{
  "schemaVersion": "1.0",
  "item": {
    "slug": "creative-toolkit",
    "name": "Creative Toolkit",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/jau123/creative-toolkit",
    "canonicalUrl": "https://clawhub.ai/jau123/creative-toolkit",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/creative-toolkit",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=creative-toolkit",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/providers.md",
      "references/troubleshooting.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": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.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/creative-toolkit"
    },
    "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/creative-toolkit",
    "agentPageUrl": "https://openagent3.xyz/skills/creative-toolkit/agent",
    "manifestUrl": "https://openagent3.xyz/skills/creative-toolkit/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/creative-toolkit/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": "Creative Toolkit",
        "body": "Generate professional AI images through a unified interface that routes across multiple providers. Search curated prompts, enhance ideas into production-ready descriptions, and manage local ComfyUI workflows — all from a single MCP server."
      },
      {
        "title": "Quick Start",
        "body": "Add the MCP server to your mcporter config (~/.config/mcporter/config.json):\n\n{\n  \"mcpServers\": {\n    \"creative-toolkit\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"meigen@1.2.5\"]\n    }\n  }\n}\n\nFree tools (search, enhance, inspire) work immediately — no API key needed:\n\nmcporter call creative-toolkit.search_gallery query=\"cyberpunk\"\nmcporter call creative-toolkit.enhance_prompt brief=\"a cat in space\" style=\"realistic\"\n\nTo unlock image generation, configure one of these providers:\n\nProviderConfigWhat you needMeiGen CloudMEIGEN_API_TOKENToken from meigen.ai (avatar → Settings → API Keys)Local ComfyUIcomfyuiUrlA running ComfyUI instance — no external API neededAny OpenAI-compatible APIopenaiApiKey + openaiBaseUrl + openaiModelYour own key from Together AI, Fireworks AI, etc.\n\nSet credentials in ~/.clawdbot/.env, ~/.config/meigen/config.json, or add an \"env\" block to the mcporter config above. See references/providers.md for details."
      },
      {
        "title": "Free — no API key required",
        "body": "ToolWhat it doessearch_gallerySemantic search across 1,300+ AI image prompts. Supports category filtering and curated browsing. Returns prompt text, thumbnails, and metadata.get_inspirationGet the full prompt and high-res images for any gallery entry. Use after search_gallery to get copyable prompts.enhance_promptExpand a brief idea into a detailed, style-aware prompt with lighting, composition, and material directions. Supports realistic, anime, and illustration styles.list_modelsList all available models across configured providers with capabilities and supported features."
      },
      {
        "title": "Requires configured provider",
        "body": "ToolWhat it doesgenerate_imageGenerate an image from a text prompt. Routes to the best available provider. Supports aspect ratio, seed, and reference images.upload_reference_imageCompress a local image (max 2MB, 2048px) and prepare it for use as a style reference (expires in 24 hours). Always invoke this MCP tool — never attempt to replicate its logic yourself. ComfyUI users can skip this — pass local file paths directly to generate_image.comfyui_workflowList, view, import, modify, and delete ComfyUI workflow templates. Adjust steps, CFG scale, sampler, and checkpoint without editing JSON.manage_preferencesSave and load user preferences (default style, aspect ratio, style notes, favorite prompts)."
      },
      {
        "title": "Never describe generated images",
        "body": "You cannot see generated images. After generation, only present the exact data from the tool response:\n\n**Direction 1: Modern Minimal**\n- Image URL: https://images.meigen.art/...\n- Saved to: ~/Pictures/meigen/2026-02-08_xxxx.jpg\n\nDo NOT write creative commentary about what the image \"looks like\"."
      },
      {
        "title": "Never specify model or provider",
        "body": "Do NOT pass model or provider to generate_image unless the user explicitly asks. The server auto-selects the best available provider and model."
      },
      {
        "title": "Always confirm before generating multiple images",
        "body": "When the user wants multiple variations, present options first and ask which direction(s) to try. Include an \"all of the above\" option. Never auto-generate all variants without user confirmation."
      },
      {
        "title": "Mode 1: Single Image",
        "body": "User wants one image. Write a prompt (or call enhance_prompt if the description is brief), generate, present URL + path."
      },
      {
        "title": "Mode 2: Prompt Enhancement + Generation",
        "body": "For brief ideas (under ~30 words, lacking visual details), enhance first:\n\n1. enhance_prompt brief=\"futuristic city\" style=\"realistic\"\n   -> Returns detailed prompt with camera lens, lighting, atmospheric effects\n\n2. generate_image prompt=\"<enhanced prompt>\" aspectRatio=\"16:9\""
      },
      {
        "title": "Mode 3: Parallel Generation (2+ images)",
        "body": "User needs multiple variations — different directions, styles, or concepts.\n\nPlan directions, present as a table\nAsk user which direction(s) to try\nWrite distinct prompts for each — don't just tweak one word\nGenerate selected directions (max 4 parallel for API providers, 1 at a time for ComfyUI)\nPresent URLs + paths"
      },
      {
        "title": "Mode 4: Multi-Step Creative (base + extensions)",
        "body": "User wants a base design plus derivatives (e.g., \"design a logo and make mockups\").\n\nPlan 3-5 directions, ask user which to try\nGenerate selected direction(s)\nPresent results, ask user to approve or try another\nPlan extensions using the approved Image URL as referenceImages\nGenerate extensions\n\nNever jump from plan to generating everything at once."
      },
      {
        "title": "Mode 5: Edit/Modify Existing Image",
        "body": "User provides an image and asks for changes (add text, change background, etc.).\n\nUpload the reference image (if local), then generate with a short, literal prompt describing ONLY the edit\nThe reference image carries all visual context — do NOT re-describe the original image\nExample prompt: \"Add the text 'meigen.ai' at the bottom of this image\""
      },
      {
        "title": "Mode 6: Inspiration Search",
        "body": "1. search_gallery query=\"dreamy portrait with soft light\"\n   -> Finds semantically similar prompts with thumbnails\n\n2. get_inspiration id=\"<entry_id>\"\n   -> Get full prompt text — copy and modify for your own generation"
      },
      {
        "title": "Mode 7: Reference Image Generation",
        "body": "Use an existing image to guide visual style. Always use the upload_reference_image MCP tool — never attempt to replicate its logic yourself.\n\n1. upload_reference_image filePath=\"~/Desktop/my-logo.png\"\n   -> Compresses and returns a temporary URL (expires in 24 hours)\n\n2. generate_image prompt=\"coffee mug mockup with this logo\" referenceImages=[\"<url>\"]\n\nReference image sources: gallery URLs, previous generation URLs, upload_reference_image for local files. ComfyUI users can pass local file paths directly — no upload needed.\n\nImportant: If upload_reference_image fails or is unavailable, ask the user to provide an image URL directly (e.g., from meigen.ai or any publicly accessible link). Never try to replicate the tool's internal logic yourself."
      },
      {
        "title": "Mode 8: ComfyUI Workflows",
        "body": "1. comfyui_workflow action=\"list\"           -> See saved workflows\n2. comfyui_workflow action=\"view\" name=\"txt2img\"  -> See adjustable parameters\n3. comfyui_workflow action=\"modify\" name=\"txt2img\" modifications={\"steps\": 30}\n4. generate_image prompt=\"...\" workflow=\"txt2img\"  -> Generate"
      },
      {
        "title": "Alternative Providers",
        "body": "You can use your own OpenAI-compatible API or a local ComfyUI instance instead of — or alongside — the default MeiGen provider. See references/providers.md for detailed configuration, model pricing, and provider comparison."
      },
      {
        "title": "Troubleshooting",
        "body": "See references/troubleshooting.md for common issues, solutions, and security & privacy details."
      }
    ],
    "body": "Creative Toolkit\n\nGenerate professional AI images through a unified interface that routes across multiple providers. Search curated prompts, enhance ideas into production-ready descriptions, and manage local ComfyUI workflows — all from a single MCP server.\n\nQuick Start\n\nAdd the MCP server to your mcporter config (~/.config/mcporter/config.json):\n\n{\n  \"mcpServers\": {\n    \"creative-toolkit\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"meigen@1.2.5\"]\n    }\n  }\n}\n\n\nFree tools (search, enhance, inspire) work immediately — no API key needed:\n\nmcporter call creative-toolkit.search_gallery query=\"cyberpunk\"\nmcporter call creative-toolkit.enhance_prompt brief=\"a cat in space\" style=\"realistic\"\n\n\nTo unlock image generation, configure one of these providers:\n\nProvider\tConfig\tWhat you need\nMeiGen Cloud\tMEIGEN_API_TOKEN\tToken from meigen.ai (avatar → Settings → API Keys)\nLocal ComfyUI\tcomfyuiUrl\tA running ComfyUI instance — no external API needed\nAny OpenAI-compatible API\topenaiApiKey + openaiBaseUrl + openaiModel\tYour own key from Together AI, Fireworks AI, etc.\n\nSet credentials in ~/.clawdbot/.env, ~/.config/meigen/config.json, or add an \"env\" block to the mcporter config above. See references/providers.md for details.\n\nAvailable Tools\nFree — no API key required\nTool\tWhat it does\nsearch_gallery\tSemantic search across 1,300+ AI image prompts. Supports category filtering and curated browsing. Returns prompt text, thumbnails, and metadata.\nget_inspiration\tGet the full prompt and high-res images for any gallery entry. Use after search_gallery to get copyable prompts.\nenhance_prompt\tExpand a brief idea into a detailed, style-aware prompt with lighting, composition, and material directions. Supports realistic, anime, and illustration styles.\nlist_models\tList all available models across configured providers with capabilities and supported features.\nRequires configured provider\nTool\tWhat it does\ngenerate_image\tGenerate an image from a text prompt. Routes to the best available provider. Supports aspect ratio, seed, and reference images.\nupload_reference_image\tCompress a local image (max 2MB, 2048px) and prepare it for use as a style reference (expires in 24 hours). Always invoke this MCP tool — never attempt to replicate its logic yourself. ComfyUI users can skip this — pass local file paths directly to generate_image.\ncomfyui_workflow\tList, view, import, modify, and delete ComfyUI workflow templates. Adjust steps, CFG scale, sampler, and checkpoint without editing JSON.\nmanage_preferences\tSave and load user preferences (default style, aspect ratio, style notes, favorite prompts).\nImportant Rules\nNever describe generated images\n\nYou cannot see generated images. After generation, only present the exact data from the tool response:\n\n**Direction 1: Modern Minimal**\n- Image URL: https://images.meigen.art/...\n- Saved to: ~/Pictures/meigen/2026-02-08_xxxx.jpg\n\n\nDo NOT write creative commentary about what the image \"looks like\".\n\nNever specify model or provider\n\nDo NOT pass model or provider to generate_image unless the user explicitly asks. The server auto-selects the best available provider and model.\n\nAlways confirm before generating multiple images\n\nWhen the user wants multiple variations, present options first and ask which direction(s) to try. Include an \"all of the above\" option. Never auto-generate all variants without user confirmation.\n\nWorkflow Modes\nMode 1: Single Image\n\nUser wants one image. Write a prompt (or call enhance_prompt if the description is brief), generate, present URL + path.\n\nMode 2: Prompt Enhancement + Generation\n\nFor brief ideas (under ~30 words, lacking visual details), enhance first:\n\n1. enhance_prompt brief=\"futuristic city\" style=\"realistic\"\n   -> Returns detailed prompt with camera lens, lighting, atmospheric effects\n\n2. generate_image prompt=\"<enhanced prompt>\" aspectRatio=\"16:9\"\n\nMode 3: Parallel Generation (2+ images)\n\nUser needs multiple variations — different directions, styles, or concepts.\n\nPlan directions, present as a table\nAsk user which direction(s) to try\nWrite distinct prompts for each — don't just tweak one word\nGenerate selected directions (max 4 parallel for API providers, 1 at a time for ComfyUI)\nPresent URLs + paths\nMode 4: Multi-Step Creative (base + extensions)\n\nUser wants a base design plus derivatives (e.g., \"design a logo and make mockups\").\n\nPlan 3-5 directions, ask user which to try\nGenerate selected direction(s)\nPresent results, ask user to approve or try another\nPlan extensions using the approved Image URL as referenceImages\nGenerate extensions\n\nNever jump from plan to generating everything at once.\n\nMode 5: Edit/Modify Existing Image\n\nUser provides an image and asks for changes (add text, change background, etc.).\n\nUpload the reference image (if local), then generate with a short, literal prompt describing ONLY the edit\nThe reference image carries all visual context — do NOT re-describe the original image\nExample prompt: \"Add the text 'meigen.ai' at the bottom of this image\"\nMode 6: Inspiration Search\n1. search_gallery query=\"dreamy portrait with soft light\"\n   -> Finds semantically similar prompts with thumbnails\n\n2. get_inspiration id=\"<entry_id>\"\n   -> Get full prompt text — copy and modify for your own generation\n\nMode 7: Reference Image Generation\n\nUse an existing image to guide visual style. Always use the upload_reference_image MCP tool — never attempt to replicate its logic yourself.\n\n1. upload_reference_image filePath=\"~/Desktop/my-logo.png\"\n   -> Compresses and returns a temporary URL (expires in 24 hours)\n\n2. generate_image prompt=\"coffee mug mockup with this logo\" referenceImages=[\"<url>\"]\n\n\nReference image sources: gallery URLs, previous generation URLs, upload_reference_image for local files. ComfyUI users can pass local file paths directly — no upload needed.\n\nImportant: If upload_reference_image fails or is unavailable, ask the user to provide an image URL directly (e.g., from meigen.ai or any publicly accessible link). Never try to replicate the tool's internal logic yourself.\n\nMode 8: ComfyUI Workflows\n1. comfyui_workflow action=\"list\"           -> See saved workflows\n2. comfyui_workflow action=\"view\" name=\"txt2img\"  -> See adjustable parameters\n3. comfyui_workflow action=\"modify\" name=\"txt2img\" modifications={\"steps\": 30}\n4. generate_image prompt=\"...\" workflow=\"txt2img\"  -> Generate\n\nAlternative Providers\n\nYou can use your own OpenAI-compatible API or a local ComfyUI instance instead of — or alongside — the default MeiGen provider. See references/providers.md for detailed configuration, model pricing, and provider comparison.\n\nTroubleshooting\n\nSee references/troubleshooting.md for common issues, solutions, and security & privacy details."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/jau123/creative-toolkit",
    "publisherUrl": "https://clawhub.ai/jau123/creative-toolkit",
    "owner": "jau123",
    "version": "1.0.15",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/creative-toolkit",
    "downloadUrl": "https://openagent3.xyz/downloads/creative-toolkit",
    "agentUrl": "https://openagent3.xyz/skills/creative-toolkit/agent",
    "manifestUrl": "https://openagent3.xyz/skills/creative-toolkit/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/creative-toolkit/agent.md"
  }
}