Sd Decision Engine

CommunityPopular

lixiaoxiao9888-create

sd-decision-engine

【套装内部技能 · 全流程用户通常无需直接调用；直接说需求给总控 short-drama-director 即可，总控会自动路由到本技能】【漫剧老李 V7.4.26 套装 · 子技能】导演决策引擎（分镜选型依据层）：情境映射 E01~E15 + 80/15/5 权重机制 + 情绪锚点表 + 构图雷区 A/B 双态白名单，回答'这场戏该用什么镜头'，为分镜引擎提供选型依据。触发词：情境映射、这场戏用什么机位、情绪锚点、节拍表、雷区、构图雷区、正面居中能不能用、这镜该用什么。本技能为套装成员，完整全流程从总控 short-drama-director 进入。

Overview

Publisher	lixiaoxiao9888-create
Repository	`manju-laoli-skill`
Skill name	`sd-decision-engine`
Stars	1.8K
Forks	192
Bundled files	3
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
3 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by lixiaoxiao9888-create on GitHub. Read the source before you install it.

Installation

Install the Sd Decision Engine AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/lixiaoxiao9888-create/manju-laoli-skill/tree/main/sd-decision-engine
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/lixiaoxiao9888-create/manju-laoli-skill.git /tmp/manju-laoli-skill
mkdir -p .claude/skills
cp -r /tmp/manju-laoli-skill/sd-decision-engine .claude/skills/sd-decision-engine

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sd Decision Engine in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Sd Decision Engine on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Sd Decision Engine is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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

步骤 5 · 雷区判定

按 forbidden-zone-whitelist.md §六流程逐节拍检查：

A 类是否命中白名单？命中则标注解锁项 + 配套约束
B 类强制写「限制」字段规避

步骤 6 · 输出

输出三件套：

情绪锚点表（6 列 · 工程版）
情境对照表（用户友好版）
分镜数量决策说明（一句话）
（如有雷区）雷区判定清单

输出格式详见 references/emotion-anchor-table.md。

五、输出格式

标准输出结构：


【大分镜 #BXX · 情绪锚点表】

| 节拍 # | 情绪关键词 | 服务的剧本动作 | 情境 ID | 核心组合摘要（80%定死） | 解锁雷区 |
|---|---|---|---|---|---|
| ... |

【本段情境对照】
- 节拍 1：xxx → Exx 情境名
...

本段选择 X 个分镜，原因：____。

【雷区判定】（如有）
- 节拍 N：命中 A1 正面居中 → 解锁（白名单 ② 仪式感）· 配套后缀"强对称构图"
- 全段：B 类规避项 = 物体穿身 / 服装突变 → 已生成限制字段

不输出：最终分镜稿、投喂提示词、时长标注、镜头具体写法（焦段数值细节/运镜曲线等——那是分镜引擎的活）。

六、高频铁律速查

节拍数 3-5，超 5 拆段，少于 3 说明戏不够。
核心组合 80% 锁死，不许 LLM 替换/删除/自由发挥。
情境 ID 禁止编造，只能从基础表/进阶表/用户自定义三处取。
节拍之间必须有变化，4 个相同情绪 = 戏没推进。
B 类雷区永不解锁；A 类解锁必须标注 + 配套约束 + 写清理由。
术语全中文：景别/焦段/机位一律用体系，禁英文。
不越界：不写分镜稿、不写投喂格式、不定时长——那是别的技能的活。
同段内 ID 可重复，但动态变化由辅助锚点承担。

七、规则库索引

文件	内容	何时读
`references/context-mapping.md`	情境映射库：E01~E15（12 基础 + 3 进阶）核心组合、80/15/5 权重机制、辅助锚点池、增强项池、选 ID 优先级流程、雷区解锁标注规范	选情境 ID、分配权重时
`references/forbidden-zone-whitelist.md`	构图雷区 A/B 双态系统：A 类 7 条（可白名单解锁）+ B 类 7 条（永不解锁）+ 多人/微距/类型化次级雷区 + 自查流程 + 限制字段自动链路	每次设计镜头后自查、判定雷区时
`references/emotion-anchor-table.md`	情绪锚点表：6 列标准格式、硬约束 6 条、三层作用、用户友好版输出、分镜数量决策说明、完整示例	输出锚点表时

八、快速调用语

"这段戏帮我做情境映射" → 输出情绪锚点表三件套
"这场戏该用什么机位" → 给出 E-ID + 核心组合
"这段分镜的雷区帮我查" → 雷区判定清单
"帮我做情绪锚点表" → 6 列标准表
"正面居中能不能用" → A1 白名单判定

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Sd Decision Engine AI skill do?

Why use Sd Decision Engine on TypingMind?

Because you install it once and use it with any model. Sd Decision Engine is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Sd Decision Engine in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lixiaoxiao9888-create/manju-laoli-skill/tree/main/sd-decision-engine. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Sd Decision Engine?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Sd Decision Engine?

As many as you like. As long as a model supports skills, you can use Sd Decision Engine with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Sd Decision Engine AI skill free?

Yes. It is published on GitHub by lixiaoxiao9888-create under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Channel Message Flows

openclaw

OrganizationPopular

Use when running QA Lab channel message flow evidence.

Claw Score

Audit or refresh OpenClaw maturity scorecard docs from root taxonomy, maturity scores, and QA evidence artifacts without using maintainer discrawl data or committed inventory reports.

Clawdtributor

Clawtributor PRs here, last week or another window: discover conversation refs, recheck GitHub, rank by impact.

Clawsweeper

Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

sd-decision-engine · 决策引擎（导演选型依据层）

一、角色定位

二、与总控的关系（套装契约）

三、术语口径（最高优先级）

四、工作流程

步骤 1 · 接收材料

步骤 2 · 切分节拍

步骤 3 · 选情境 ID

步骤 4 · 分配 80/15/5 权重

步骤 5 · 雷区判定

步骤 6 · 输出

五、输出格式

六、高频铁律速查

七、规则库索引

八、快速调用语

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now