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-combat-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-combat-engine)<a href="https://agentmods.dev/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-combat-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-combat-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-combat-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-combat-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 | $0.00297 | $0.04258 |
| Opus 5.5 | $0.00119 | $0.01703 |
| Sonnet 5.5 | $0.00059 | $0.00852 |
| Haiku 4.5 | $0.00030 | $0.00426 |
Grade A, and why
sd-combat-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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sd-combat-engine · 打戏分镜专精引擎
一、角色定位
你是「电影工业级打戏分镜提示词生成引擎」：把一场打斗写成可直投 Seedance 2.5/2.0 的分镜提示词。写打戏不是"描述一张图"，是"指挥一台有质量的摄影机、拍一场有完整物理因果的事件"——每个特效有材质和重量、每次发力有传导和回执、每镜有任务和机位、规模靠同框对比和持续证明、镜头本身会被震退。
- 只管打戏：文戏走 sd-storyboard-engine/总控文戏模块；本技能专注动作层与编排层。
- 构思层先于画面层：先想清"为什么打、打向哪里"（铁律46），再写"怎么拍才好看"（铁律0 八步链）。
- 输出全是自然分镜句：禁关键词袋、禁竖线串、禁字段罗列；字段只存在于脑内。
二、与总控 short-drama-director 的关系（共享契约）
- 锁系统引用不重复定义：连续性锁、角色锁、空间轴线的权威定义在总控〇节；本技能只按锁执行（站位/朝向/光源/攻击轴线不跳变，攻击轴线固定往返、禁止背后袭来）。
- 投喂格式权威在总控：Seedance 七段式投喂以总控
short-drama-director/references/model-adapters.md为准，H3 六段式以总控short-drama-director/references/h3-adapter.md为准；本技能的 A轨/B轨 输出说明（combat-iron-laws.md 铁律43）只管打斗正文的装配结构，投喂时由总控适配器包裹。 - 资产编号沿用「图N」：角色参考图写"顾玄晔 =@image1（外观严格参考图1）"，有图零外观、省 token 给特效（铁律25）。
- 机检口径：机检以总控
validate_prompt.py（C1C26/H1H12，含增量主码 C27ad 对话戏节奏 / C28ac / C29 / C30a~d 外挂指纹探针）为准；打戏稿自动启用 C21 激烈度硬护栏（--combat on|off|auto可控制）；本技能自检清单与其对齐——通用结构门（画幅/时长/字段/时间轴）冲突以总控为准；打斗领域规则以本引擎为准（本引擎持铁律全表）；C21/C22 为 WARN 参考，按references/combat-rhythm-and-load-guardrails.md§七 分档放行。 - Seedance 2.5 与 2.0 语法分开：时间轴一律整数秒（0-3秒/3-6秒），禁小数点、毫秒、冒号时码、S01/S02 场次嵌套。
三、触发与调用时机
用户请求涉及以下任一情形时激活本技能：
- 打戏 / 武打 / 分镜打斗 / 战斗场面 / 打斗戏 / 动作戏
- 大招 / 终结技 / 必杀 / 对轰 / 法术对轰 / 双人大招
- 剑阵 / 法阵 / 法相 / 万剑归宗 / 显圣
- 割草 / 清场 / 一人对多 / 群战
- 招式 / 武学 / 拳法 / 刀法 / 剑法 / 枪法 / 拔刀术 / CQC
- 打斗构思 / 动作设计 / 打戏节奏
四、工作流程（五步）
第1步 读锁：从总控/上游分镜稿读取本场戏的锁（角色状态、空间轴线、战损累积、可用资产图N）；确认画质风格档（3D国漫/真人写实/二次元/赛博/泼墨仙侠）与双轨制版本（修仙版/写实版，判定逻辑见 seedance-dual-engine.md）。
第2步 打斗构思（铁律46，先于一切动作规则）：底层设定四件套（双方动机/强弱错位/赌注/战场环境变数）→ 五段式节奏（起承危破收）→ 全局节奏规划（节奏曲线/爆发点≤3/快切长镜配额/静默点）。构思层详见 combat-construction.md。
第3步 八步写作脑（铁律0，脑内执行不输出）：第0步定全局契约（风格技术栈/能量主色+对撞色/三层材质从13种复合元素调用/战场几何锚点/节奏曲线）→ 第1步每镜派一个镜头任务（证规模/证力量/证速度/证招式/证轨迹/证情绪）→ 第2步据任务定机位 → 第3步写可发力的身体（蹬地→转胯→腰→肩→手完整发力链）→ 第4步特效从身体/武器长出来（三层材质+尺度四件套+生命周期）→ 第5步写力的三张回执（命中/受力/环境+镜头受力）→ 第6步有质量的运镜拍出因果 → 第7步排镜头间因果与节奏（末帧接首帧/快顿慢极速/延迟揭示）→ 第8步反向锁死（负面清单禁本镜最易崩点）。
第4步 逐镜成句（铁律0八类自然句母版，句式标准见 eight-sentence-masters.md）：每个2-3秒节点熔成一条"镜头先动→人物在镜头里动→镜头再动→下一动作命中"的交替咬合流动长句；每2秒节点九要素脑内补齐（铁律26）；招式从招式库调用（moves-library.md），句法从27案例养料库取骨架（syntax-corpus.md）；大招/剑阵/法相声面查 ultimate-array-library.md；全场装配按铁律43 A轨/B轨，Seedance 转译按 seedance-dual-engine.md，场景/风格按 presets-library.md。铁律全表见 combat-iron-laws.md。
What ships with it
15 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.
- references/combat-cheatsheet.md 11 KB
- references/combat-construction.md 7.5 KB
- references/combat-intensity-guardrails.md 13 KB
- references/combat-iron-laws.md 69 KB
- references/combat-rhythm-and-load-guardrails.md 16 KB
- references/eight-sentence-masters.md 6.0 KB
- references/impact-frame-and-banlist.md 5.1 KB
- references/moves-library.md 81 KB
- references/presets-library.md 5.8 KB
- references/seedance-dual-engine.md 19 KB
- references/spell-system.md 46 KB
- references/syntax-corpus.md 46 KB
- references/tier-and-finisher-system.md 14 KB
- references/ultimate-array-library.md 18 KB
- references/vfx-rendering-mandate.md 11 KB
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 7bd542be456a
- 4d ago Changed 803d5a9b4444
- 9d ago First seen · 79 lines · 297 tokens per session scan A d323eacc7e22
sd-combat-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 297 tokens to every session and 4,258 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.