{
  "schemaVersion": "1.0",
  "item": {
    "slug": "filtrix-image-gen",
    "name": "Filtrix Image Generation",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/lumenclaw-cloud/filtrix-image-gen",
    "canonicalUrl": "https://clawhub.ai/lumenclaw-cloud/filtrix-image-gen",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/filtrix-image-gen",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=filtrix-image-gen",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/gpt-image-1.md",
      "references/mcp-tools.md",
      "references/nano-banana-2.md",
      "references/nano-banana.md",
      "references/prompts.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/filtrix-image-gen"
    },
    "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/filtrix-image-gen",
    "agentPageUrl": "https://openagent3.xyz/skills/filtrix-image-gen/agent",
    "manifestUrl": "https://openagent3.xyz/skills/filtrix-image-gen/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/filtrix-image-gen/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": "Filtrix Image Gen (MCP)",
        "body": "This skill is MCP-only.\n\nEndpoint: https://mcp.filtrix.ai/mcp\nAuth: Authorization: Bearer <FILTRIX_MCP_API_KEY>\nPrimary tools:\n\ngenerate_image_text\nedit_image_text\nget_account_credits\n\nAvailable MCP tools:\n\nget_account_credits\ngenerate_image_text\nedit_image_text"
      },
      {
        "title": "Setup",
        "body": "Required:\n\nFILTRIX_MCP_API_KEY\n\nOptional:\n\nFILTRIX_MCP_URL (default: https://mcp.filtrix.ai/mcp)"
      },
      {
        "title": "Generate",
        "body": "python scripts/generate.py \\\n  --prompt \"...\" \\\n  [--mode gpt-image-1|nano-banana|nano-banana-2] \\\n  [--size 1024x1024|1536x1024|1024x1536|auto] \\\n  [--resolution 1K|2K|4K] \\\n  [--search-mode] \\\n  [--enhance-mode] \\\n  [--idempotency-key KEY] \\\n  [--output PATH]"
      },
      {
        "title": "Edit",
        "body": "Use this when user wants iterative refinement, style transfer, background changes, object replacement, etc.\n\npython scripts/edit.py \\\n  --prompt \"make the sky sunset orange and add volumetric light\" \\\n  (--image-path /path/to/input.png | --image-url https://...) \\\n  [--mode gpt-image-1|nano-banana|nano-banana-2] \\\n  [--size 1024x1024|1536x1024|1024x1536|auto] \\\n  [--resolution 1K|2K|4K] \\\n  [--search-mode] \\\n  [--enhance-mode] \\\n  [--idempotency-key KEY] \\\n  [--output PATH]"
      },
      {
        "title": "Mode Mapping",
        "body": "gpt-image-1: general quality route\nnano-banana: fast generation route\nnano-banana-2: advanced generation route"
      },
      {
        "title": "Recommended Workflow",
        "body": "First pass with generate_image_text (scripts/generate.py).\nUse edit_image_text (scripts/edit.py) for targeted changes.\nUse a new idempotency_key for each new edit intent."
      },
      {
        "title": "Idempotency",
        "body": "idempotency_key prevents duplicate billing on retries.\nIf omitted, scripts auto-generate one UUID-based key."
      },
      {
        "title": "References",
        "body": "MCP Tools Reference\ngpt-image-1 Mode\nnano-banana Mode\nnano-banana-2 Mode\nPrompt Guide"
      }
    ],
    "body": "Filtrix Image Gen (MCP)\n\nThis skill is MCP-only.\n\nEndpoint: https://mcp.filtrix.ai/mcp\nAuth: Authorization: Bearer <FILTRIX_MCP_API_KEY>\nPrimary tools:\ngenerate_image_text\nedit_image_text\nget_account_credits\n\nAvailable MCP tools:\n\nget_account_credits\ngenerate_image_text\nedit_image_text\nSetup\n\nRequired:\n\nFILTRIX_MCP_API_KEY\n\nOptional:\n\nFILTRIX_MCP_URL (default: https://mcp.filtrix.ai/mcp)\nGenerate\npython scripts/generate.py \\\n  --prompt \"...\" \\\n  [--mode gpt-image-1|nano-banana|nano-banana-2] \\\n  [--size 1024x1024|1536x1024|1024x1536|auto] \\\n  [--resolution 1K|2K|4K] \\\n  [--search-mode] \\\n  [--enhance-mode] \\\n  [--idempotency-key KEY] \\\n  [--output PATH]\n\nEdit\n\nUse this when user wants iterative refinement, style transfer, background changes, object replacement, etc.\n\npython scripts/edit.py \\\n  --prompt \"make the sky sunset orange and add volumetric light\" \\\n  (--image-path /path/to/input.png | --image-url https://...) \\\n  [--mode gpt-image-1|nano-banana|nano-banana-2] \\\n  [--size 1024x1024|1536x1024|1024x1536|auto] \\\n  [--resolution 1K|2K|4K] \\\n  [--search-mode] \\\n  [--enhance-mode] \\\n  [--idempotency-key KEY] \\\n  [--output PATH]\n\nMode Mapping\ngpt-image-1: general quality route\nnano-banana: fast generation route\nnano-banana-2: advanced generation route\nRecommended Workflow\nFirst pass with generate_image_text (scripts/generate.py).\nUse edit_image_text (scripts/edit.py) for targeted changes.\nUse a new idempotency_key for each new edit intent.\nIdempotency\n\nidempotency_key prevents duplicate billing on retries. If omitted, scripts auto-generate one UUID-based key.\n\nReferences\nMCP Tools Reference\ngpt-image-1 Mode\nnano-banana Mode\nnano-banana-2 Mode\nPrompt Guide"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/lumenclaw-cloud/filtrix-image-gen",
    "publisherUrl": "https://clawhub.ai/lumenclaw-cloud/filtrix-image-gen",
    "owner": "lumenclaw-cloud",
    "version": "1.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/filtrix-image-gen",
    "downloadUrl": "https://openagent3.xyz/downloads/filtrix-image-gen",
    "agentUrl": "https://openagent3.xyz/skills/filtrix-image-gen/agent",
    "manifestUrl": "https://openagent3.xyz/skills/filtrix-image-gen/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/filtrix-image-gen/agent.md"
  }
}