$npx -y skills add MagicCube/agentara --skill video-character-designCreate character design documentation and character design sheet images for video, storyboard, advertising, animation, or AI video-generation workflows. Use this skill whenever the user asks to design a character, extract a character from a reference image, make a character sheet
| 1 | # Video Character Design |
| 2 | |
| 3 | Use this skill to create a reusable character asset package for video planning, storyboard generation, and image-to-video generation. |
| 4 | |
| 5 | The package has two files: |
| 6 | |
| 7 | 1. `{character-name}.md` — the character design specification. |
| 8 | 2. `{character-name}.png` — the character design sheet image generated only after the user confirms the `.md`. |
| 9 | |
| 10 | The user-facing `.md` may be written in the user's preferred local language unless they request English. Keep file names simple, lowercase, and filesystem-safe. |
| 11 | |
| 12 | ## Core Rule: Spec First, Image Second |
| 13 | |
| 14 | Always create the `.md` design spec first. |
| 15 | |
| 16 | Do not generate the `.png` in the same step unless the user has already explicitly approved an existing character spec or says to proceed without confirmation. |
| 17 | |
| 18 | Default sequence: |
| 19 | |
| 20 | 1. Extract or design the character. |
| 21 | 2. Save `{character-name}.md`. |
| 22 | 3. Ask the user to confirm or revise the design. |
| 23 | 4. After approval, generate `{character-name}.png`. |
| 24 | 5. Save the generated image beside the `.md`. |
| 25 | |
| 26 | This confirmation step matters because character images are expensive to iterate after the identity, wardrobe, and sheet layout are wrong. |
| 27 | |
| 28 | ## Output Location |
| 29 | |
| 30 | Use a project-local character directory when one exists. If no convention exists, create: |
| 31 | |
| 32 | ```text |
| 33 | characters/ |
| 34 | ``` |
| 35 | |
| 36 | Save outputs as: |
| 37 | |
| 38 | ```text |
| 39 | characters/{character-name}.md |
| 40 | characters/{character-name}.png |
| 41 | ``` |
| 42 | |
| 43 | If the user explicitly requests another directory, use that directory. |
| 44 | |
| 45 | Examples: |
| 46 | |
| 47 | - `characters/campus-girl.md` |
| 48 | - `characters/campus-girl.png` |
| 49 | - `characters/travel-boyfriend.md` |
| 50 | - `characters/blue-team-runner.png` |
| 51 | |
| 52 | Do not overwrite existing files unless the user requested replacement. For alternatives, use suffixes such as `-v2`, `-summer-uniform`, or `-hero-look`. |
| 53 | |
| 54 | ## Input Modes |
| 55 | |
| 56 | Support two input modes. |
| 57 | |
| 58 | ### Mode A: Extract From Reference |
| 59 | |
| 60 | Use this when the user points to an image, storyboard, video still, uploaded reference, or existing generated asset. |
| 61 | |
| 62 | Extract observable traits: |
| 63 | |
| 64 | - Apparent age range and casting type. |
| 65 | - Face shape, hairstyle, skin tone, expression, and distinguishing features. |
| 66 | - Body proportions and posture. |
| 67 | - Wardrobe, shoes, accessories, bag, jewelry, props. |
| 68 | - Color palette and materials. |
| 69 | - Clothing material details: weave, knit, sheen, thickness, drape, seams, cuffs, stitching, wrinkles, weathering, and how the fabric reacts to studio light. |
| 70 | - Scene context, lighting, and camera feel. |
| 71 | |
| 72 | Be honest about uncertainty. If a detail is unclear, mark it as an assumption instead of inventing a precise fact. |
| 73 | |
| 74 | ### Mode B: Design From Scratch |
| 75 | |
| 76 | Use this when the user describes a character without a reference image. |
| 77 | |
| 78 | Ask only for missing details that materially change the character: |
| 79 | |
| 80 | - Character role in the video. |
| 81 | - Age range or life stage. |
| 82 | - Gender presentation if relevant. |
| 83 | - Setting and genre. |
| 84 | - Wardrobe direction. |
| 85 | - Visual tone: realistic, commercial, documentary, stylized, animation, etc. |
| 86 | |
| 87 | If the user wants speed, make reasonable assumptions and list them in the `.md`. |
| 88 | |
| 89 | ## Character Name |
| 90 | |
| 91 | Derive a concise slug from the role when the user does not provide a name. |
| 92 | |
| 93 | Rules: |
| 94 | |
| 95 | - Lowercase. |
| 96 | - Use hyphens. |
| 97 | - ASCII only. |
| 98 | - Avoid spaces and punctuation. |
| 99 | - Keep it stable across revisions. |
| 100 | |
| 101 | Examples: |
| 102 | |
| 103 | - "校园广告里的女生" -> `campus-girl` |
| 104 | - "男主,旅行情侣里的男生" -> `travel-boyfriend` |
| 105 | - "basketball team captain" -> `basketball-captain` |
| 106 | |
| 107 | ## `{character-name}.md` Template |
| 108 | |
| 109 | Use this structure for the design spec. Translate headings if the user prefers another language. |
| 110 | |
| 111 | ```markdown |
| 112 | # [Character Display Name] |
| 113 | |
| 114 | ## Source |
| 115 | |
| 116 | - Input mode: [Extracted from reference / Designed from scratch] |
| 117 | - Reference file(s): [paths or "none"] |
| 118 | - Project context: [video/storyboard/ad/scene] |
| 119 | |
| 120 | ## Design Intent |
| 121 | |
| 122 | [One short paragraph explaining the character's role, personality, and visual function in the video.] |
| 123 | |
| 124 | ## Identity & Casting |
| 125 | |
| 126 | - Apparent age: |
| 127 | - Gender presentation: |
| 128 | - Ethnicity / cultural context: |
| 129 | - Build and height impression: |
| 130 | - Posture and movement quality: |
| 131 | |
| 132 | ## Face & Hair |
| 133 | |
| 134 | - Face shape: |
| 135 | - Skin tone and texture: |
| 136 | - Eyes: |
| 137 | - Brows: |
| 138 | - Nose: |
| 139 | - Mouth: |
| 140 | - Hairstyle: |
| 141 | - Distinguishing details: |
| 142 | |
| 143 | ## Wardrobe |
| 144 | |
| 145 | - Top: |
| 146 | - Bottom: |
| 147 | - Shoes: |
| 148 | - Socks: |
| 149 | - Outerwear: |
| 150 | - Accessories: |
| 151 | - Bag / carried items: |
| 152 | - Color palette: |
| 153 | - Fabric and fit: |
| 154 | - Clothing material details: |
| 155 | |
| 156 | ## Props |
| 157 | |
| 158 | - Primary props: |
| 159 | - Secondary props: |
| 160 | - Prop consistency rules: |
| 161 | |
| 162 | ## Character Sheet Layout |
| 163 | |
| 164 | - Canvas: 16:9 |
| 165 | - Background: photography studio gray, |