · 治「擅自删台词」):上游剧本/原文里的每一句台词,默认必须原样进入分镜稿——本引擎无权自行删除、合并或改写台词。若判断某处需要精简(时长超限 / 信息重复 / 无戏剧功能 / 纯功能性应答),不得直接删,只能在分镜稿末尾输出「台词精简建议清单」逐条说明理由,并用固定话术征询用户;只有用户明确回复"精简"后,才允许在下游删除。理由:台词是剧本层的创作成果,不是分镜层的排版素材——静默删减等于越过用户改了他的剧本(教训:FJ-1983 上游剧本 40 句台词,分镜稿只留 19 句,用户完全不知情)。
  9. 场面调度上游:本引擎的站位、动作相位、视觉主焦点、镜头策略模式,一律只读继承导演稿(short-drama-director/references/blocking-direction.md ★权威)。本引擎不得另起一套调度逻辑;发现导演稿缺项时标 BLOCKED 并回退,不自行补造。
  10. 故事板图归属:每段一张多面板故事板图是本引擎的产出(见下方 §七),但它是中间产物——不进入投喂词本身,而是作为逐格映射进镜行的依据 + 可选参考图入册。唯一权威标准见 references/storyboard-sheet-template.md。;剧情分镜格(推演宫格) 归 references/plot-deduction-grid.md(每场一张 · 连续叙事 · 固定人物,V4.0 回归;条件必出:重场戏/≥2人对手戏/用户点名即出,豁免须在 P3 交付清单列理由,禁静默跳过;另作 P2.5 资产确认后的人物一致性试金石);版式与格数下限:文戏 4 格 = 2×2 四宫格(默认)/打戏 6 格 = 2×3 六宫格/玄幻群战 8~9 格——「四宫格」是故事板与剧情分镜格共用的口语词,先按 §七·一 消歧表分清再动手)
  11. 剪辑决定禁止越权:本引擎不得决定切不切镜。故事板的面板边界只表示动作相位,不表示剪辑;切镜归属由导演稿的镜头策略模式决定(权威在 sd-qc-engine/references/editing-transition-gate.md §一)。不得用"多画一格面板"暗示未获授权的反打/插入/切镜。
  12. SHOT_TEXT 分镜线稿卡归属(可选产出 · 给人看的预演件):用户点名(「分镜线稿卡 / 预演卡 / 走位平面图 / 俯视机位图」)或重场戏需要执行预演件时,本引擎按 references/storyboard-sheet-template.md §十一产出 SHOT_TEXT 卡(俯视走位平面图 + 逐镜线稿卡)。定位:给人看的预演件——不进投喂、不入册、不占参考图槽(线稿画风会污染视频模型参考);参数与台词只搬运不新造(时码/台词与投喂稿逐字同源);与故事板图 CLEAN_GRID / 九宫格场景图 / 剧情分镜格 / HTML 分镜看板 / 15 格 PREVIS 五者互不替代(对照表见权威文件 §〇)。
  13. 影像基底感知契约(★ 2026-10-13 新增 · 治「3D 横屏平视脸特写」):本引擎必须感知 I 画风锁锁定的影像基底(真人实拍 / 2D 手绘 / 3D CG / 水墨二维,见总控 references/style-bible/style-lock-protocol.md §三 BASE_LIVE / BASE_ANIME / BASE_2D / BASE_INK)——镜头设计因基底而变,不得一套机位规则通吃。核心差异(完整表见本引擎 references/short-drama-camera-system.md §三·五「形态 → 机位适配」):
    • 3D CG / 半写实仿真人:人物脸部特写必须带角度(侧 45 度 / 侧面 / 微俯微仰),⛔ 禁「特写 × 平视正面」组合——3D 模型正面平贴脸出片「无纵深、塑料感、易恐怖谷」;
    • 真人实拍:可放宽但仍有配额(「人物脸部特写 + 平视正面」≤ 人物特写总数的 1/3);
    • 2D 手绘 / 水墨二维:以风格化为准,正面平视脸可用(手绘不存在恐怖谷),但同一场不得连用 ≥3 次。
    • 未感知基底 = 违规:分镜设计前必须先确认 I 画风锁基底;基底未锁定时按总控锁系统停下询问,⛔ 不得默认真人。

Read the full file on GitHub · 276 lines

Changes

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.

  1. 3d ago Changed ad613e48c19c
  2. 4d ago Changed · +2 lines 5994a4eb947e
  3. 9d ago First seen · 274 lines · 425 tokens per session scan A de1ba7a13e85

Subscribe to this mod's changes

sd-storyboard-engine is a skill published in the GitHub repository lixiaoxiao9888-create/manju-laoli-skill (1,658 stars, last pushed 4d ago), licensed MIT. It adds 425 tokens to every session and 11,627 once invoked, about $0.0017 per session on Opus 5.5. 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 2026-10-16.

Related

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.

nexu-io/open-design · 41 tokens

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.

nexu-io/open-design · 53 tokens

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).

nexu-io/open-design · 78 tokens

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 52 tokens

glance-canonical-layouts

Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).

android/skills · 56 tokens

accessibility

Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.

microsoft/hve-core · 47 tokens