all publishers

2799662352

@2799662352 source repo

214 published skills · page 1 of 3

  1. ▌
    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.
    8 repo stars
  2. ▌
    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.
    8 repo stars
  3. ▌
    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.
    8 repo stars
  4. ▌
    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.
    8 repo stars
  5. ▌
    Catimation Understand · 2799662352
    Understand video / audio / documents / and research the web with the omni-modal qwen3.8-omni-flash inside CATIMATION. Trigger to 理解/分析视频, 听/转写 音频/录音/音乐, 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 / understand_audio, then hand technical QC + fixes back to the ffmpeg-win skill. 视频/音频/图文理解统一走 qwen(omni)。
    8 repo stars
  6. ▌
    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.
    8 repo stars
  7. ▌
    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 / 深度捕捉. 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.
    8 repo stars
  8. ▌
    Nai5 Comic Storyboard · 2799662352 bundle
    Use when the user wants comic story architecture, page and panel planning, a four-panel narrative, a complete text storyboard, or a targeted story, shot, layout, or continuity revision.
    8 repo stars
  9. ▌
    Nai5 Illustration Composition · 2799662352 bundle
    Use when the user already has an idea or subject and wants an illustration composition, a visual moment, staging, camera, spatial relationships, lighting, or a targeted visual design revision.
    8 repo stars
  10. ▌
    Nai5 Ideas · 2799662352 bundle
    Use when the user wants an overall idea, theme, story seed, premise, relationship concept, or an open imaginative direction.
    8 repo stars
  11. ▌
    Nai5 Writing · 2799662352 bundle
    Use when the user needs general NovelAI prompt syntax, field or preset guidance, wording for a settled ordinary illustration, or an exact edit or correction to existing prompt text.
    8 repo stars
  12. ▌
    Nai5 Scene Design · 2799662352 bundle
    Use when the user wants a scene, place, environment or situational design, an environment-centered visual concept, or a targeted revision to an existing setting.
    8 repo stars
  13. ▌
    Oc Costume Design · 2799662352 bundle
    Use when the user wants an original character outfit, a wardrobe, a clothing design direction, or a visual garment redesign. Converting a settled outfit into prompt text belongs to nai5-writing.
    8 repo stars
  14. ▌
    Nai5 Art Direction · 2799662352 bundle
    Use when the user wants emotional or symbolic visual expression in representational, realistic, or stylized imagery, artistic direction, composition or light-and-color exploration, medium or style exploration, abstract or surreal concepts, or a targeted visual-form revision.
    8 repo stars
  15. ▌
    Nai5 Comic Writing · 2799662352 bundle
    Use when the user wants NovelAI prompt text for a settled comic or four-panel storyboard, asks for ready-to-use comic or four-panel prompts directly without a storyboard review, wants a page or panel export, or wants a targeted correction to existing comic prompt text.
    8 repo stars
  16. ▌
    Nai5 Reverse Prompt · 2799662352 bundle
    Use when the user sends an image and wants a ready-to-use NovelAI V5 prompt reverse-engineered from it, or only one part of it (composition, lighting, colors, outfit, appearance, pose, expression, scene, relationships, or on-image text). Not for merely describing what an image shows.
    8 repo stars
  17. ▌
    Oc Character Design · 2799662352 bundle
    Use when the user wants to create an original character, develop a character core, world relationships, behavior or visual identity, or make a targeted character redesign.
    8 repo stars
  18. ▌
    Nai5 Costume Writing · 2799662352 bundle
    Use when the user wants prompt wording for a settled outfit, a clothing-only fragment, clothing in a complete image prompt, or a targeted correction to clothing prompt text.
    8 repo stars
  19. ▌
    Sd2 Pe 3 · 2799662352
    Optimizes user prompts for Seedance 2.0 multi-modal video generation. Invoke when a user provides an initial prompt or multimedia assets for video generation, or explicitly requests prompt optimization.
    8 repo stars
  20. ▌
    Film Studio 3 · 2799662352 bundle
    端到端「做电影/做片子」的总编排器(制片导演),把一个想法/故事一条龙串成成片时使用——概念 → 剧本 → 分镜镜头表 → 角色与场景设定锚点 → 逐镜出图 → 图生视频(Seedance 2.0)→ 配音配乐 → ffmpeg 拼接 → 爆款体检交付,每个阶段带审批门(gate),并在每一步调用本 app 本地已装的工艺 skill(screenwriter / scene-blueprint / storyboard-* / director-* / animation-craft / seedance-video-craft / ffmpeg-win),而不是把它们重写。End-to-end AI film/animation production orchestrator that chains local craft skills with approval gates. 触发词:做电影、做片子、做短片、拍一部、做一部片、成片、一条龙、端到端、从剧本到成片、制片、总编排、短片项目、宣传片、微电影、make a film、short film、produce a video、full production、film pipeline、concept to delivery。
    8 repo stars
  21. ▌
    Ffmpeg Win 3 · 2799662352 bundle
    Process video/audio through the ffmpeg-win MCP tool (Dockerized FFmpeg 8.1 with automatic Windows-path conversion) instead of a local ffmpeg binary. Use for transcoding, resizing, trimming, speed change, compression, audio extraction, concat, cropping, fades, overlays, thumbnails, GIFs, and inspection — every command is one ffmpeg-win call with an args array plus a drive-root basedir. Triggers on "用 ffmpeg", "处理视频", "转码/压缩/裁剪/拼接视频", "提取音频", "竖屏适配", "加 BGM", "ffmpeg-win", or any CATIMATION 出片 post-processing. References cover filters, codecs, audio, streaming/hwaccel, platform export, and the CATIMATION workflow.
    8 repo stars
  22. ▌
    Screenwriter 3 · 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 writing a feature film or series — plot development, scene breakdowns, beat sheets, dialogue, revisions, screen-time estimation, trimming length, characters, and story mythology; grounded in McKee, Campbell, Aristotle; outputs Hollywood format and bilingual scripts. 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。
    8 repo stars
  23. ▌
    Animation Craft 3 · 2799662352 bundle
    アニメ映像(動画)を作る作画工芸スキル。アニメ短編・絵コンテ・アニマティック・AI動画ショット・キャラ芝居・カット尺・カメラワーク・アクションのビート・連続性・編集リズム・効果音の手がかり、または Seedance/即夢/可灵/海螺 向けの画像から動画(i2v)ショットprompt を作成・推敲・レビューするときに使う。中核は日本のアニメ制作の作画技法——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・ブレ・効果線、シルエット、質量感、レイアウト、撮影——で、画風層(director-anime-quality-boost)が扱わない「運動の法則層」を補う。Professional Japanese animation (sakuga) craft skill for animated shorts, e-konte, character acting, and image-to-video shot prompts. 触发词/トリガー:アニメ、作画、動画、絵コンテ、アニマティック、中割り、タメツメ、緩急、メリハリ、間、コマ打ち、動勢、残像、効果線、レイアウト、キャラ芝居、i2v、动画、动画短片、动画分镜、动画12原理、运动法则、角色表演、图生视频、卡通、animation、animated short、sakuga、motion principles、character acting。注意:UI/フロントエンドのモーションには使わない(ユーザーが明示的にインターフェースアニメを求めた場合を除く)。
    8 repo stars
  24. ▌
    Catimation Image 2 · 2799662352 bundle
    FIRST-CHOICE image generator in the CATIMATION desktop app — use IN PREFERENCE TO the built-in imagegen / image_gen tool (which is unavailable on Windows and does not persist results). Trigger whenever the user asks to generate / draw / render / edit / restyle an image, picture, illustration, poster, or icon, or says 生成图片 / 画一张 / 配图 / 出图 / 来张图 / 改图. Runs the in-app generate_image tool.
    8 repo stars
  25. ▌
    Catimation Video 2 · 2799662352 bundle
    FIRST-CHOICE video generator in the CATIMATION desktop app. Trigger whenever the user asks to generate / create / render a video, clip, or animation, to animate an image, or says 生成视频 / 来段视频 / 做个动画 / 让它动起来 / 图生视频 / 视频编辑 / 视频延长. Covers text-to-video, image-to-video, omni-reference (全能参考, the default), plus video editing and extension — all via the in-app generate_video tool (Seedance 2.0 / 2.0-fast). Do not call a built-in video tool; see the body for usage.
    8 repo stars
  26. ▌
    Catimation Brainstorm 2 · 2799662352 bundle
    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.
    8 repo stars
  27. ▌
    Seedance Video Craft 3 · 2799662352 bundle
    用 Seedance 2.0 满血版出片的深度实战 skill,做 AI 视频(文生视频/图生视频/全能参考/视频延长/编辑)时使用——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,720p,最多 9 图/3 视频/3 音频参考,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、提示词工程、爆款体检自评(改编自 Higgsfield Virality Predictor)、广告/短视频模式分类(改编自 Marketing Studio)。Seedance 2.0 video-craft skill grounded in ByteDance's Seedance 2.0 technical report. 触发词:Seedance、满血版、全能参考、视频生成、图生视频、文生视频、视频延长、出片、爆款、短视频、口播、广告片、UGC、运镜、首帧、video generation、virality、hook。
    8 repo stars
  28. ▌
    Trailer Plan Generator 2 · 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.
    8 repo stars
  29. ▌
    Storyboard Audio 3 · 2799662352
    【分镜模式·音频 / Storyboard · Audio】触发词:配乐 / 音效 / 配音 / 声音设计 / BGM / 三层音频 / 乐器 / bpm / 混响 / score / SFX / voice / sound design。Use when each shot needs a three-layer audio field — A1 Score (ref:Composer/Work + 乐器 + 力度 pp-ff + 速度 bpm + 张力值 0-10, derived via score_bpm = motion_freq × 60), A2 SFX (材质 + 动作 + 频率Hz + 衰减s + 空间定位), A3 Voice (基频Hz + 气声比% + 语速字/秒 + 混响 RT60) — banning emotion adjectives in favor of physical parameters (配乐 / 音效 / 配音) — 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.
    8 repo stars
  30. ▌
    Storyboard Dodge 3 · 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 / 暴力裸露改写 / 轮廓化 / 力学矢量改写 / content filter / dodge / safe rewrite。Use when output text risks tripping content filters with explicit anatomical terms, action verbs (thrust/penetrate), graphic injury, or nudity — rewrite via contour/silhouette, force vectors (impact 200N, compression 3cm), pressure / velocity / amplitude, fabric silhouette, shallow DoF blur, or steam diffusion (规避审查) — 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.
    8 repo stars
  31. ▌
    Storyboard Style 3 · 2799662352
    【分镜模式·风格 / Storyboard · Style】触发词:风格 / 配色 / 色板 / 色彩 / 光源 / 阴影 / 色调 / 美术风格 / palette / hex / lighting / shadow。Use when a scene needs a hard palette decomposition — dominant [hex] + accent [hex] in ratio ≥ 7:3, light source typed as rim / fill / key with angle and intensity %, and shadow depth expressed as percentage of frame in shadow (配色 / 光源 / 阴影) — 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.
    8 repo stars
  32. ▌
    Storyboard Visual 3 · 2799662352
    【分镜模式·视觉 / Storyboard · Visual】触发词:视觉 / 打光 / 色彩层次 / 镜头规格 / 焦段光圈 / Z轴 / 前中后景 / 阴影占比 / lighting / color / lens / Z-axis / shadow。Use when a shot needs physical lighting (shadow 10-40% day / 60-90% night, rim / candle / natural / fill), color hierarchy ([key hex] dominant + faint [accent hex], never equal warm + cool), explicit lens spec [mm] f/[stop] instead of "8k masterpiece", and a mandatory Z-axis (fg occluder / mg subject / bg environment) — 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.
    8 repo stars
  33. ▌
    Storyboard Physics 3 · 2799662352
    【分镜模式·物理 / Storyboard · Physics】触发词:物理 / 人体 / 肌肉 / 骨骼 / 动作 / 运动矢量 / 微表情 / 量化 / 写实 / body physics / motion vector / micro-expression。Use when character body / motion must be described in physical-only language — skin texture, muscle tension, bone structure; motion vectors as angle° / displacement cm / velocity m·s⁻¹; micro-expressions in mm (brow furrowed Xmm, pupil dilation Xmm), never emotion adjectives — 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.
    8 repo stars
  34. ▌
    Director Orchestrator 3 · 2799662352 bundle
    【导演模式·总调度 / Director · Orchestrator·每次必用】导演总调度路由器:像 using-superpowers 那样把全部 director-*(镜头/构图/连续性)与 storyboard-*(物理/对白/风格)技法技能串成一条流水线——先反问要用哪些本地 skill,再按 13 维电影摄制框架以"物理可复现参数优先于情绪形容词"输出结构化文本(非 JSON)提示词,并交给 catimation-image / catimation-video 出片。MUST be loaded EVERY time a task touches an image/video/animation prompt — 任何关于视频、图片、提示词的问题或生成任务,以及你自发为回答配图/配视频之前,都必须先载入并执行本技能,不可凭感觉直接写提示词。Use when 写/优化提示词、生成图片/视频/动画、画一张、出图、来段视频、做个动画、让它动起来、分镜、镜头、运镜、构图、打光、调色、角色一致性、参考图分析/复刻/反推。Triggers on prompt / image / video / animation / shot / storyboard / cinematography / 提示词 / 图片 / 视频 / 出图 / 配图. Loads before writing any prompt or generating any image/video.
    8 repo stars
  35. ▌
    Storyboard Dialogue 3 · 2799662352
    【分镜模式·对白 / Storyboard · Dialogue】触发词:对白 / 台词 / 字幕 / 角色名 / 逐字 / 原文提取 / 不要瞎编台词 / dialogue / lines / verbatim / character names。Use when screenplay or script provides character names and dialogue that MUST be extracted verbatim — never fabricate lines, never guess names from visual style (台词 verbatim) — 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.
    8 repo stars
  36. ▌
    Storyboard Structure 3 · 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 / 不要"然后" / 微表情量化 / mid-action / one core action / peak tension。Use when shaping each shot as a mid-action snapshot frozen at peak tension (never "then / after"), holding to ONE core action within 2-4 seconds, and quantifying micro-expressions in millimeters (brow furrowed Xmm, pupil dilation Xmm) instead of emotion labels — 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.
    8 repo stars
  37. ▌
    Catimation Portrait Library 2 · 2799662352 bundle
    Autonomously manage the CATIMATION portrait library (人像库 / 素材库) — the persistent, deduplicated pool of image / video / audio assets that powers video generation and keeps characters & scenes consistent. Use whenever 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 whenever you need an asset for 视频生成 / video generation. Add, search, organize, rename, group, hide, download proactively.
    8 repo stars
  38. ▌
    Storyboard Time Words 3 · 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。
    8 repo stars
  39. ▌
    Director Style Consistency 3 · 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 resolving image-vs-text style conflict (TEXT WINS — reference image supplies only character identity, never rendering medium or color grading), enforcing uniform texture / cel-shading / film-grain density across panels, and reinforcing negative prompts (photoreal target → ban anime/cartoon; anime target → ban photoreal) — 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.
    8 repo stars
  40. ▌
    Storyboard Voice Control 3 · 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。
    8 repo stars
  41. ▌
    Director Anime Quality Boost 3 · 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 output drifts toward painterly / 厚涂 / oil-painterly texture instead of cel-shaded anime screenshot style, character identity must lock across panels (hair / outfit / accessories), or injecting JSON instruction blocks with Color Harmony 1.5 and No-Painterly 1.8 weights (日式动画截图) — 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.
    8 repo stars
  42. ▌
    Storyboard Scene Breakdown 3 · 2799662352
    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”“Seedance/Sora/Kling/Runway 提示词”等场景。不要生成标签词堆砌,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。
    8 repo stars
  43. ▌
    Storyboard Character Acting 3 · 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。适用于 Sora/Kling/Runway/Seedance/Hailuo 视频提示词、角色演技、微表情控制、肢体语言、情绪因果、环境音效、声音视觉化、AI导演思维。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。
    8 repo stars
  44. ▌
    Storyboard Feature Collapse 3 · 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。
    8 repo stars
  45. ▌
    Storyboard Negative Control 3 · 2799662352
    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。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、Midjourney/Stable Diffusion/NanoBananaPro。
    8 repo stars
  46. ▌
    Storyboard Director Thinking 3 · 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 Seedance/可灵/海螺/NanoBananaPro 的空间调度、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。
    8 repo stars
  47. ▌
    Storyboard Emotional Montage 3 · 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。
    8 repo stars
  48. ▌
    Codex Research Grounded Prompting 3 · 2799662352 bundle
    Use when writing high-stakes prompts for video or image generation models (Sora, Midjourney, Kling, Veo, Stable Diffusion), when designing prompt-engineering systems, or when the user wants outputs grounded in both academic research and creator craft. Triggers on phrases such as "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 any task that demands rigor — source verification, multi-perspective structure, weight tuning, priority hierarchy, persuasion-over-accuracy, granularity alignment, or verification checklists.
    8 repo stars
  49. ▌
    Storyboard Pseudo Perspective 3 · 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。
    8 repo stars
  50. ▌
    Storyboard Robustness Breaking 3 · 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。
    8 repo stars
  51. ▌
    Storyboard Character Motivation 3 · 2799662352
    用于让 AI 视频/图像提示词里的人物更像真人而不是摆拍。适用于 Sora/Kling/Runway/Seedance/Hailuo 等视频提示词、单人物/多人物视频提示词、人物真实感、行为动机、无意识动作、微弱生命反应、去除AI感,或当生成的人物显得僵硬、站桩、像雕塑、太AI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”。
    8 repo stars
  52. ▌
    Storyboard Creative Imagination 3 · 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。
    8 repo stars
  53. ▌
    Storyboard Foreground Occlusion 3 · 2799662352
    用于通过前景遮挡去除 AI 画面的塑料感、真空感、壁纸感、证件照感,建立机位感、Z轴空间、偷窥感、空气透视和电影感。适用于 AI生图、图生视频、Midjourney、NanoBananaPro、Kling、Hailuo、Seedance、前景遮挡、物理遮挡、氛围遮挡、丁达尔效应、微尘、薄雾、景深、电影构图。
    8 repo stars
  54. ▌
    Storyboard Light Reconstruction 3 · 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。
    8 repo stars
  55. ▌
    Storyboard Color Grading Control 3 · 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。
    8 repo stars
  56. ▌
    Storyboard Shot Emotion Matching 3 · 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。
    8 repo stars
  57. ▌
    Storyboard Live Character Realism 3 · 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。
    8 repo stars
  58. ▌
    Storyboard Style Extraction Logic 3 · 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。
    8 repo stars
  59. ▌
    Storyboard Multi Character Control 3 · 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 AI视频多角色、可灵/即梦/海螺/NanoBananaPro/Midjourney、多人物动作、空间占位、时间段拆分、语义视频编辑。
    8 repo stars
  60. ▌
    Storyboard Video Prompt Optimization 3 · 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/Kling/Hailuo/Sora/Runway 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。
    8 repo stars
  61. ▌
    Storyboard Kinematic Reverse Engineering 3 · 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。
    8 repo stars
  62. ▌
    Vue 2 · 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.
    8 repo stars
  63. ▌
    Vite 2 · 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.
    8 repo stars
  64. ▌
    Antfu 2 · 2799662352 bundle
    Anthony Fu's {Opinionated} preferences and best practices for web development
    8 repo stars
  65. ▌
    Slidev 2 · 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.
    8 repo stars
  66. ▌
    Turborepo 2 · 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.
    8 repo stars
  67. ▌
    Vitepress 2 · 2799662352 bundle
    VitePress static site generator powered by Vite and Vue. Use when building documentation sites, configuring themes, or writing Markdown with Vue components.
    8 repo stars
  68. ▌
    Vueuse Functions 2 · 2799662352 bundle
    Apply VueUse composables where appropriate to build concise, maintainable Vue.js / Nuxt features.
    8 repo stars
  69. ▌
    Sd2 Pe 2 · 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.
    8 repo stars
  70. ▌
    Sd25 Pe 2 · 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。
    8 repo stars
  71. ▌
    Film Studio 2 · 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)。
    8 repo stars
  72. ▌
    Ffmpeg Win 2 · 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.
    8 repo stars
  73. ▌
    Screenwriter 2 · 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。
    8 repo stars
  74. ▌
    Animation Craft 2 · 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。
    8 repo stars
  75. ▌
    Wan3 Product Tvc 2 · 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。
    8 repo stars
  76. ▌
    Wan3 Cinematic 30s 2 · 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。
    8 repo stars
  77. ▌
    Seedance Video Craft 2 · 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。
    8 repo stars
  78. ▌
    Storyboard Audio 2 · 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.
    8 repo stars
  79. ▌
    Storyboard Dodge 2 · 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.
    8 repo stars
  80. ▌
    Storyboard Style 2 · 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.
    8 repo stars
  81. ▌
    Script Visual Optimizer 2 · 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。
    8 repo stars
  82. ▌
    Storyboard Visual 2 · 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).
    8 repo stars
  83. ▌
    Storyboard Physics 2 · 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.
    8 repo stars
  84. ▌
    Cinematic Prompt Format 2 · 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.
    8 repo stars
  85. ▌
    Director Orchestrator 2 · 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。
    8 repo stars
  86. ▌
    Storyboard Dialogue 2 · 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.
    8 repo stars
  87. ▌
    Storyboard Structure 2 · 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.
    8 repo stars
  88. ▌
    Director Narrative Flow 2 · 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。
    8 repo stars
  89. ▌
    Storyboard Time Words 2 · 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。
    8 repo stars
  90. ▌
    Director Style Consistency 2 · 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。
    8 repo stars
  91. ▌
    Director Visual Continuity 2 · 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。
    8 repo stars
  92. ▌
    Storyboard Voice Control 2 · 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。
    8 repo stars
  93. ▌
    Director Prompt Engineering 2 · 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。
    8 repo stars
  94. ▌
    Director Anime Quality Boost 2 · 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。
    8 repo stars
  95. ▌
    Director Lighting Continuity 2 · 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。
    8 repo stars
  96. ▌
    Storyboard Scene Breakdown 2 · 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。
    8 repo stars
  97. ▌
    Director Scene Analysis Depth 2 · 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。
    8 repo stars
  98. ▌
    Storyboard Character Acting 2 · 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。
    8 repo stars
  99. ▌
    Storyboard Feature Collapse 2 · 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。
    8 repo stars
  100. ▌
    Storyboard Grid To Seedance 2 · 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。
    8 repo stars