{
  "schemaVersion": "1.0",
  "item": {
    "slug": "wavespeed",
    "name": "WaveSpeed AI",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/al1enjesus/wavespeed",
    "canonicalUrl": "https://clawhub.ai/al1enjesus/wavespeed",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/wavespeed",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=wavespeed",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "package.json",
      "references/models.md",
      "scripts/wavespeed.js"
    ],
    "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "wavespeed",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-04T11:36:58.088Z",
      "expiresAt": "2026-05-11T11:36:58.088Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=wavespeed",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=wavespeed",
        "contentDisposition": "attachment; filename=\"wavespeed-1.1.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "wavespeed"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/wavespeed"
    },
    "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/wavespeed",
    "agentPageUrl": "https://openagent3.xyz/skills/wavespeed/agent",
    "manifestUrl": "https://openagent3.xyz/skills/wavespeed/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/wavespeed/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "WaveSpeed AI",
        "body": "700+ AI models (Google, OpenAI, ByteDance, Kling, Luma) via one API. Images in <2s, videos in <2min."
      },
      {
        "title": "API Key — check in this order",
        "body": "WAVESPEED_API_KEY env var — already set in all Clawster containers, just use it directly\nTOOLS.md in the workspace — look for WaveSpeed AI section\nAsk the user\n\nNever search for the key — if WAVESPEED_API_KEY is in the environment, it's ready to go. Check with:\n\necho $WAVESPEED_API_KEY"
      },
      {
        "title": "Get your API key",
        "body": "Sign up at wavespeed.ai → Dashboard → API Keys.\nNew accounts get free credits. Pay-as-you-go pricing — no subscription required.\n\nexport WAVESPEED_API_KEY=your_key_here\n\nThe skill script is at skills/wavespeed/scripts/wavespeed.js."
      },
      {
        "title": "Usage",
        "body": "# Image generation\nnode wavespeed.js generate --model flux --prompt \"sunset over mountains\" --output out.png\nnode wavespeed.js generate --model seedream --prompt \"...\" --size 1024x1024\n\n# Image editing (face/portrait-safe — preserves identity)\nnode wavespeed.js edit --model nbp --prompt \"change bathrobe to black hoodie, dark background\" \\\n  --image https://example.com/photo.jpg --output result.png\n\n# Video from image\nnode wavespeed.js video --model wan-i2v --prompt \"slow cinematic zoom\" \\\n  --image https://example.com/frame.jpg --output clip.mp4\n\n# List all aliases\nnode wavespeed.js models\n\n# Check task status\nnode wavespeed.js status --id task_abc123"
      },
      {
        "title": "Key Models (Quick Reference)",
        "body": "TaskAliasBest forEdit photo keeping facenbpPortrait retouching, outfit/bg changeFast image genflux-schnellDrafts, quick testsBest image qualityflux-pro / seedreamFinal outputsImage → Videowan-i2vFast, affordablePremium videokling / veoCinematic qualityText → Videosora / veoStory videos\n\nSee references/models.md for full model list with IDs, params, and pricing."
      },
      {
        "title": "Important Notes",
        "body": "Image editing (nbp, nb-edit): always pass images as images: [url] array — this is required\nFace preservation: google/nano-banana-pro/edit is the best model for editing photos while keeping the person's face identical\nOutput files are saved to current directory by default; use --output to specify path\nVideos can take 2-5 minutes; script auto-polls with progress indicator\nFor multiple input images (multi-reference editing), use --images url1,url2"
      }
    ],
    "body": "WaveSpeed AI\n\n700+ AI models (Google, OpenAI, ByteDance, Kling, Luma) via one API. Images in <2s, videos in <2min.\n\nAPI Key — check in this order\nWAVESPEED_API_KEY env var — already set in all Clawster containers, just use it directly\nTOOLS.md in the workspace — look for WaveSpeed AI section\nAsk the user\n\nNever search for the key — if WAVESPEED_API_KEY is in the environment, it's ready to go. Check with:\n\necho $WAVESPEED_API_KEY\n\nGet your API key\n\nSign up at wavespeed.ai → Dashboard → API Keys.\nNew accounts get free credits. Pay-as-you-go pricing — no subscription required.\n\nexport WAVESPEED_API_KEY=your_key_here\n\n\nThe skill script is at skills/wavespeed/scripts/wavespeed.js.\n\nUsage\n# Image generation\nnode wavespeed.js generate --model flux --prompt \"sunset over mountains\" --output out.png\nnode wavespeed.js generate --model seedream --prompt \"...\" --size 1024x1024\n\n# Image editing (face/portrait-safe — preserves identity)\nnode wavespeed.js edit --model nbp --prompt \"change bathrobe to black hoodie, dark background\" \\\n  --image https://example.com/photo.jpg --output result.png\n\n# Video from image\nnode wavespeed.js video --model wan-i2v --prompt \"slow cinematic zoom\" \\\n  --image https://example.com/frame.jpg --output clip.mp4\n\n# List all aliases\nnode wavespeed.js models\n\n# Check task status\nnode wavespeed.js status --id task_abc123\n\nKey Models (Quick Reference)\nTask\tAlias\tBest for\nEdit photo keeping face\tnbp\tPortrait retouching, outfit/bg change\nFast image gen\tflux-schnell\tDrafts, quick tests\nBest image quality\tflux-pro / seedream\tFinal outputs\nImage → Video\twan-i2v\tFast, affordable\nPremium video\tkling / veo\tCinematic quality\nText → Video\tsora / veo\tStory videos\n\nSee references/models.md for full model list with IDs, params, and pricing.\n\nImportant Notes\nImage editing (nbp, nb-edit): always pass images as images: [url] array — this is required\nFace preservation: google/nano-banana-pro/edit is the best model for editing photos while keeping the person's face identical\nOutput files are saved to current directory by default; use --output to specify path\nVideos can take 2-5 minutes; script auto-polls with progress indicator\nFor multiple input images (multi-reference editing), use --images url1,url2"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/al1enjesus/wavespeed",
    "publisherUrl": "https://clawhub.ai/al1enjesus/wavespeed",
    "owner": "al1enjesus",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/wavespeed",
    "downloadUrl": "https://openagent3.xyz/downloads/wavespeed",
    "agentUrl": "https://openagent3.xyz/skills/wavespeed/agent",
    "manifestUrl": "https://openagent3.xyz/skills/wavespeed/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/wavespeed/agent.md"
  }
}