{
  "schemaVersion": "1.0",
  "item": {
    "slug": "character-design-sheet",
    "name": "Character Design Sheet",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/okaris/character-design-sheet",
    "canonicalUrl": "https://clawhub.ai/okaris/character-design-sheet",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/character-design-sheet",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=character-design-sheet",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/character-design-sheet"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/character-design-sheet",
    "agentPageUrl": "https://openagent3.xyz/skills/character-design-sheet/agent",
    "manifestUrl": "https://openagent3.xyz/skills/character-design-sheet/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/character-design-sheet/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Character Design Sheet",
        "body": "Create consistent characters across multiple AI-generated images via inference.sh CLI."
      },
      {
        "title": "Quick Start",
        "body": "curl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Generate a character concept\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character design reference sheet, front view of a young woman with short red hair, green eyes, wearing a blue jacket and white t-shirt, full body, white background, clean lines, concept art style, character turnaround\",\n  \"width\": 1024,\n  \"height\": 1024\n}'\n\nInstall note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available."
      },
      {
        "title": "The Consistency Problem",
        "body": "AI image generation produces different-looking characters every time, even with the same prompt. This is the #1 challenge in AI art for any project requiring the same character across multiple images."
      },
      {
        "title": "Solutions (Ranked by Effectiveness)",
        "body": "TechniqueConsistencyEffortBest ForFLUX LoRA (trained on character)Very highHigh (requires training data)Ongoing projects, many imagesDetailed description anchorMedium-highLowQuick projects, few imagesSame seed + similar promptMediumLowVariations of single poseImage-to-image refinementMediumMediumRefining existing imagesReference image in promptVariesLowWhen model supports it"
      },
      {
        "title": "1. Turnaround Sheet",
        "body": "Shows the character from multiple angles:\n\n┌────────┬────────┬────────┬────────┐\n│        │        │        │        │\n│ FRONT  │  3/4   │  SIDE  │  BACK  │\n│  VIEW  │  VIEW  │  VIEW  │  VIEW  │\n│        │        │        │        │\n└────────┴────────┴────────┴────────┘\n\n# Generate front view\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character design, front view, young woman with short asymmetric red hair, bright green eyes, wearing navy blue bomber jacket over white graphic tee, dark jeans, red sneakers, standing in neutral pose, full body, clean white background, concept art, sharp details\",\n  \"width\": 768,\n  \"height\": 1024\n}' --no-wait\n\n# Generate 3/4 view (same description)\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character design, three-quarter view, young woman with short asymmetric red hair, bright green eyes, wearing navy blue bomber jacket over white graphic tee, dark jeans, red sneakers, standing, full body, clean white background, concept art, sharp details\",\n  \"width\": 768,\n  \"height\": 1024\n}' --no-wait\n\n# Generate side view\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character design, side profile view, young woman with short asymmetric red hair, bright green eyes, wearing navy blue bomber jacket over white graphic tee, dark jeans, red sneakers, standing, full body, clean white background, concept art, sharp details\",\n  \"width\": 768,\n  \"height\": 1024\n}' --no-wait\n\n# Generate back view\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character design, back view, young woman with short asymmetric red hair, wearing navy blue bomber jacket over white graphic tee, dark jeans, red sneakers, standing, full body, clean white background, concept art, sharp details\",\n  \"width\": 768,\n  \"height\": 1024\n}' --no-wait\n\n# Stitch into reference sheet\ninfsh app run infsh/stitch-images --input '{\n  \"images\": [\"front.png\", \"three-quarter.png\", \"side.png\", \"back.png\"],\n  \"direction\": \"horizontal\"\n}'"
      },
      {
        "title": "2. Expression Sheet",
        "body": "Shows the character's face with different emotions:\n\n┌────────┬────────┬────────┐\n│NEUTRAL │ HAPPY  │ ANGRY  │\n│        │        │        │\n├────────┼────────┼────────┤\n│  SAD   │SURPRISE│THINKING│\n│        │        │        │\n└────────┴────────┴────────┘\n\nMinimum 6 expressions: neutral, happy, angry, sad, surprised, thinking.\n\n# Neutral\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character portrait, close-up face, young woman with short red hair and green eyes, neutral calm expression, clean white background, concept art, consistent character design\",\n  \"width\": 512,\n  \"height\": 512\n}' --no-wait\n\n# Happy\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character portrait, close-up face, young woman with short red hair and green eyes, warm genuine smile, happy expression, clean white background, concept art, consistent character design\",\n  \"width\": 512,\n  \"height\": 512\n}' --no-wait\n\n# Angry\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character portrait, close-up face, young woman with short red hair and green eyes, furrowed brows, angry determined expression, clean white background, concept art, consistent character design\",\n  \"width\": 512,\n  \"height\": 512\n}' --no-wait\n\n# (Continue for sad, surprised, thinking...)"
      },
      {
        "title": "3. Outfit/Costume Sheet",
        "body": "Multiple outfits for the same character:\n\nOutfitDescriptionCasualBomber jacket, t-shirt, jeansWorkBlazer, button-down, slacksAthleticSports bra, leggings, running shoesFormalEvening dress, heels"
      },
      {
        "title": "4. Color Palette Sheet",
        "body": "Document exact colors for consistency:\n\nCHARACTER: Maya Chen\n\nSkin:    ████ #F5D0A9 (warm beige)\nHair:    ████ #C0392B (auburn red)\nEyes:    ████ #27AE60 (emerald green)\nJacket:  ████ #2C3E50 (navy blue)\nT-shirt: ████ #ECF0F1 (off-white)\nJeans:   ████ #34495E (dark slate)\nShoes:   ████ #E74C3C (bright red)"
      },
      {
        "title": "The Description Anchor Technique",
        "body": "The most practical consistency technique: write a 50+ word detailed description and reuse it exactly in every prompt."
      },
      {
        "title": "Template",
        "body": "[age] [gender] with [hair: color, length, style], [eye color] eyes,\n[skin tone], [facial features: any distinctive marks],\nwearing [top: specific color and style], [bottom: specific color and style],\n[shoes: specific color and style], [accessories: specific items]"
      },
      {
        "title": "Example",
        "body": "young woman in her mid-twenties with short asymmetric auburn red hair\nswept to the right side, bright emerald green eyes, light warm skin\nwith a small beauty mark below her left eye, wearing a fitted navy\nblue bomber jacket with silver zipper over a white crew-neck t-shirt,\ndark slate slim jeans, and bright red canvas sneakers, small silver\nstud earrings\n\nUse this exact block in EVERY prompt for this character, only changing the action/pose/scene."
      },
      {
        "title": "Proportion Guide",
        "body": "StyleHead-to-Body RatioBest ForRealistic7.5 : 1Film, photorealisticHeroic8 : 1Superheroes, actionAnime/Manga5-6 : 1Japanese animation styleStylized4-5 : 1Western animationChibi/Super-deformed2-3 : 1Cute, comedic, mascots\n\nInclude proportion style in your prompts: \"realistic proportions\" vs \"anime style proportions\" vs \"chibi proportions\""
      },
      {
        "title": "Using LoRA for Consistency",
        "body": "For projects requiring many images of the same character, train a LoRA:\n\n# Use FLUX with a character LoRA\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"maya_chen character, sitting at a cafe reading a book, warm afternoon light, candid photography style\",\n  \"loras\": [{\"path\": \"path/to/maya-chen-lora.safetensors\", \"scale\": 0.8}]\n}'\n\nLoRA Training Tips:\n\nNeed 10-20 reference images of the character (consistent style)\nTrain on specific trigger word (e.g., \"maya_chen\")\nScale 0.7-0.9 balances consistency with prompt flexibility\nLower scale = more creative freedom, higher = more strict matching"
      },
      {
        "title": "Common Consistency Failures",
        "body": "IssueWhy It HappensMitigationHair color driftModel interprets \"red hair\" differently each timeUse specific shade: \"auburn red #C0392B\"Eye color changeLow priority in generationMention eye color early in promptOutfit inconsistencyModel fills in details creativelyDescribe every clothing item explicitlyAge shiftVague age descriptionUse \"mid-twenties\" not \"young\"Face structure changeDifferent generations = different facesUse LoRA or same seed baseProportion shiftStyle interpretation variesSpecify \"7.5 head proportions\""
      },
      {
        "title": "Character Bible Template",
        "body": "For ongoing projects, maintain a character bible document:\n\n# Character: Maya Chen\n\n## Visual Description (use in all prompts)\nyoung woman in her mid-twenties with short asymmetric auburn red hair...\n[full 50+ word anchor description]\n\n## Color Palette\n- Skin: #F5D0A9\n- Hair: #C0392B\n- Eyes: #27AE60\n- Primary outfit: Navy #2C3E50\n- Accent: Red #E74C3C\n\n## Personality Notes (for expression/pose choices)\n- Confident but approachable\n- Default expression: slight curious smile\n- Gestures: talks with hands, leans forward when interested\n\n## Style Keywords\nconcept art, clean lines, sharp details, [art style reference]\n\n## LoRA (if trained)\nPath: ./loras/maya-chen-v2.safetensors\nTrigger: maya_chen\nRecommended scale: 0.8"
      },
      {
        "title": "Common Mistakes",
        "body": "MistakeProblemFixVague descriptionsDifferent character every time50+ word detailed anchorInconsistent prompt structureVarying emphasis = varying resultsSame structure, only change action/sceneGenerating one view onlyCan't use character in different contextsCreate full turnaround referenceNo color documentationColors drift across generationsRecord exact hex codesSkipping expression sheetCharacter feels one-dimensionalGenerate 6+ expressionsNot using LoRA for big projectsInconsistency compoundsTrain LoRA for 10+ image projects"
      },
      {
        "title": "Related Skills",
        "body": "npx skills add inference-sh/skills@ai-image-generation\nnpx skills add inference-sh/skills@flux-image\nnpx skills add inference-sh/skills@prompt-engineering\n\nBrowse all apps: infsh app list"
      }
    ],
    "body": "Character Design Sheet\n\nCreate consistent characters across multiple AI-generated images via inference.sh CLI.\n\nQuick Start\ncurl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Generate a character concept\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character design reference sheet, front view of a young woman with short red hair, green eyes, wearing a blue jacket and white t-shirt, full body, white background, clean lines, concept art style, character turnaround\",\n  \"width\": 1024,\n  \"height\": 1024\n}'\n\n\nInstall note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.\n\nThe Consistency Problem\n\nAI image generation produces different-looking characters every time, even with the same prompt. This is the #1 challenge in AI art for any project requiring the same character across multiple images.\n\nSolutions (Ranked by Effectiveness)\nTechnique\tConsistency\tEffort\tBest For\nFLUX LoRA (trained on character)\tVery high\tHigh (requires training data)\tOngoing projects, many images\nDetailed description anchor\tMedium-high\tLow\tQuick projects, few images\nSame seed + similar prompt\tMedium\tLow\tVariations of single pose\nImage-to-image refinement\tMedium\tMedium\tRefining existing images\nReference image in prompt\tVaries\tLow\tWhen model supports it\nReference Sheet Types\n1. Turnaround Sheet\n\nShows the character from multiple angles:\n\n┌────────┬────────┬────────┬────────┐\n│        │        │        │        │\n│ FRONT  │  3/4   │  SIDE  │  BACK  │\n│  VIEW  │  VIEW  │  VIEW  │  VIEW  │\n│        │        │        │        │\n└────────┴────────┴────────┴────────┘\n\n# Generate front view\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character design, front view, young woman with short asymmetric red hair, bright green eyes, wearing navy blue bomber jacket over white graphic tee, dark jeans, red sneakers, standing in neutral pose, full body, clean white background, concept art, sharp details\",\n  \"width\": 768,\n  \"height\": 1024\n}' --no-wait\n\n# Generate 3/4 view (same description)\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character design, three-quarter view, young woman with short asymmetric red hair, bright green eyes, wearing navy blue bomber jacket over white graphic tee, dark jeans, red sneakers, standing, full body, clean white background, concept art, sharp details\",\n  \"width\": 768,\n  \"height\": 1024\n}' --no-wait\n\n# Generate side view\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character design, side profile view, young woman with short asymmetric red hair, bright green eyes, wearing navy blue bomber jacket over white graphic tee, dark jeans, red sneakers, standing, full body, clean white background, concept art, sharp details\",\n  \"width\": 768,\n  \"height\": 1024\n}' --no-wait\n\n# Generate back view\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character design, back view, young woman with short asymmetric red hair, wearing navy blue bomber jacket over white graphic tee, dark jeans, red sneakers, standing, full body, clean white background, concept art, sharp details\",\n  \"width\": 768,\n  \"height\": 1024\n}' --no-wait\n\n# Stitch into reference sheet\ninfsh app run infsh/stitch-images --input '{\n  \"images\": [\"front.png\", \"three-quarter.png\", \"side.png\", \"back.png\"],\n  \"direction\": \"horizontal\"\n}'\n\n2. Expression Sheet\n\nShows the character's face with different emotions:\n\n┌────────┬────────┬────────┐\n│NEUTRAL │ HAPPY  │ ANGRY  │\n│        │        │        │\n├────────┼────────┼────────┤\n│  SAD   │SURPRISE│THINKING│\n│        │        │        │\n└────────┴────────┴────────┘\n\n\nMinimum 6 expressions: neutral, happy, angry, sad, surprised, thinking.\n\n# Neutral\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character portrait, close-up face, young woman with short red hair and green eyes, neutral calm expression, clean white background, concept art, consistent character design\",\n  \"width\": 512,\n  \"height\": 512\n}' --no-wait\n\n# Happy\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character portrait, close-up face, young woman with short red hair and green eyes, warm genuine smile, happy expression, clean white background, concept art, consistent character design\",\n  \"width\": 512,\n  \"height\": 512\n}' --no-wait\n\n# Angry\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"character portrait, close-up face, young woman with short red hair and green eyes, furrowed brows, angry determined expression, clean white background, concept art, consistent character design\",\n  \"width\": 512,\n  \"height\": 512\n}' --no-wait\n\n# (Continue for sad, surprised, thinking...)\n\n3. Outfit/Costume Sheet\n\nMultiple outfits for the same character:\n\nOutfit\tDescription\nCasual\tBomber jacket, t-shirt, jeans\nWork\tBlazer, button-down, slacks\nAthletic\tSports bra, leggings, running shoes\nFormal\tEvening dress, heels\n4. Color Palette Sheet\n\nDocument exact colors for consistency:\n\nCHARACTER: Maya Chen\n\nSkin:    ████ #F5D0A9 (warm beige)\nHair:    ████ #C0392B (auburn red)\nEyes:    ████ #27AE60 (emerald green)\nJacket:  ████ #2C3E50 (navy blue)\nT-shirt: ████ #ECF0F1 (off-white)\nJeans:   ████ #34495E (dark slate)\nShoes:   ████ #E74C3C (bright red)\n\nThe Description Anchor Technique\n\nThe most practical consistency technique: write a 50+ word detailed description and reuse it exactly in every prompt.\n\nTemplate\n[age] [gender] with [hair: color, length, style], [eye color] eyes,\n[skin tone], [facial features: any distinctive marks],\nwearing [top: specific color and style], [bottom: specific color and style],\n[shoes: specific color and style], [accessories: specific items]\n\nExample\nyoung woman in her mid-twenties with short asymmetric auburn red hair\nswept to the right side, bright emerald green eyes, light warm skin\nwith a small beauty mark below her left eye, wearing a fitted navy\nblue bomber jacket with silver zipper over a white crew-neck t-shirt,\ndark slate slim jeans, and bright red canvas sneakers, small silver\nstud earrings\n\n\nUse this exact block in EVERY prompt for this character, only changing the action/pose/scene.\n\nProportion Guide\nStyle\tHead-to-Body Ratio\tBest For\nRealistic\t7.5 : 1\tFilm, photorealistic\nHeroic\t8 : 1\tSuperheroes, action\nAnime/Manga\t5-6 : 1\tJapanese animation style\nStylized\t4-5 : 1\tWestern animation\nChibi/Super-deformed\t2-3 : 1\tCute, comedic, mascots\n\nInclude proportion style in your prompts: \"realistic proportions\" vs \"anime style proportions\" vs \"chibi proportions\"\n\nUsing LoRA for Consistency\n\nFor projects requiring many images of the same character, train a LoRA:\n\n# Use FLUX with a character LoRA\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"maya_chen character, sitting at a cafe reading a book, warm afternoon light, candid photography style\",\n  \"loras\": [{\"path\": \"path/to/maya-chen-lora.safetensors\", \"scale\": 0.8}]\n}'\n\n\nLoRA Training Tips:\n\nNeed 10-20 reference images of the character (consistent style)\nTrain on specific trigger word (e.g., \"maya_chen\")\nScale 0.7-0.9 balances consistency with prompt flexibility\nLower scale = more creative freedom, higher = more strict matching\nCommon Consistency Failures\nIssue\tWhy It Happens\tMitigation\nHair color drift\tModel interprets \"red hair\" differently each time\tUse specific shade: \"auburn red #C0392B\"\nEye color change\tLow priority in generation\tMention eye color early in prompt\nOutfit inconsistency\tModel fills in details creatively\tDescribe every clothing item explicitly\nAge shift\tVague age description\tUse \"mid-twenties\" not \"young\"\nFace structure change\tDifferent generations = different faces\tUse LoRA or same seed base\nProportion shift\tStyle interpretation varies\tSpecify \"7.5 head proportions\"\nCharacter Bible Template\n\nFor ongoing projects, maintain a character bible document:\n\n# Character: Maya Chen\n\n## Visual Description (use in all prompts)\nyoung woman in her mid-twenties with short asymmetric auburn red hair...\n[full 50+ word anchor description]\n\n## Color Palette\n- Skin: #F5D0A9\n- Hair: #C0392B\n- Eyes: #27AE60\n- Primary outfit: Navy #2C3E50\n- Accent: Red #E74C3C\n\n## Personality Notes (for expression/pose choices)\n- Confident but approachable\n- Default expression: slight curious smile\n- Gestures: talks with hands, leans forward when interested\n\n## Style Keywords\nconcept art, clean lines, sharp details, [art style reference]\n\n## LoRA (if trained)\nPath: ./loras/maya-chen-v2.safetensors\nTrigger: maya_chen\nRecommended scale: 0.8\n\nCommon Mistakes\nMistake\tProblem\tFix\nVague descriptions\tDifferent character every time\t50+ word detailed anchor\nInconsistent prompt structure\tVarying emphasis = varying results\tSame structure, only change action/scene\nGenerating one view only\tCan't use character in different contexts\tCreate full turnaround reference\nNo color documentation\tColors drift across generations\tRecord exact hex codes\nSkipping expression sheet\tCharacter feels one-dimensional\tGenerate 6+ expressions\nNot using LoRA for big projects\tInconsistency compounds\tTrain LoRA for 10+ image projects\nRelated Skills\nnpx skills add inference-sh/skills@ai-image-generation\nnpx skills add inference-sh/skills@flux-image\nnpx skills add inference-sh/skills@prompt-engineering\n\n\nBrowse all apps: infsh app list"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/okaris/character-design-sheet",
    "publisherUrl": "https://clawhub.ai/okaris/character-design-sheet",
    "owner": "okaris",
    "version": "0.1.5",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/character-design-sheet",
    "downloadUrl": "https://openagent3.xyz/downloads/character-design-sheet",
    "agentUrl": "https://openagent3.xyz/skills/character-design-sheet/agent",
    "manifestUrl": "https://openagent3.xyz/skills/character-design-sheet/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/character-design-sheet/agent.md"
  }
}