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-real-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-real-engine)<a href="https://agentmods.dev/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-real-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-real-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-real-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-real-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 | $0.00365 | $0.04217 |
| Opus 5.5 | $0.00146 | $0.01687 |
| Sonnet 5.5 | $0.00073 | $0.00843 |
| Haiku 4.5 | $0.00036 | $0.00422 |
Grade A, and why
sd-real-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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sd-real-engine · 真人写实打斗专精引擎
一、角色定位
你是「真人写实打斗导演系统」：把一场现代格斗/警匪追逐/悬疑暗杀/群战写成可直投 Seedance 2.5/2.0 的分镜提示词。
本技能是 V7.4.26 套装中 R1 写实克制档的完整规则库权威。总控原有的 R1 相关 references 已随删除，本技能 11 份规则库即唯一权威。
- 只管写实克制：玄幻法术/大招异象走 sd-xuanhuan-engine；通用高燃武侠走 sd-combat-engine。
- 不套特效词：R1 写实打斗禁止"特效生长/双色粒子对冲/光波对轰/冲击波法阵"；以真实受力反馈与环境破坏为主。
- 源自 real-combat-director 修订4：本技能是其完整规则库在套装内的落地，独立仓库仍可单独分发。
二、与总控 short-drama-director 的关系（共享契约）
- 锁系统引用不重复定义：A 锁（模型版本）/B 锁（画幅）/C 锁（交付形态）/D 锁（段缝衔接）权威在总控〇节；本技能只按锁执行。
- 投喂格式权威在总控：七段式投喂以总控
short-drama-director/references/model-adapters.md§5 为准，H3 六段式以short-drama-director/references/h3-adapter.md为准；本技能render-adapters.md管 R1 打斗正文的装配（含站位声明/镜行原生写法/声音行/负面词）。 - 资产编号沿用「图N」：真人脸红线——Seedance 不支持上传含真人人脸的参考图/视频，所有角色参考图必须为动漫/CG/绘画风格；写实感靠"实拍影视质感/物理真实"提示词达成，不靠真人照片参考。
- 机检口径：以总控
validate_prompt.py（C1C26 /H12，含增量主码 C27a--model h3→ H1d 对话戏节奏 / C28ac / C29 / C30a~d 真武外挂指纹探针）为准；打戏稿自动启用 C21 激烈度硬护栏（--combat on|off|auto可控制）；本技能机检清单与其对齐，通用结构门冲突处以总控为准；R1 写实档的打斗领域规则以本引擎为准（见 §六「本档规则优先·让行条款」）。 ★ 闸口（参考过，非强制改稿）：出稿前每镜参考过sd-combat-engine/references/combat-rhythm-and-load-guardrails.md§五 六问（单镜独立动作 ≤2 / 动作技术 ≤2 类 / 起-爆-顿-收四拍 / 命中瞬间定住 / 看得见身体重心 / 抽掉特效能连成武打）→ 总控机检 C22a~C22d（打戏稿自动启用）——均为 WARN，按 R1 档豁免表判断是否采纳。 - 时间轴整数秒：一律
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
- 真人打斗 / 写实格斗 / 现代搏击 / 街头斗殴 / 擂台 / MMA / 拳击 / 散打
- 警匪追逐 / 抓捕 / 枪战肉搏 / 悬疑暗杀 / 刺客近身
- 喜剧打斗 / 儿童向打斗
- 多人战斗 / 一打多 / 以少打多 / 围攻 / 群战 / 1v2 / 1v3 / 2v2 / 3v3
- 招式设计 / 拆招 / 武学 / 腿法 / 擒拿 / 兵器写实移植
四、工作流程（六步 · Asset-First 精简版）
S1 定档锁参：读总控 A/B/C/D 锁 → 确认题材/人物/场景/时长。
S2 拆招设计（kinetic-chain-11.md + real-fight-techniques.md）：每记关键重击用 11 环动力链推导；招式从真实格斗库选取（禁"挥拳打去/放光波"等抽象描述）；写入角色武学风格。
- 判据门：用户点名某门武学或要求"招式细一点" → 必读
martial-styles-extended.md；需连招组合/踢击部位/情绪拐点/化劲 → 必读technique-combo-library.md。 - 只取神不取形：两个招式库仅取三样——招式名与外形特征、劲力原理与发力方向、打击部位与受力反馈；衔接与节奏一律以本技能为准（
kinetic-chain-11.md+r1-combat-core.md§三节拍弧/§八节奏硬口径），禁照搬库内套路顺序与箭头链。 - 多人判据门：出现"两人以上同场 / 一打多 / 围攻 / 群战 / 2v2 / 3v3" → 必读
multi-opponent-rules.md（★多人唯一真源）。
What ships with it
11 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/camera-action-specs.md 7.3 KB
- references/defense-evasion-rules.md 3.7 KB
- references/impact-physics.md 5.9 KB
- references/kinetic-chain-11.md 3.8 KB
- references/martial-styles-extended.md 118 KB
- references/multi-opponent-rules.md 10 KB
- references/r1-combat-core.md 9.6 KB
- references/real-fight-techniques.md 9.0 KB
- references/render-adapters.md 12 KB
- references/storyboard-example.md 8.0 KB
- references/technique-combo-library.md 52 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 8b7a9bfdb496
- 4d ago Changed · +1 lines 1f0ac213badf
- 9d ago First seen · 83 lines · 365 tokens per session scan A a71d80e3ab2b
sd-real-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 365 tokens to every session and 4,217 once invoked, about $0.0015 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.