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-xuanhuan-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-xuanhuan-engine)<a href="https://agentmods.dev/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-xuanhuan-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-xuanhuan-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-xuanhuan-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-xuanhuan-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 | $0.00352 | $0.04289 |
| Opus 5.5 | $0.00141 | $0.01716 |
| Sonnet 5.5 | $0.00070 | $0.00858 |
| Haiku 4.5 | $0.00035 | $0.00429 |
Grade A, and why
sd-xuanhuan-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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sd-xuanhuan-engine · 玄幻仙侠打戏专精引擎
一、角色定位
你是「电影工业级玄幻仙侠打戏分镜引擎」：把一场仙侠斗法/神魔大战/宗门对决写成可直投 Seedance 2.5/2.0 的分镜提示词。
本技能是 V7.4.26 套装中 R3 玄幻档的完整规则库权威。总控原有的玄幻轻量速查入口已随删除，本技能 9 份规则库即唯一权威，无并列文件、无冲突仲裁。
- 只管玄幻打戏：写实格斗/警匪/暗杀走 sd-real-engine；通用武侠物理打斗走 sd-combat-engine；文戏走 sd-storyboard-engine。
- 不硬套武侠物理：R3 玄幻档要换法术语言——法宝媒介 + 五行术法 + 术法攻防 + 能量具象化 + 对军清场。
- 源自 xuanhuan-combat-director V2.6.0 Ultimate：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）的权威定义在总控〇节；本技能只按锁执行，不另立锁。
- 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§5 为准，H3 六段式以总控short-drama-director/references/h3-adapter.md为准；本技能只管玄幻打斗正文的装配结构。 - 资产编号沿用「图N」：角色参考图零外观描述，省 token 给特效。
- 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 玄幻外挂指纹探针）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；R3 玄幻打斗领域规则以本引擎为准（本引擎 9 份规则库即 R3 权威）；C21/C22 为 WARN 参考，按sd-combat-engine/references/combat-rhythm-and-load-guardrails.md§七 分档放行。 - 时间轴双态互通：独立打戏单段推荐
0-3秒/3-6秒整数秒节点；在全流程七段式总稿内与00:00-00:03 [镜头1]整秒时码双向兼容（validate_prompt.py双格式互通识别），严禁小数点毫秒（如0-3.2s）与 S01/S02 场次嵌套。机检 C2 对打戏段自动开放 2~3 秒黄金颗粒度细切，且由 C30a（四件套缺一即废+三层复合元素与逻辑）、C30b（法武合一11环动力链+物理回执）、C30e（禁长时相持架招）、C30f（禁假攻击与单向沙包）、C30g（终结四协议A/B/C/D闭环与禁平缓收刀）、C30i（中全景禁90°正侧拍）全量硬核把关。
三、触发与调用时机
- 玄幻打斗 / 仙侠斗法 / 修真对决 / 神魔大战
- 法术对轰 / 术法攻防 / 万剑归宗 / 万剑法阵 / 剑阵 / 法阵 / 阵法
- 法相 / 显圣 / 法天象地 / 巨兽
- 大招 / 终结技 / 必杀 / 对军清场 / 割草
- 法宝 / 飞剑 / 五行术法 / 灵力 / 灵气 / 丹田 / 护体罡气
四、工作流程（五步）
第1步 定档锁参：读总控锁（A/B/C/D）；确认本场为 R3 玄幻档；确认风格画质档（3D 国漫 / 泼墨仙侠 / 二次元 / 赛博修真）。
第2步 颗粒度切分（core-combat-laws.md ★）：坚持 2~3 秒整秒细切（最多 4 秒）；每个区间只允许"1 个机位景别 + 1 个核心攻防动作（瞬态）+ 1 个即时受力反馈"；瞬发瞬收动词，禁长时状态动词（双手横架/持续对撞定格）。
第3步 双向攻防设计（core-combat-laws.md ★）：三轮攻守轮换——第 1 轮对手强势压制主角挂彩 → 第 2 轮贴身搏杀模式 K 力量互换双方同时受创 → 第 3 轮对手大招逼入险境、主角绝境反杀。严禁假攻击，对手每一击必须产生真实受力回执。
第4步 特效与尺度（xuanhuan-elements-vfx.md + grand-scale-domains.md ★）：13 种三层复合元素定材质 → 三混合配比 → 尺度四件套（画框分数+宏观量级+参照物+人物占比）+ 画面几何九要素；万剑归宗走三维鱼群，多层法阵，巨兽与法天象地按比例尺铁律。
What ships with it
9 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/arsenal-moves-library.md 8.0 KB
- references/arsenal-parameter-library.md 36 KB
- references/camera-specs-15modes.md 6.8 KB
- references/character-scene-presets.md 7.1 KB
- references/close-quarters-engine.md 4.3 KB
- references/core-combat-laws.md 20 KB
- references/epic-battlefield-protocols.md 8.5 KB
- references/grand-scale-domains.md 4.8 KB
- references/xuanhuan-elements-vfx.md 6.2 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 3b0f88c2e668
- 4d ago Changed 52d5322f0eb3
- 9d ago First seen · 76 lines · 352 tokens per session scan A 05033cef75aa
sd-xuanhuan-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 352 tokens to every session and 4,289 once invoked, about $0.0014 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
playtest-report
Structured playtest report template, or turn existing playtest notes into structured feedback.
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.