2799662352

@2799662352 source repo

98 skills
0 followers
5 hours ago last updated

▌
Vue · 2799662352 bundle
Vue.js progressive JavaScript framework. Use when building Vue components, working with reactivity (ref, reactive, computed, watch), or implementing Vue Composition API patterns.

0
installs
▌
Vite · 2799662352 bundle
Vite next-generation frontend build tool with fast HMR and optimized builds. Use when configuring Vite, adding plugins, working with dev server, or building for production.

0
installs
▌
Antfu · 2799662352 bundle
Anthony Fu's {Opinionated} preferences and best practices for web development

0
installs
▌
Slidev · 2799662352 bundle
Create and present web-based slides for developers using Markdown, Vue components, code highlighting, animations, and interactive features. Use when building technical presentations, conference talks, or teaching materials.

0
installs
▌
Turborepo · 2799662352 bundle
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

0
installs
▌
Vitepress · 2799662352 bundle
VitePress static site generator powered by Vite and Vue. Use when building documentation sites, configuring themes, or writing Markdown with Vue components.

0
installs
▌
Vueuse Functions · 2799662352 bundle
Apply VueUse composables where appropriate to build concise, maintainable Vue.js / Nuxt features.

0
installs
▌
Graphify 2 · 2799662352
Map a folder or codebase into a queryable knowledge graph with the graphify CLI (local tree-sitter AST, zero LLM cost) and answer structure questions from it: 架构 / 依赖关系 / 什么调用了 X / A 和 B 怎么关联 / 这个项目怎么组织 / 知识图谱 / graphify. Trigger when the user points at a project directory and asks about its structure, wants a graph or architecture report of it, or types /graphify or $graphify. Query an existing graphify-out/ first; build one only when missing.

0
installs
▌
Director Narrative Flow · 2799662352
【导演模式·叙事节奏 / Director · Narrative Flow】触发词:叙事 / 镜头顺序 / 节奏 / 180度轴线 / 视线匹配 / 景别交替 / 剪辑流 / shot sequencing / 180-degree rule / eye-line。Use when sequencing shots — open with an establishing wide, follow with mediums for interaction, save close-ups for emotional peaks; enforce the 180-degree rule, eye-line matches, action continuity across cuts, and alternate scales to avoid 3-in-a-row of the same shot type — applies to image-generation models (Midjourney, DALL-E, FLUX, Stable Diffusion, Imagen, Ideogram, Recraft), video-generation models (Sora, Veo, Runway, Kling, Seedance, Hailuo, Higgsfield, Hunyuan), screenplays, scripts, storyboards, AI video, AI image, 提示词, 视频模型, 图像模型, 写剧本, 脚本, 分镜.

0
installs
▌
Director Visual Continuity · 2799662352
【导演模式·连续性 / Director · Continuity】触发词:连续性 / 一致性 / 配色一致 / 色温 / 比例一致 / 穿帮检查 / 地标一致 / continuity / consistency / color temperature / scale drift。Use when verifying that a scene's 2-3 dominant colors stay consistent, color temperature does not mix warm and cool, object-to-character scale holds (table at waist height stays at waist height, ≤20% drift), and architecture / environment landmarks keep their spatial relationships across panels — applies to image-generation models (Midjourney, DALL-E, FLUX, Stable Diffusion, Imagen, Ideogram, Recraft), video-generation models (Sora, Veo, Runway, Kling, Seedance, Hailuo, Higgsfield, Hunyuan), screenplays, scripts, storyboards, AI video, AI image, 提示词, 视频模型, 图像模型, 写剧本, 脚本, 分镜.

0
installs
▌
Director Prompt Engineering · 2799662352
【导演模式·提示词结构 / Director · Prompt Structure】触发词:提示词结构 / 七字段 / 提示词模板 / 怎么写提示词 / 镜头+灯光+构图+风格 / prompt structure / 7-field / prompt template。Use when assembling a prompt in the canonical 7-field order — Subject+Action → Character Ref ([char1] tags) → Scene → Shot+Camera (e.g. 50mm, eye-level) → Lighting (direction, quality, color temperature) → Composition (rule of thirds, DoF) → Style+Mood — within 120 words and paired with negative prompts (blurry, deformed, bad anatomy, extra limbs, watermark) — applies to image-generation models (Midjourney, DALL-E, FLUX, Stable Diffusion, Imagen, Ideogram, Recraft), video-generation models (Sora, Veo, Runway, Kling, Seedance, Hailuo, Higgsfield, Hunyuan), screenplays, scripts, storyboards, AI video, AI image, 提示词, 视频模型, 图像模型, 写剧本, 脚本, 分镜.

0
installs
▌
Director Lighting Continuity · 2799662352
【导演模式·光照连续性 / Director · Lighting Continuity】触发词:打光 / 光源方向 / 色温 / 光影一致 / 布光 / 黄金时刻 / 夜景光 / 霓虹 / lighting / key light / color temperature。Use when locking key light direction (left / right / top / back), quality (hard / soft), and color temperature (golden hour 3000-4000K, overcast 5500-6500K, night blue ambient + warm practicals, neon mixed) across every panel in a scene; flag light-direction reversals and color-temperature jumps without time skip — applies to image-generation models (Midjourney, DALL-E, FLUX, Stable Diffusion, Imagen, Ideogram, Recraft), video-generation models (Sora, Veo, Runway, Kling, Seedance, Hailuo, Higgsfield, Hunyuan), screenplays, scripts, storyboards, AI video, AI image, 提示词, 视频模型, 图像模型, 写剧本, 脚本, 分镜.

0
installs
▌
Director Scene Analysis Depth · 2799662352
【导演模式·场景分析 / Director · Scene Analysis】触发词:场景分析 / 参考图分析 / 环境提取 / 主体清单 / 风格提取 / 看图拆解 / scene analysis / reference breakdown。Use when extracting from a reference image the env field (location + time + atmosphere + weather in one sentence), a subjects array (one entry per visible person/animal/object with spatial relationships), and a style field (art style + color palette + lighting quality + emotional tone), reading time of day from shadow angles and light color — applies to image-generation models (Midjourney, DALL-E, FLUX, Stable Diffusion, Imagen, Ideogram, Recraft), video-generation models (Sora, Veo, Runway, Kling, Seedance, Hailuo, Higgsfield, Hunyuan), screenplays, scripts, storyboards, AI video, AI image, 提示词, 视频模型, 图像模型, 写剧本, 脚本, 分镜.

0
installs
▌
Director Character Consistency · 2799662352
【导演模式·角色一致性 / Director · Character Consistency】触发词:角色一致性 / 同一人物 / 跨镜一致 / 不变脸 / 服装道具不变 / 角色稳定 / character consistency / same character。Use when the same character must appear identical across panels — anchored by face / build / outfit / markers, with hair / outfit / props unchanged across cuts and relative skin-tone descriptors used instead of absolute color — applies to image-generation models (Midjourney, DALL-E, FLUX, Stable Diffusion, Imagen, Ideogram, Recraft), video-generation models (Sora, Veo, Runway, Kling, Seedance, Hailuo, Higgsfield, Hunyuan), screenplays, scripts, storyboards, AI video, AI image, 提示词, 视频模型, 图像模型, 写剧本, 脚本, 分镜.

0
installs
▌
Director Cinematic Composition · 2799662352
【导演模式·构图 / Director · Composition】触发词:构图 / 取景 / 三分法 / 景深 / 前中后景 / 引导线 / 焦段 / 留白 / 机位 / composition / framing / rule of thirds / leading lines / focal length。Use when framing a shot — placing the subject at a rule-of-thirds intersection, building foreground / midground / background layers, deploying leading lines, varying focal length wide → medium → close-up, and tuning negative space / look-space for tension vs calm — applies to image-generation models (Midjourney, DALL-E, FLUX, Stable Diffusion, Imagen, Ideogram, Recraft), video-generation models (Sora, Veo, Runway, Kling, Seedance, Hailuo, Higgsfield, Hunyuan), screenplays, scripts, storyboards, AI video, AI image, 提示词, 视频模型, 图像模型, 写剧本, 脚本, 分镜.

0
installs
▌
Director Structured Captioning · 2799662352
STRUCTURED CAPTIONING — separate global context from per-shot details (HoloCine pattern):

0
installs
▌
Director Shot Sequence Patterns · 2799662352
【导演模式·镜头 / Director · Shots】触发词:镜头 / 景别 / 分镜序列 / 转场 / 建立镜头 / 正反打 / 动作镜头 / 情绪镜头 / shot / shot sequence / cut / dolly / establishing / shot-reverse-shot。Use when picking the shot pattern that matches the scene's dramatic intent — Establishing (wide → medium → close-up → detail), Dialogue (two-shot → shot-reverse-shot → reaction → re-establish), Action (wide → medium action → close-up impact → wide aftermath), Emotional (medium → close-up → extreme close-up → release) — and labeling every transition ("cut to", "dolly in", "match cut", "time skip") — applies to image-generation models (Midjourney, DALL-E, FLUX, Stable Diffusion, Imagen, Ideogram, Recraft), video-generation models (Sora, Veo, Runway, Kling, Seedance, Hailuo, Higgsfield, Hunyuan), screenplays, scripts, storyboards, AI video, AI image, 提示词, 视频模型, 图像模型, 写剧本, 脚本, 分镜.

0
installs
▌
Director Anchor Extraction Quality · 2799662352
【导演模式·角色锚点 / Director · Character Anchors】触发词:角色锚点 / 锚点提取 / 人物设定 / 参考图提取 / 脸型 / 体型 / 服装 / 区分相似角色 / character anchor / reference extraction。Use when extracting character anchors from reference images where every anchor must list face / build / outfit / markers, hit the 40-word minimum, differentiate similar builds explicitly ("A is taller by ~10cm"), and mark occluded parts with [inferred] — applies to image-generation models (Midjourney, DALL-E, FLUX, Stable Diffusion, Imagen, Ideogram, Recraft), video-generation models (Sora, Veo, Runway, Kling, Seedance, Hailuo, Higgsfield, Hunyuan), screenplays, scripts, storyboards, AI video, AI image, 提示词, 视频模型, 图像模型, 写剧本, 脚本, 分镜.

0
installs
▌
Graphify · 2799662352 bundle
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.

0
installs
▌
Storyboard Audio · 2799662352
【分镜模式·音频 / Storyboard · Audio】触发词:配乐 / 音效 / 配音 / BGM / 三层音频 / score / SFX / voice。Use when each shot needs a three-layer audio field (A1 Score / A2 SFX / A3 Voice) described in physical parameters (Hz / bpm / % / RT60) instead of emotion adjectives.

0
installs
▌
Storyboard Dodge · 2799662352
【分镜模式·规避审查 / Storyboard · Dodge】触发词:规避审查 / 过审 / 绕过敏感词 / 力学矢量改写 / safe rewrite。Use when output text risks tripping content filters (explicit anatomy, action verbs, graphic injury, nudity) — rewrite via contour/silhouette, force vectors, shallow-DoF blur, or steam diffusion.

0
installs
▌
Storyboard Style · 2799662352
【分镜模式·风格 / Storyboard · Style】触发词:配色 / 色板分解 / 光源类型 / 阴影占比 / palette / hex。Use when a scene needs a hard palette decomposition (dominant+accent hex ≥ 7:3), typed light source (rim/fill/key) with angle and intensity %, and shadow depth as % of frame.

0
installs
▌
Storyboard Visual · 2799662352
【分镜模式·视觉 / Storyboard · Visual】触发词:物理打光 / 镜头规格 / 焦段光圈 / Z轴前中后景 / lens / Z-axis。Use when a shot needs physical lighting (shadow %), color hierarchy (key+accent hex), explicit lens [mm] f/[stop], and a mandatory Z-axis (fg/mg/bg).

0
installs
▌
Storyboard Physics · 2799662352
【分镜模式·物理 / Storyboard · Physics】触发词:物理描述 / 运动矢量 / 微表情量化 / 写实人体 / motion vector。Use when character body and motion must be described in physics-only language — angle° / displacement cm / velocity m·s⁻¹, micro-expressions in mm — never emotion adjectives.

0
installs
▌
Storyboard Dialogue · 2799662352
【分镜模式·对白 / Storyboard · Dialogue】触发词:对白 / 台词逐字提取 / 角色名 / 不要瞎编台词 / verbatim。Use when a screenplay provides character names and dialogue that MUST be extracted verbatim — never fabricate lines or guess names from visual style.

0
installs
▌
Storyboard Structure · 2799662352
【分镜模式·结构 / Storyboard · Structure】触发词:分镜结构 / 瞬间抓拍 / 峰值张力 / 单一核心动作 / mid-action。Use when shaping each shot as a mid-action snapshot frozen at peak tension, one core action within 2-4s, micro-expressions in mm instead of emotion labels.

0
installs
▌
Sd2 Pe · 2799662352
Seedance 2.0 video prompt engineering base (八大要素, 全能参考绑定). Decide by what the user wants produced. Wants a video (生成视频 / 图生视频 / 让它动起来 / 批量出片): do NOT pick this skill from those words — load the catimation-video entry and follow its tier plan, which names this skill when it is due. Wants a prompt (writing / rewriting / optimizing a Seedance 视频提示词, pasting a draft to improve, 全能参考 binding-syntax questions): load this directly, no entry needed.

0
installs
▌
Sd25 Pe · 2799662352 bundle
Seedance 2.5 prompt optimizer (火山方舟官方 sd25-pe 原文 + 本 app 适配). Decide by what the user wants produced. Wants a video (生成视频 / 出片 / 让它动起来): do NOT pick this skill from those words — load the catimation-video entry and follow its tier plan, which names this skill when it is due. Wants a Seedance 2.5 prompt (writing / rewriting / optimizing a 2.5 提示词, 2.5 的编辑 / 延长 / 关键帧 / 宫格分镜 / 白模 / 多素材主体映射): load this directly. Seedance 2.0 家族的提示词改用 sd2-pe。

0
installs
▌
Narrative Flow · 2799662352
【导演模式·叙事节奏 / Director · Narrative Flow】触发词:叙事 / 镜头顺序 / 节奏 / 180度轴线 / 视线匹配 / 景别交替 / 剪辑流 / shot sequencing / 180-degree rule / eye-line。Use when 一组分镜读起来不连贯、越轴、视线不匹配、节奏平时:建立镜开场 → 中景交互 → 特写留给情绪峰值;守 180 度轴线、视线对位、动作跨格衔接,交替景别避免同景别连排。

0
installs
▌
Deep Agents Core · 2799662352
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.

0
installs
▌
Deep Agents Memory · 2799662352
INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.

0
installs
▌
Audio Score Design · 2799662352 bundle
Use when designing audio, music, sound effects, or voice/dialogue for video storyboards, AI video generation pipelines, film scoring, or any project requiring per-shot synchronized sound design with three layers (score, SFX, voice). Triggers include "audio design", "film score", "sound design", "voice acting", "BGM", "soundtrack", "配乐", "音效", "配音", "声音设计".

0
installs
▌
Cinematic Director · 2799662352
Use when generating cinematic storyboard prompts, designing shot sequences, writing AI-video-ready keyframes, reviewing director system prompts for completeness, or enriching visual descriptions with micro-expressions, color grading, and atmospheric detail.

0
installs
▌
Ffmpeg Win · 2799662352 bundle
Process video/audio locally with the bundled FFmpeg 8.1 CLI (ffmpeg/ffprobe on PATH, zero Docker); ffmpeg-win Docker MCP tool as fallback. Use for transcode, resize, trim, compress, concat, subtitle burn-in, watermark, speed, fade, flip, audio extract/mix/mux, frame extraction, 3x3 contact sheets (九宫格), GIFs, inspection, and the inspect→process→verify loop. Triggers on "用 ffmpeg", 转码/压缩/裁剪/拼接视频, 给视频加字幕/加水印/混音/变速/调音量/淡入淡出/镜像翻转, 提取音频, 抽帧, 九宫格, 审片/质检.

0
installs
▌
Director Style Consistency · 2799662352
【导演模式·风格一致性 / Director · Style Consistency】触发词:风格一致 / 风格统一 / 图文风格冲突 / 材质统一 / 赛璐璐密度 / 颗粒一致 / 写实vs动画 / style consistency / uniform texture。Use when 多格风格漂移、参考图风格与文本模板冲突时:TEXT WINS(参考图只给角色身份,不给渲染介质与调色),统一跨格材质 / 赛璐璐 / 颗粒密度,负向按需补充防漂回。

0
installs
▌
Visual Continuity · 2799662352
【导演模式·连续性 / Director · Continuity】触发词:连续性 / 一致性 / 配色一致 / 色温 / 比例一致 / 穿帮检查 / 地标一致 / continuity / consistency / color temperature / scale drift。Use when 同场景多格配色乱、冷暖混用、物体相对人物比例漂移(桌子从齐腰变齐胸)、地标空间关系穿帮时:锁 2-3 主色、色温只随时段变、比例漂移控制在 20% 内。

0
installs
▌
Film Studio · 2799662352 bundle
带审批门的制片流水线编排器,由 catimation-film 入口卡在确认「这是真正的多镜成片项目」之后加载 —— 不要从触发词直接跳到这里,也不要与入口卡同时加载。Use when 成片项目已经确认:做电影、做短片、拍一部、从剧本到成片、制片、宣传片、微电影、short film、 full production、film pipeline。单镜等非成片请求不触发本技能(那是视频入口快速/标准模式的事,规格同样不降)。

0
installs
▌
Prompt Engineering · 2799662352
【导演模式·提示词结构 / Director · Prompt Structure】触发词:提示词结构 / 七字段 / 提示词模板 / 怎么写提示词 / 镜头+灯光+构图+风格 / prompt structure / 7-field / prompt template。Use when 提示词字段乱序、丢字段导致出图不稳,需要一条规范可复现的成品提示词时:按七字段顺序拼装(主体动作 → 角色引用 → 场景 → 镜头相机 → 光照 → 构图 → 风格情绪),120 词内,负向按需补充。

0
installs
▌
Screenwriter · 2799662352 bundle
编剧 / 剧作 skill,写电影或剧集剧本时使用——开发剧情、分场、写场景、节拍表、对白、改稿、估算片长、删减时长、塑造人物与世界观。基于 McKee《故事》、Campbell《千面英雄》、Aristotle《诗学》三大方法论,产出好莱坞格式剧本,支持双语剧本(对白原文 + 括号内译文),并按因果链与价值流审结构。Screenwriter / screenplay / script skill for feature films or series — plot, scenes, beat sheets, dialogue, revisions, screen-time estimation; Hollywood format, bilingual. 触发词:写剧本、剧本、剧作、编剧、写场景、分场、节拍表、对白、台词、好莱坞格式、片长估算、删减时长、人物小传、世界观、screenplay、script、screenwriter、beat sheet。

0
installs
▌
Director Anime Quality Boost · 2799662352
【导演模式·动画质感 / Director · Anime Look】触发词:动画质感 / 日式动画截图 / 赛璐璐 / cel / 去厚涂 / 油画感 / 二次元 / 番剧风 / anime screenshot / no painterly。Use when 输出跑偏成厚涂 / 油画 / 3D 质感、需要拉回赛璐璐日式动画截图风格,或角色跨格身份(发型 / 服装 / 配饰)需要锁定时;Color Harmony / No-Painterly 为内部参数,成品以 markdown 交付、不输出 JSON。

0
installs
▌
Lighting Continuity · 2799662352
【导演模式·光照连续性 / Director · Lighting Continuity】触发词:打光 / 光源方向 / 色温 / 光影一致 / 布光 / 黄金时刻 / 夜景光 / 霓虹 / lighting / key light / color temperature。Use when 同场景多格光源方向乱、色温跳变、影子方向不一致时:锁定主光方向(左/右/顶/背)、软硬与色温(黄金时刻 3000-4000K、阴天 5500-6500K、夜景蓝环境+暖实用光、霓虹混合),排查无时间跳变的光向反转。

0
installs
▌
Scene Analysis Depth · 2799662352
【导演模式·场景分析 / Director · Scene Analysis】触发词:场景分析 / 参考图分析 / 环境提取 / 主体清单 / 风格提取 / 看图拆解 / scene analysis / reference breakdown。Use when 拿到参考图要做反推 / 复刻的前置拆解时:提取 env 字段(地点+时刻+氛围+天气一句话)、主体清单(逐个可见人物含空间关系)、style 字段(美术+色板+光质+情绪),时刻由阴影角与光色读出。

0
installs
▌
Character Consistency · 2799662352
【导演模式·角色一致性 / Director · Character Consistency】触发词:角色一致性 / 同一人物 / 跨镜一致 / 不变脸 / 服装道具不变 / 角色稳定 / character consistency / same character。Use when 同一角色跨格出现变脸、发型服装道具漂移时:按 Face / Build / Outfit / Markers 锚定,跨格锁定发型 / 服装 / 道具,肤色用相对描述而非绝对色。

0
installs
▌
Cinematic Composition · 2799662352
【导演模式·构图 / Director · Composition】触发词:构图 / 取景 / 三分法 / 景深 / 前中后景 / 引导线 / 焦段 / 留白 / 机位 / composition / framing / rule of thirds / leading lines / focal length。Use when 单格取景构图:主体置三分线交点、前中后景分层、引导线导向焦点、焦段随景别变化、以留白 / look-space 调张弛;画面扁平死居中、视线前无留白时用。

0
installs
▌
Structured Captioning · 2799662352
【导演模式·结构化描述 / Director · Structured Captioning】触发词:结构化描述 / HoloCine / 全局+角色+分镜 / 省token / 角色标签 / [char1] / 锁定外观 / structured caption / token saving。Use when 多格提示词反复重描角色外貌、token 浪费、外观微漂移时:改 HoloCine 结构 GLOBAL → CHARACTER DEFINITIONS → PER-SHOT(只用 [char1] 标签引用,不重描外貌),省约 40% token 并锁定唯一外观。

0
installs
▌
Animation Craft · 2799662352 bundle
アニメ映像(動画)を作る作画工芸スキル——日本アニメ作画の「運動法則層」を担う専門知識モジュール。タメ・ツメ、緩急、メリハリ、間、コマ打ち(1/2/3コマ)、動勢、慣性、フォロースルー、予備動作、残像・効果線、シルエット、質量感、レイアウトを扱い、絵コンテ・アニマティック・キャラ芝居・カット尺・アクションのビート・i2v ショット prompt の作成・推敲・レビューに使う。画風層 (director-anime-quality-boost)が扱わない運動の設計を補う。触发词:アニメ、作画、絵コンテ、タメツメ、コマ打ち、间、动画分镜、动画12原理、运动法则、动作节奏、sakuga、e-konte。UI/フロントエンドのモーションには使わない。

0
installs
▌
Shot Sequence Patterns · 2799662352
【导演模式·镜头 / Director · Shots】触发词:镜头 / 景别 / 分镜序列 / 转场 / 建立镜头 / 正反打 / 动作镜头 / 情绪镜头 / shot / shot sequence / cut / dolly / establishing / shot-reverse-shot。Use when 一场戏需要现成景别套路与转场标注时:按戏剧意图选建立 / 对话 / 动作 / 情绪四种镜头模式,并给转场打标(cut to / dolly in / match cut / time skip)。

0
installs
▌
Wan3 Product Tvc · 2799662352 bundle
创建、优化或批量生成 Wan3.0 可直接粘贴的 30 秒产品 TVC 提示词；支持产品参考图、纯文生视频、影棚实拍、纯 CG、户外生活方式、家居置景、ARRI Alexa 电影写实、反转创意和零 Logo 模式。

0
installs
▌
Deep Agents Orchestration · 2799662352
INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.

0
installs
▌
Wan3 Cinematic 30s · 2799662352 bundle
用“视觉复杂、逻辑简单”的方法生成、改写和诊断可直接粘贴的电影感视频提示词，尤其适用于完整30秒、16:9的文生视频与图生视频、角色参考图改编、高概念成人科幻选集气质、Higgsfield Series式短篇，以及带清晰反转、人物与道具连续性、物理动作、镜头、灯光、同步音效和定制负面约束的提示词。用户提到“30秒提示词”“有反转”“根据这张角色图写视频”“无垫图文生视频”“视觉复杂逻辑简单”“Series感”时使用。

0
installs
▌
Anchor Extraction Quality · 2799662352
【导演模式·角色锚点 / Director · Character Anchors】触发词:角色锚点 / 锚点提取 / 人物设定 / 参考图提取 / 脸型 / 体型 / 服装 / 区分相似角色 / character anchor / reference extraction。Use when 从参考图提取可复现角色锚点:锚点缺 Face/Build/Outfit/Markers 字段、不足 40 词导致出图漂移、相似角色分不清("A 比 B 高约 10cm")、遮挡部位需标 [inferred] 时。

0
installs
▌
Seedance Video Craft · 2799662352 bundle
用 Seedance 2.0 满血版出片的深度实战 skill——由视频入口在**复杂 Seedance 任务** 中加载:多模态参考配比(9图/3视频/3音频)、多镜叙事、视频编辑/延长、复杂动作、口播/广告片、高质量商业交付、爆款体检。基于字节 Seedance 2.0 技术报告 (统一多模态音视频联合生成,4-15s,原生音频+口型,主体控制/运动操控/风格迁移/ 视频延长),给出全能参考配方、模型对齐提示词补充、爆款体检自评(改编自 Higgsfield Virality Predictor)与广告/短视频模式分类。简单单镜生成不触发本技能。

0
installs
▌
Storyboard Prompt Engineering · 2799662352 bundle
Use when optimizing prompts for AI video storyboard pipelines, implementing dodge layers for content filters, adding continuity locks for retry consistency, creating custom PromptSkill modules, or debugging prompt-related quality issues in multi-pass LangGraph pipelines. Triggers include "dodge layer", "filter bypass", "continuity lock", "prompt modular", "storyboard pipeline", "PromptSkill", "分镜提示词".

0
installs
▌
Director Orchestrator · 2799662352 bundle
【导演模式·总调度 / Director · Orchestrator】复杂镜头设计的调度器:由 catimation-image / catimation-video / film-studio 在专业·制片级任务中加载。按 13 维电影摄制框架把镜头写成「物理可复现参数优先于情绪形容词」的结构化文本 (非 JSON)提示词,并按维度路由 director-* / storyboard-* 技法。Use when 任务需要复杂镜头设计、专业构图与光影协同、多维提示词优化、参考图分析复刻, 或多镜连续性设计;简单生成请求不触发本技能。

0
installs
▌
Storyboard Time Words · 2799662352
用于通过时间词让 AI 图像/视频获得情绪、动态和因果痕迹,解决画面像死物、摆拍、蜡像、没有生活气息的问题。适用于过去式、现在进行时、将来时、just finished、after、leftover、mid-leap、billowing、about to、moments before、impending、时间补偿机制、情绪残留、决定性瞬间、势能与悬念。

0
installs
▌
Catimation Audio · 2799662352
FIRST-CHOICE audio / speech generator inside CATIMATION and the ONLY top-level audio entry. Trigger whenever the user asks to 生成音频 / 配音 / 旁白 / 念一段 / 朗读 / 语音 / 音效 / tts / text-to-speech / read this aloud, or wants a voiceover for a scene. Runs the in-app generate_audio tool (火山豆包 seed-audio-1.0); describe the scene in natural language — it does multiple speakers, accents, ambient sound and background music from one prompt.

0
installs
▌
Cinematic Prompt Format · 2799662352 bundle
Model-agnostic 12-item completeness and media-profile leaf for complex video prompt work. Load with whichever prompt base the task's model selects (2.0, 2.5, or 万相 3.0) for path B, multishot, mixed-media, or expanded director / reference work; path A may skip it. Provides format-free content definitions, live-action/2D/3D profiles, language defaults, and checks. No routing or QA.

0
installs
▌
Script Visual Optimizer · 2799662352
短剧单集剧本的可视化优化改写:在不改剧情、人物、台词、胜负与实力设定的前提下, 把文戏补成可拍的神态 / 微表情 / 走位 / 光影 · 空气粒子 · 风态三要素,把武戏补成完整攻防闭环 + 受创反馈 + 环境联动,并为玄幻武打设计与光影粒子融合的特效,输出按时间顺叙、不含镜头术语、可直接配音与交给分镜/出片链路的文字脚本。触发词: 剧本优化 / 改写剧本 / 剧本润色成可拍 / 加武戏 / 武打设计 / 补神态走位 / 短剧脚本。只写新剧本用 screenwriter;要拆镜头表用 shotlist-builder;要直接出视频走 catimation-video。

0
installs
▌
Catimation Canvas · 2799662352
Interactive AI image canvas (tldraw) in the CATIMATION desktop app. Trigger when the user wants to work on the 画布 / canvas, place a generated image there, or iterate on an image by drawing annotations (arrows+notes, circles, boxes). Especially trigger on 打开画布 / 开启自动修图 / 自动修图模式 / 按标注修图 / 在画布上改图 / canvas edit. The canvas AUTO-SUBMITS an edit request when the user finishes annotating (no button); keep watching for and applying those. Uses the canvas_* + generate_image tools.

0
installs
▌
Storyboard Voice Control · 2799662352
用于控制 AI 角色的语气、语速、音色、台词节奏和人物开口真实感。适用于 AI角色配音、人物台词、AI口播、声音公式、语气控制、语速控制、音色控制、多句台词、角色塑造、视频生成带对白。把“愤怒地说/悲伤地讲”改写成年龄感、声线质感、语速、停顿、气息、重音、尾音和标点节奏。

0
installs
▌
Storyboard Scene Breakdown · 2799662352 bundle
用于把爆款视频、参考图、截图或文字描述拆解成可复刻的 AI 视频/图像提示词。适用于“反推提示词”“复刻视频”“画面结构拆解”“逐帧拆解”“时间线”“空间关系”“镜头轨迹”“分镜分析”等场景。不输出标签词堆砌,而是输出时间切片、构图机位、主体动作、光影方向、环境纵深和镜头运动。

0
installs
▌
Catimation Subagents · 2799662352
Look at images and videos WITHOUT burning the main context, and delegate batch work. Trigger when more than one image/frame/board needs looking at, when a contact sheet or reference set must be judged, or when several independent jobs could run side by side (多图分析 / 批量看图 / 分头去做 / 并行 / 委派 / 子代理). Media analysis lands as a `.vision.json` + `.vision.md` sidecar next to the file, so the next session reads text instead of re-opening pixels.

0
installs
▌
Storyboard Character Acting · 2799662352
用于修复 AI 视频角色的“NPC感”“假笑”“摆拍”“面无表情流泪”“用力过猛”等演技问题。把“开心/生气/悲伤”等情绪标签改写成微表情序列、协同肢体小动作和环境声音线索。适用于角色演技、微表情控制、肢体语言、情绪因果、声音视觉化。

0
installs
▌
Storyboard Feature Collapse · 2799662352
用于利用 AI 绘画的特征塌陷机制,主动压缩非主体细节、制造背景语义模糊、边缘衰减、烟雾化/梦境感,并用局部锚点强化情绪。适用于特征塌陷、Feature Collapse、减法美学、情绪肖像、背景 bokeh、soft collapse、fading edges、focus on eyes、极虚极实、Inpainting 局部重绘、梦核/赛博写意。

0
installs
▌
Storyboard Grid To Seedance · 2799662352 bundle
用图像模型生成或使用 3×3/4×4/16 格故事板、镜头总览板、电影美术设定板，并在 Seedance 中把它们设为低约束氛围参考、让文字提示词主导成片时使用。触发场景:一张图出整套分镜、九宫格/多宫格、grid storyboard、富文本美术设定图、把故事板整图或拆格图喂给视频、提示词为主、降低分镜约束并保留导演发挥、舞蹈/动作序列网格、漫画页转视频。

0
installs
▌
Storyboard Negative Control · 2799662352 bundle
用于通过负向提示词和边界限制反向控制 AI 画质,解决默认网红脸、塑料锐化、脏纹理、梦幻=烟雾、高级=金粉、自动补齐背景等误解机制;并含 Seedance 2.0 内容合规审核与正向化改写(9 类敏感检测 + A–G 改写策略)。适用于 negative prompt、--no、禁止词、反向控制、抽象词拆解、视觉公式、缺省词、自动补齐、画质真实感、内容合规、过审、敏感词改写、Midjourney/Stable Diffusion/NanoBananaPro。

0
installs
▌
Catimation Understand · 2799662352
Understand video / documents / and research the web with qwen3.7-plus-dashscope inside CATIMATION. Trigger to 理解/分析视频, 看懂/读文档/PDF, or 上网查/搜一下/扒资料/最新消息. Also the model understand/review stage of the multimedia inspect→verify loop (不只审片): judge content here with understand_video, then hand technical QC + fixes back to the ffmpeg-win skill. 视频理解以 qwen(understand_video)为主、apiyi 为辅; apiyi 的 Gemini(gemini-3.5-flash,禁传 2.5)主要做音频理解(qwen 音频不好)和视频的深度理解。

0
installs
▌
Storyboard Director Thinking · 2799662352
用于建立 AI 视频导演思维,避免只做提示词工具人。适用于空间调度、场面调度、Z轴纵深、动机光源、视差运镜、核心行动、叙事优先、剪辑补拍、A-roll/B-roll、多镜头组合、从一键直出升级为导演控制。

0
installs
▌
Storyboard Emotional Montage · 2799662352
用于用电影蒙太奇表达情绪,解决 AI 视频摆拍感、假哭、商业图库素材感、情绪直白、镜头没有节奏等问题。适用于情绪蒙太奇、客观对应物、库里肖夫效应、环境代替情绪、极静/极动对比、特写放大情绪、手部/眼部微距特写、镜头组合、AI视频导演。

0
installs
▌
Storyboard Pseudo Perspective · 2799662352
用于打破 AI 图像的平面感,通过伪透视词、方向延伸、空气透视、尺度反差、广角/长焦/移轴、明暗切分来制造强纵深和空间张力。适用于伪透视、透视词、消失点、leading lines、converging lines、atmospheric depth、foreground bokeh、worm's-eye view、giant scale、chiaroscuro、Tyndall effect。

0
installs
▌
Storyboard Robustness Breaking · 2799662352
用于让 AI 画面从模板化、安全答案、过度稳定中轻微失稳,获得松弛、自然、不完美、有高级感的可控失控效果。适用于鲁棒性破坏、可控失控感、构图破坏、光线破坏、风格破坏、主体偏移、前景干扰、不均匀光、漏光、风格噪音、减少AI味、时尚大片、胶片风、真实感摄影。

0
installs
▌
Storyboard Character Motivation · 2799662352
用于当人物显得僵硬、站桩、像雕塑、太AI、摆拍时,把“人物在动”改写成“人物因某事自然行动,并产生连续微反应”。侧重行为动机、无意识动作、微弱生命反应、去除AI感的单人物/多人物写法。

0
installs
▌
Storyboard Creative Imagination · 2799662352
用于让 AI 图像/视频不再只追求真实和大片感,通过打破物理定律、让时间失控、把镜头变成角色来制造创意感和想象力。适用于反重力、失重、瀑布倒流、巨物漂浮、时间异常、时空割裂、动作阻断、第一人称物体视角、极端低/高机位、创意视频、脑洞提示词。

0
installs
▌
Storyboard Foreground Occlusion · 2799662352
用于画面平、塑料感、真空感、壁纸感、证件照感、缺纵深时,通过前景遮挡建立机位感、Z轴空间、偷窥感、空气透视和电影感。适用于物理遮挡、氛围遮挡、丁达尔效应、微尘、薄雾、景深、电影构图。

0
installs
▌
Storyboard Light Reconstruction · 2799662352
用于解决 AI 图像/视频的光影混乱、左右光源不听话、大平光、廉价糖水片、塑料高光、图生图残留光影等问题。适用于 AI提示词、光影重构、局部打光、伦勃朗光、冷暖对比、Tapnow、NanoBananaPro/GPT Image 二次控光、去光再加光、后期精准控制。把“侧光/电影光”改写成光源位置、物理效果、阴影结果和重构流程。

0
installs
▌
Catimation Director Stage · 2799662352
Drive the 3D Director Stage (导演台) in the CATIMATION desktop app: place models/mannequins, pose characters, play the ≈2000-clip animation library, author custom pose-keyframe animations (K 动画), set lights/color grading, manage camera slots, and record camera-move videos. Trigger on 导演台 / 3D 摆场景 / 摆个姿势 / 假人 / K 动画 / 运镜 / 打光 / 机位 / 3D 预演 / staging / blocking. Uses the director_* MCP tools (director_open/scene/snapshot/capture/ record/exec).

0
installs
▌
Catimation Video Director Router · 2799662352
【症状修复速查 / Symptom Repair Router】把用户对已生成结果的自然语言"症状" (太假 / AI味 / 塑料 / 像壁纸 / 没电影感 / 动作怪 / 站桩 / 像NPC / 假笑 / 风格跑了 / 光很平 / 糖水 / 混脸)映射到对症的 director-* / storyboard-* 技法技能。Use ONLY when 用户反馈生成结果存在明确问题、要求返工修复,或需要从素材(图/视频/剧本/音频)里诊断质量缺陷;常规生成前的路由由唯一入口 (catimation-image / catimation-video)的分级与症状表负责,不经过本技能。

0
installs
▌
Storyboard Color Grading Control · 2799662352
用于控制 AI 图像/视频的色彩体系、HEX 色卡、电影级调色、色彩DNA、低饱和胶片感、数据驱动调色、色彩一致性、首帧色彩延续。适用于 HEX调色法、电影调色、AI塑料感、风格复刻、DIT参数、色相分布、明暗比例、色温偏移、饱和度映射、A/B验证。把“复古电影感/王家卫/沙丘色调”降维成 HEX、光比、色温、饱和度和负向约束。

0
installs
▌
Storyboard Shot Emotion Matching · 2799662352
用于匹配镜头语言与情绪,解决景别乱用、广角/长焦冲突、远景+浅景深+背景压缩等光学逻辑打架问题。适用于镜头情绪匹配、景别、心理距离、焦段、空间压迫、广角畸变、长焦压缩、50mm真实感、特写情绪高潮、远景渺小感、统一空间逻辑、AI画面从机器生成变成导演创作。

0
installs
▌
Codex Research Grounded Prompting · 2799662352 bundle
Use when writing high-stakes prompts for video or image generation models (e.g. Sora, Midjourney), when designing prompt-engineering systems, or when the user wants outputs grounded in both academic research and creator craft. Triggers on "Sora prompt", "video generation prompt", "视频提示词", "动画 prompt", "怎么写更好的提示词", "prompt 方法论", or tasks demanding rigor — source verification, multi-perspective structure, priority tuning, and verification checklists.

0
installs
▌
Storyboard Live Character Realism · 2799662352
用于赋予 AI 角色“活人感”,去除塑料AI味、油腻感、空洞眼神、精致但无灵魂、假人走秀、图库素材感。适用于 AI绘画、图生视频、人物真实感、微表情控制、环境对抗、物理惯性、局部光源、冷暖对比、哑光皮肤、首帧控质感。把人物从“好看但假”改写成有潜台词、有环境阻力、有局部光影的真实角色。

0
installs
▌
Storyboard Style Extraction Logic · 2799662352
用于从参考图/电影截图中提取可复用的风格逻辑,避免只用 describe/反推提示词做语义拟合。适用于风格即选择、约束点提取、看没什么、样本提纯、风格对照组、共性提取、不可变条件、风格DNA、空间构图/光线氛围/色彩质感/负向约束四维模型。用户提到“风格提取”“风格即选择”“反推提示词”时使用。

0
installs
▌
Catimation Core · 2799662352 bundle
Use when 在 CATIMATION 应用里要生成图片/出图/画一张、管理人像库或素材库、记住某个角色或场景以保持一致性、或需求模糊高价值要先定方向时。Triggers on image / 出图 / 画一张 / 生成图片 / 人像库 / 素材库 / 角色一致性 / brainstorm / 定方向.

0
installs
▌
Catimation Film · 2799662352 bundle
Use when 做一整部片子/短片/宣传片/微电影/MV/剧集/预告片,要把一个想法或故事一条龙做成成片, 或需要写剧本、分镜成片、批量出图出视频再拼接交付时。这是 catimation-film 插件的入口卡, 只做分诊与路由:确认是成片项目后由它加载 film-studio 门控流水线,确认只缺剧本则转 screenwriter。先加载本卡,不要跳过它直接进 film-studio,也不要两个一起加载。阶段技能(配音、剪辑、出图等)也不要预载:进到该阶段时由本卡或流水线点名。 Triggers on film / movie / 短片 / 宣传片 / 预告片 / 剧本 / 成片 / trailer / screenplay.

0
installs
▌
Storyboard Multi Character Control · 2799662352
用于控制 AI 图像/视频中的两个或多个角色,解决多角色动作失控、左右角色互相污染、一个角色动另一个变异、动作稀释、背景板、语义编辑、保留满意角色、分阶段动作接力等问题。适用于多人物动作、空间占位、时间段拆分、语义视频编辑。

0
installs
▌
Catimation Image · 2799662352
FIRST-CHOICE image generator and the ONLY top-level image orchestrator in the CATIMATION desktop app — use INSTEAD OF the built-in imagegen / image_gen tool (unavailable on Windows, no persistence). Trigger whenever the user asks to generate / draw / render / edit / restyle an image, poster, or icon, or says 生成图片 / 画一张 / 配图 / 出图 / 改图 / 图层分离. Runs the in-app generate_image tool and grades every request into 快速/标准/专业/制片 four tiers before loading any other skill.

0
installs
▌
Catimation Video · 2799662352
FIRST-CHOICE video generator and the ONLY top-level video orchestrator in CATIMATION. Trigger whenever the user asks to generate / render a video or animation, animate a still, or says 生成视频 / 图生视频 / 让它动起来 / 视频编辑 / 视频延长 / 视频工作台 / 批量出片 / 多镜. Covers text/still-to-video, omni-reference (全能参考, default), editing and extension on both output surfaces (generate_video one-shot + video_workbench_* batch), and grades every request 快速/标准/专业/制片 before loading other skills.

0
installs
▌
Storyboard Video Prompt Optimization · 2799662352 bundle
用于优化 AI 图生视频/文生视频提示词,解决提示词太长、风格词堆砌、首帧权重被忽视、镜头/光影指令冲突、动作太多导致运动权重稀释、PPT感、动作敷衍等问题。适用于 Seedance 等视频提示词优化、首帧霸权、单一主导逻辑、时间线控制、分镜头脚本、运动算力分配。

0
installs
▌
Catimation Brainstorm · 2799662352
Co-direct open-ended or high-value creative work in CATIMATION via clickable choice cards (the ask_user tool). Trigger when the user is vague/ambitious about a video/image ("做个宣传片" / "来点有电影感的" / "帮我想想" / "随便发挥"), asks to brainstorm / 头脑风暴 / 给我几个方案 / 你来引导, OR asks you to offer choices ("给我几个选项" / "让我选" / "二选一" / "可选" / "options" / "which should I"). Ask ONE focused question at a time with concrete options. Skip for clear simple asks.

0
installs
▌
Storyboard Kinematic Reverse Engineering · 2799662352
用于反推 AI 视频或参考视频的运动学规律,避免只看图说话。适用于视频反推、三帧分析、起始帧/爆发帧/结尾帧、相机运动结构、运动矢量、dolly/zoom/pan/truck/crane 区分、焦距变化、视差、速度、motion weight、把感性描述翻译成动作参数。

0
installs
▌
Trailer Plan Generator · 2799662352 bundle
Generate five professional 90-second trailer plan options from a provided script or story treatment. Use when the user asks in Chinese or English to turn a screenplay, episode outline, short story, animation plot, game story, or promotional script into trailer方案, 90s预告片结构, planA/planB/planC/planD/planF, Hitchcock suspense, Kuleshov effect, MacGuffin, delayed gratification, omitted causality, or Chekhov's gun style trailer planning.

0
installs
▌
Catimation Director · 2799662352 bundle
【导演模式·索引 / Director · Index】catimation-director 插件家族索引卡:按症状挑选 director-* 工艺技法(构图 / 景别与转场 / 打光与色温 / 叙事节奏 / 提示词七字段 / 结构化描述 / 角色锚点与一致性 / 风格与动画质感)。Triggers on director / 导演模式 / 镜头 / 构图 / 打光 / 提示词 / 一致性 / 反推 / 运镜.

0
installs
▌
Shotlist Builder · 2799662352 bundle
Use when a script, treatment, scene list or multi-shot brief has to be planned as a multi-shot VIDEO piece — 剧本拆镜、分场拆镜头、多镜规划、镜头清单、拍摄计划、逐镜视频提示词总表、分镜表、shotlist、shot breakdown — landing as one searchable HTML table with per-shot durations and 4–15s Seedance groupings. 素材要和剧本对上号时(剧本 + 一批图 / 图片文件夹 / 分镜稿)在这条视频路径内一并对表。只做规划与交付物,不定级、不路由、不调生成工具。**纯出图任务不走本 skill**: 只要关键帧/一组角色图而不做成片时,由图片入口直接出,一致性交给角色链与人像库。

0
installs
▌
Catimation Portrait Library · 2799662352
Autonomously manage the CATIMATION portrait library (人像库 / 素材库) — the persistent, deduplicated pool of image / video / audio reference assets that keeps characters & scenes consistent. Use when the user mentions 人像库 / 素材库 / 参考素材 / 角色库, wants to save / 收藏 / 搜索 / 整理 / 重命名 / 分组 / 删除 / 下载 a reference asset, or when a reference asset is needed for 视频生成 / video generation. Add, search, organize, rename, group, hide, download proactively.

0
installs
▌
Create Storyboard · 2799662352 bundle
Create director-grade storyboard production packages for Image 2 and SceneDance/Seedance. Use for scripts, scene/ad/drama/animation/product concepts, 分镜图/剧本分镜/连续性分镜, shot cards, keyframes, continuity/edit-boundary matrices, Seedance assets, and 3×3/4×4 sequence or cinematic art-direction boards with prompt-led atmosphere-reference handling.

0
installs
▌
Catimation Storyboard · 2799662352 bundle
需要按症状挑选分镜技法时使用:反推/复刻爆款、修 AI 感/塑料感/摆拍/假笑、光影混乱、调色、多角色失控、前景遮挡、伪透视、过审改写等,从 catimation-storyboard 插件的 29 个 storyboard-* 工艺技能里挑对的来用。Triggers on storyboard / 分镜 / 提示词 / 反推 / 复刻 / 打光 / 调色 / 演技 / 真实感 / AI感.

0
installs
▌
Catimation Video Workbench · 2799662352
Use when the user is on the CATIMATION 视频工作台 (video workbench) page, or asks to 批量出片 / 排成卡片 / 一次落板 / 铺满工作台 / 跑一批镜头; when a board of shot cards needs reordering, regenerating or version comparison; or when a 剧本 / 分镜表 / shot list / 制片包 should become a board. Load the catimation-video entry together with this one — this is a leaf under that entry, never a replacement for it. Symptoms: 该拆的镜头挤在一张卡里超了时长, 跨卡漂脸漂服装漂风格, 建完卡直接开跑, 拿批次摘要当验片.

0
installs
▌
Catimation Storyboard Pro · 2799662352 bundle
Use when 用户给了剧本/场景创意/广告概念/镜头清单,需要一键产出完整的导演级故事板制作包(逐镜),供 Image 2 与 SceneDance/Seedance 出图出视频时。Triggers on storyboard / 故事板 / 分镜制作包 / 镜头表 / create storyboard / 广告分镜.

0
installs

98 published skills