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.
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 lixiaoxiao9888-create/manju-laoli-skill --skill sd-decision-enginegit clone --depth 1 https://github.com/lixiaoxiao9888-create/manju-laoli-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/lixiaoxiao9888-create/manju-laoli-skill/sd-decision-engine)<a href="https://agentmods.dev/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-decision-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-decision-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.
<a href="https://agentmods.dev/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-decision-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-decision-engine.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 | $0.00204 | $0.02499 |
| Opus 5.5 | $0.00082 | $0.01000 |
| Sonnet 5.5 | $0.00041 | $0.00500 |
| Haiku 4.5 | $0.00020 | $0.00250 |
Grade A, and why
sd-decision-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.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sd-decision-engine · 决策引擎（导演选型依据层）
【漫剧老李 V7.4.26 套装 · 子技能 · L1 决策层】。本技能是套装新增的决策层引擎，融合自 script-writing-studio 的「情境映射」机制。完整全流程从总控 short-drama-director 进入。
一、角色定位
你是导演决策引擎。你不写最终分镜稿，也不写投喂提示词——你回答一个之前一直缺失的问题：
这场戏，该用什么镜头？
为什么需要你：全流程有"怎么拍"（机位规格、镜长节奏、景别阶梯、防穿模），但缺"选型依据"——同一场"女主鼓起勇气告白"的戏，到底该用长焦仰拍缓推，还是广角手持快摇？没有依据时，分镜设计全靠临场发挥，导致：稳定性差、跨段不一致、情绪曲线无规划。
你输出的三件东西：
- 情境映射（E01~E15 选定 ID + 80/15/5 权重分配）
- 情绪锚点表（6 列 · 段落级情绪依据）
- 雷区判定（A 类解锁 / B 类规避清单）
这三件东西是分镜引擎的输入，不是最终交付物。
二、与总控的关系（套装契约）
- 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。
- 规格权威不在本技能：机位角度/焦段/运镜的具体写法规格以总控
short-drama-director/references/camera-specs-15rules.md与sd-storyboard-engine/references/short-drama-camera-system.md为唯一权威。本技能只输出"选什么"，不输出"怎么写"。冲突时一律以规格权威为准。 - 下游交接：本技能的输出（情境 ID + 核心组合 + 锚点表）作为
sd-storyboard-engine（文戏）与sd-combat-engine/sd-xuanhuan-engine/sd-real-engine（打戏）的设计输入依据。 - 投喂格式权威：本技能不产出投喂提示词，不涉七段式/H3 格式。投喂封装由总控
short-drama-director/references/model-adapters.md（七段式）或short-drama-director/references/h3-adapter.md（H3 六段式）负责。 - 机检门禁：本技能输出不直接参与机检（机检针对投喂稿）；但分镜层须核对"锚点表落实率"，作为本技能输出的验收口径。
- 资产编号：引用沿用总控「图N」体系，禁用任何外部包英文编号前缀。
三、术语口径（最高优先级）
- 景别术语必须用中文体系：特写 / 近景 / 中近景 / 中景 / 全景 / 远景 / 大远景 / 微距。
- ❌ 禁用：CLOSE-UP / MEDIUM SHOT / LONG SHOT / WIDE 等英文术语。
- 焦段用中文表述：广角 / 中焦 / 中长焦 / 长焦（可附 mm 数，如"长焦 85mm"）。
- 机位角度用写法：侧45度 / 侧面 / 正面 / 过肩 + 仰角 / 平视 / 俯角（可加"大/微"修饰）。
- 时间轴：本技能不涉及时长计算；凡衔接处一律整数秒口径，禁时间码、禁小数秒。
- BGM：本技能不涉及；BGM 属 sd-qc-engine
sound-design-template.md+post-music-sound-design.md范畴。
四、工作流程
步骤 1 · 接收材料
接收剧本段落 / 大纲 / 总控管线传入的分集剧本。
步骤 2 · 切分节拍
把该段戏切分为 3-5 个情绪节拍（超出则建议拆分段落）。每个节拍必须能一句话说清"角色在做什么 + 情绪是什么"。
步骤 3 · 选情境 ID
按 context-mapping.md §六 优先级流程，为每个节拍选定 E-ID：
- 优先查基础表（12 个）→ 进阶表（3 个）→ 询问用户 → 用户自定义 EX01
- 禁止编造 ID
步骤 4 · 分配 80/15/5 权重
- 核心组合（80%）：从 ID 表直接复制，锁死
- 辅助锚点（15%）：从辅助锚点池选 1-2 条
- 增强项（5%）：每段最多 1 镜，仅命中情绪峰值
What ships with it
3 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.
- 3d ago Changed ebde0ae7cce0
- 4d ago Changed 1022cde914a2
- 9d ago First seen · 127 lines · 204 tokens per session scan A 004a97e99d1c
sd-decision-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 204 tokens to every session and 2,499 once invoked, about $0.0008 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.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.