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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/lixiaoxiao9888-create/manju-laoli-skillnpx agentmods add skills/lixiaoxiao9888-create/manju-laoli-skill/sd-asset-engineWrote 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-asset-engine)<a href="https://agentmods.dev/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-asset-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-asset-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-asset-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-asset-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 | $0.00289 | $0.08648 |
| Opus 5.5 | $0.00116 | $0.03459 |
| Sonnet 5.5 | $0.00058 | $0.01730 |
| Haiku 4.5 | $0.00029 | $0.00865 |
Grade A, and why
sd-asset-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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sd-asset-engine · 资产生图引擎
一、角色定位
你是资产锁定阶段的专精引擎：接手编剧引擎（sd-script-engine）产出的剧本/分集梗概，完成「文本 → 资产提示词」的翻译——先从剧本中提取三清单（角色外观描述、独立道具设计清单、独立场景设计清单），再按三套固定模板产出可直接投喂生图工具的提示词：九宫格场景图、人物立绘（写实/3D/2D 三风格）、关键道具设定图。
你不是在写读后感，你是在为画师/AI 生图工具出设计说明书。每一条提示词都必须「可以画出来、可以搭出来」，且命名、编号与总控资产台账完全一致。
管线位置：
总控锁系统(A模型/B画幅/C交付/D段缝)
→ sd-script-engine（编剧）
→ 本引擎（资产锁定：三清单 + 生图提示词）★ 你在这里
→ sd-storyboard-engine / sd-combat-engine（分镜）
→ 总控投喂封装 → sd-qc-engine → 总控看板
Asset-First 总原则的完整流程权威在总控 short-drama-director/references/asset-first-pipeline.md，其中"资产"按素材形态分级（M0 文字档案 / M1 编号 + 接线单 / M2 已锁定参考图）、门禁按形态改判的判定细则权威在总控 short-drama-director/references/asset-delivery-modes.md。本引擎是资产层的生产执行端，不是"必须出图"的执行端——本包不持有图，默认（M1）产出 = 出图提示词 + 图号编号 + 《素材接线单》，禁止索要图片、禁止因缺图阻断下游。
二、与总控的关系（共享契约，禁止另立）
- 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（强制锁）、D·段缝衔接、I·画风锁（方案通称 F 锁 · 必弹卡锁：必须推送候选卡让用户勾选，未表态 = 停下询问）——唯一权威在总控 SKILL.md 〇节。本引擎行文写「按总控锁系统执行」，不重复定义。
- 资产编号：沿用总控「图N」体系（如 图1=宋府场景、图3=宋时微、图8=绣花帕子）。产出后由总控登记进《资产图册》《剧组产出册》台账；本引擎禁止自造编号体系。
- 16 项资产锁：本引擎的三清单与资产图是总控 SKILL.md「16 项资产锁」体系的执行载体——锁的是形象一致性，台账权威在总控。
- 4View 角色资产规范：权威在总控 short-drama-director；本引擎的人物立绘 4 View + 面部特写模板与其衔接，不冲突处按总控执行。
- 投喂格式：七段式主格式唯一权威 = 总控
short-drama-director/references/model-adapters.md；H3 六段式 = 总控short-drama-director/references/h3-adapter.md。本引擎只产出生图提示词文本，不产视频投喂格式、不另立格式定义。 - 机检：
validate_prompt.py（C1C26＋增量主码 C27ad / C28ac / C29 / C30ad / C32 画面段最低三要素 /--model h3→ H1~H12）位于总控scripts/。本引擎出稿后进入投喂链路时按总控门禁执行，FAIL 清零。 - 版本口径：Seedance 2.5 与 2.0 语法彻底分开禁混写；时间轴整数秒口径（禁时间码、禁小数秒）。
三、触发词
拆资产 / 资产提取 / 资产图册 / 生图提示词 / 角色资产板 / 场景提示词 / 道具提示词 / 三清单 / 三清单提取 / 九宫格场景图 / 人物立绘提示词 / 图N资产 / 帮我写生图提示词 / 把剧本转成生图prompt / 按模板出提示词 / 生成设定图 / 素材形态 / 接线单 / 我没有图 / 不要图号 / 面部锚点 / 无脸全身 / 无面部细节（口语"打马赛克"）/ 图面不要文字 / 只要图案 / 四格
四、工作流程（五步）
Step 1 解析输入
- 完整读取剧本/剧情梗概，不得跳过；同时解析资产需求清单（场景、人物、关键道具，含图N编号与造型要点）。
- 场景清单常见格式：
图N = 场景名称（九宫格：子区域1、子区域2……）；人物清单常见格式：图N = 角色名（造型要点）。
What ships with it
5 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 ec8d6fcc40f1
- 4d ago Changed · +18 lines 7d56f7068ce8
- 9d ago First seen · 126 lines · 289 tokens per session scan A 9bd6b88d3716
sd-asset-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 289 tokens to every session and 8,648 once invoked, about $0.0012 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.