liuyunlong2021-wq

Use when a user asks to find, explain, inspect, summarize, or visualize knowledge already stored in a project Wiki. Trigger on 查询Wiki, 查角色, 查设定, 查看状态, 知识库状态, 关系图, or 项目现在怎么样.

Use when a user asks to inspect a project Wiki for consistency, broken links, missing relationships, contradictions, stale structure, or a health report. Trigger on 巡检Wiki, 一致性检查, 知识库体检, 查断链, 查矛盾, or 查有没有漏改.

Use when a user asks to fill, update, maintain, or refresh a project Wiki from recent writing, development work, conversations, Raw material, documents, or verified evidence. Trigger on 填充Wiki, 整理记忆体, 更新知识库, 刷新热缓存, 开发收尾, 续写前整理, or 我刚写完/做完一段内容.

Use when a user asks to correct a confirmed Wiki error, apply a Wiki inspection report, repair a deterministic link or name, or extend an existing Wiki structure. Trigger on 修正Wiki, 执行巡检修正, 修复断链, 改错, 新建分类, or Wiki架构扩展.

Use when a user asks to create, convert, organize, or complete a project Wiki from code, documents, writing, conversations, or other material. Trigger on 转Wiki, 建Wiki, 建知识库, 初始化知识库, 项目Wiki, 文档归档, 内容转Wiki, or 整理成知识库.

Use when a user asks to create a character design prompt, character concept image, or reusable character visual asset from story material.

Use when a user asks to create, develop, continue, or organize a short-drama world, characters, story, script, or production material.

Use when a user asks to define a film or drama project style, visual direction, aspect ratio, color language, or reusable style design.

Use when converting character analysis results into Banana JSON prompts for text-to-image generation. This model benefits from explicit detail, reference-sheet layout, and strong negative constraints.

Use when converting shot-design results into Banana 3x3 storyboard grid JSON prompts for the current flashxiaolagu mainline. This skill is assembly-only and should write short natural-language cinematic beats, not rigid keyword chains.

Use when converting prop analysis results into Banana JSON prompts for the current Banana/Veo pipeline. This stage should preserve visible structure, layout blocks, multi-view detail, and generation-critical markings.

Use when converting scene analysis results into Banana JSON prompts for the current Banana/Veo pipeline. This stage should lead with one decisive narrative identity sentence, then give layered scene control rather than one giant brute-force room dump.

Use when one or more split storyboard panel images such as `storyboards/frames/.../panel_004.png` need Nano Banana Pro image editing instead of rerunning the whole Banana storyboard batch. This skill writes structured Chinese edit prompts for panel-level character, scene, prop, or fused repairs while explicitly preserving locked elements and continuity.

Use when analyzing script characters for the current Banana/Veo short-drama pipeline. Output a dual-layer character asset spec: a slim control_table for downstream automation and a lightweight production_bible for human review and reuse.

Use when converting raw script into a material engineering book before shot design. This stage translates audience-facing script into production-facing reusable material units such as dialogue coverage, action chain fragments, reveals, inserts, resets, and reactions for downstream shot design.

Use when analyzing script props for the current Banana/Veo short-drama pipeline. Output a dual-layer prop asset spec that is specific enough for detail-hungry downstream image models.

小说世界模型。基于「世界观+极致角色+催化剂→故事自然涌现」核心机制。覆盖长篇小说全流程：灵感→市场→核心梗→角色→大纲→章纲→文案→正文→复盘。渐进式逐章创作，每一步让用户做选择。输出写入 wiki/剧本/ wiki/角色/ wiki/世界/ wiki/剧情/，配合 JC-yizhixing（巡检）和 JC-jiyiyasuo（压缩）形成完整内循环。

短故事创作引擎。面向知乎/严选调性，第一人称一篇完结。9阶段管线：对标拆解→选题→★人物原型激发→核心梗→角色→大纲→正文→改稿→投稿→终检。融合原型挪移法+叙事三角引擎+节拍索引法。输出写入 wiki/剧本/ wiki/角色/ wiki/世界/ wiki/剧情/。配合 JC-yizhixing 和 JC-jiyiyasuo 形成完整内循环。

知识库记忆压缩官。负责"养库"——三种模式：①整理记忆体：把 .raw/ 对话记录、素材整理进 wiki/。②通用摄入：任何参考资料（小说/论文/电影/文献/网页）→ 原子笔记+概念索引→ wiki/参考/。③小说催化提取：摄入模式专项实例。维护 Obsidian 兼容的 Wiki 架构：补[[双链]]、刷新 hot.md 和 CLAUDE.md、生成关系图.canvas、维护伏笔追踪.base。触发词：整理记忆体、归档raw、摄入资料、拆解小说催化、提取节拍、分析节奏、生成关系图、更新伏笔表等。

输入场景描述（或读取 wiki/场景/*.md）→ Pinterest 搜索真实场景参考图 → 分析图片提取视觉DNA → 融合场景需求生成场景设定图 JSON → 写入 wiki/场景/场景名.design.json。与短剧/小说世界模型共用 Wiki 架构。触发词：场景设计、场景设定图、场景提示词、场景概念图、scene design、画场景、设计场景、空镜设计。

短剧世界模型。基于「世界观+极致角色+催化剂→故事自然涌现」的核心机制。覆盖短剧全流程：人物/场景/道具原型激发（从世界经典库挪移叙事引擎/空间引擎/道具引擎）→ 建制（世界观/爽点设计）→ 正文写作 → 改写优化。输出写入 wiki/剧本/ wiki/角色/ wiki/场景/ wiki/道具/ wiki/世界/ wiki/剧情/，自动更新 CLAUDE.md。配合 JC-yizhixing（巡检）和 JC-jiyiyasuo（压缩）形成完整内循环。

输入道具描述（或读取 wiki/道具/*.md）→ Pinterest 搜索真实道具参考图 → 分析图片提取视觉DNA → 融合道具需求生成道具设定图 JSON → 写入 wiki/道具/道具名.design.json。与短剧/小说世界模型共用 Wiki 架构。触发词：道具设计、道具设定图、道具提示词、道具清单、prop design、画道具、设计道具。

知识库一致性巡检官。对一个用 wiki 架构维护的小说/临摹/剧本知识库做"全库体检"，抓单章自查抓不到的跨章问题——换皮漏改（范本旧名残留）、命名漂移（同一角色前后换了不同新名）、映射撞车（多个角色撞成同一名）、伏笔埋了没收、角色设定前后矛盾、双链断裂、孤儿笔记。当用户说"巡检一下""检查全本一致性""体检知识库""查有没有漏改/穿帮/前后矛盾""扫一下断链和孤儿笔记""伏笔有没有收"，或刚临摹/续写了一批章节想做整体核查时使用。它与 JC-linmoxiaoshuo 的单章自查互补：linmo 管写时单章紧循环，本 skill 管隔几章对整个库做广扫。读 wiki/映射表.md 当事实源，库里有映射表就启用换皮专项检查，没有就做通用角色一致性检查。

将 JC-剧本转分镜的导演阐述 → 转成 GPT Image 2 分镜大图提示词。输出「导演节拍卷轴」——不是规整宫格，是流动的电影叙事长卷：镜头大小按情绪权重变化、箭头串联叙事流向、角色动线贯穿全卷、标注浮在任何位置。触发词：分镜大图、分镜卷轴、故事板大图、分镜生图、storyboard scroll、导演节拍卷轴。

Generates pure SVG code animations using flat design and CSS keyframes. Use when user asks for SVG code, Lottie alternatives, vector illustrations, or web-based motion graphics.

Use when a user wants a family-ethics video turned into a shoot-ready master script, or wants a high-fidelity adaptation of an existing master script for a new relationship, setting, cast, prop, budget, or duration.