{
  "schemaVersion": "1.0",
  "item": {
    "slug": "nvidia-kimi-vision",
    "name": "NVIDIA Kimi Vision",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/miladnoo/nvidia-kimi-vision",
    "canonicalUrl": "https://clawhub.ai/miladnoo/nvidia-kimi-vision",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/nvidia-kimi-vision",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=nvidia-kimi-vision",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/analyze_image.py"
    ],
    "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/nvidia-kimi-vision"
    },
    "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/nvidia-kimi-vision",
    "agentPageUrl": "https://openagent3.xyz/skills/nvidia-kimi-vision/agent",
    "manifestUrl": "https://openagent3.xyz/skills/nvidia-kimi-vision/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/nvidia-kimi-vision/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": "NVIDIA Kimi Vision",
        "body": "Fast image analysis using Kimi K2.5 multimodal model from NVIDIA NIM."
      },
      {
        "title": "Why This Skill?",
        "body": "Fast - NVIDIA NIM inference\nQuality - Kimi K2.5 is a solid vision model\nSimple - Just pass an image and prompt\nFree tier - Available through NVIDIA build.nvidia.com"
      },
      {
        "title": "API Setup (IMPORTANT)",
        "body": "When using this skill, if no API key is found, it will automatically guide the user through setup:"
      },
      {
        "title": "Step 1: Get a Free API Key",
        "body": "Go to https://build.nvidia.com\nSign up / Log in with GitHub or Google\nSearch for \"Kimi K2.5\"\nClick on the model and get your free API key"
      },
      {
        "title": "Step 2: Save the Key",
        "body": "# Option A: Save to file (recommended)\nmkdir -p ~/.config\necho 'your-api-key-here' > ~/.config/nvidia-kimi-api-key\n\n# Option B: Pass directly when running\npython3 scripts/analyze_image.py photo.jpg \"What's this?\" sk-your-key-here"
      },
      {
        "title": "First Time Setup (for agents)",
        "body": "When a user tries to use this skill without an API key, the script will output clear setup instructions. Guide them through:\n\nVisiting https://build.nvidia.com\nGetting their free API key\nSaving it to ~/.config/nvidia-kimi-api-key"
      },
      {
        "title": "Usage",
        "body": "python3 scripts/analyze_image.py <image_path> \"<prompt>\" [api_key]"
      },
      {
        "title": "Examples",
        "body": "# What's in this image?\npython3 scripts/analyze_image.py \"/path/to/image.jpg\" \"Describe what's in this image\"\n\n# Extract text from screenshot\npython3 scripts/analyze_image.py \"/path/screenshot.png\" \"Extract all text\"\n\n# Analyze a meme\npython3 scripts/analyze_image.py \"/path/meme.jpg\" \"Explain this meme\"\n\n# With API key inline\npython3 scripts/analyze_image.py photo.jpg \"What's this?\" sk-xxxxx"
      },
      {
        "title": "Image Formats",
        "body": "Supports: png, jpg, jpeg, webp"
      },
      {
        "title": "Rate Limits",
        "body": "The free tier through NVIDIA NIM has some limits, but they're not clearly documented on the site. Check https://build.nvidia.com for the latest info on your specific key's limits."
      }
    ],
    "body": "NVIDIA Kimi Vision\n\nFast image analysis using Kimi K2.5 multimodal model from NVIDIA NIM.\n\nWhy This Skill?\nFast - NVIDIA NIM inference\nQuality - Kimi K2.5 is a solid vision model\nSimple - Just pass an image and prompt\nFree tier - Available through NVIDIA build.nvidia.com\nAPI Setup (IMPORTANT)\n\nWhen using this skill, if no API key is found, it will automatically guide the user through setup:\n\nStep 1: Get a Free API Key\nGo to https://build.nvidia.com\nSign up / Log in with GitHub or Google\nSearch for \"Kimi K2.5\"\nClick on the model and get your free API key\nStep 2: Save the Key\n# Option A: Save to file (recommended)\nmkdir -p ~/.config\necho 'your-api-key-here' > ~/.config/nvidia-kimi-api-key\n\n# Option B: Pass directly when running\npython3 scripts/analyze_image.py photo.jpg \"What's this?\" sk-your-key-here\n\nFirst Time Setup (for agents)\n\nWhen a user tries to use this skill without an API key, the script will output clear setup instructions. Guide them through:\n\nVisiting https://build.nvidia.com\nGetting their free API key\nSaving it to ~/.config/nvidia-kimi-api-key\nUsage\npython3 scripts/analyze_image.py <image_path> \"<prompt>\" [api_key]\n\nExamples\n# What's in this image?\npython3 scripts/analyze_image.py \"/path/to/image.jpg\" \"Describe what's in this image\"\n\n# Extract text from screenshot\npython3 scripts/analyze_image.py \"/path/screenshot.png\" \"Extract all text\"\n\n# Analyze a meme\npython3 scripts/analyze_image.py \"/path/meme.jpg\" \"Explain this meme\"\n\n# With API key inline\npython3 scripts/analyze_image.py photo.jpg \"What's this?\" sk-xxxxx\n\nImage Formats\n\nSupports: png, jpg, jpeg, webp\n\nRate Limits\n\nThe free tier through NVIDIA NIM has some limits, but they're not clearly documented on the site. Check https://build.nvidia.com for the latest info on your specific key's limits."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/miladnoo/nvidia-kimi-vision",
    "publisherUrl": "https://clawhub.ai/miladnoo/nvidia-kimi-vision",
    "owner": "miladnoo",
    "version": "1.0.3",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/nvidia-kimi-vision",
    "downloadUrl": "https://openagent3.xyz/downloads/nvidia-kimi-vision",
    "agentUrl": "https://openagent3.xyz/skills/nvidia-kimi-vision/agent",
    "manifestUrl": "https://openagent3.xyz/skills/nvidia-kimi-vision/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/nvidia-kimi-vision/agent.md"
  }
}