{
  "schemaVersion": "1.0",
  "item": {
    "slug": "fabric-bridge",
    "name": "Fabric Bridge",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/koriyoshi2041/fabric-bridge",
    "canonicalUrl": "https://clawhub.ai/koriyoshi2041/fabric-bridge",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/fabric-bridge",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=fabric-bridge",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/popular-patterns.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/fabric-bridge"
    },
    "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/fabric-bridge",
    "agentPageUrl": "https://openagent3.xyz/skills/fabric-bridge/agent",
    "manifestUrl": "https://openagent3.xyz/skills/fabric-bridge/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/fabric-bridge/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": "Fabric Bridge",
        "body": "Run Fabric AI patterns via the fabric-ai CLI. Each pattern is a reusable system prompt for a specific task.\n\nSee references/popular-patterns.md for a curated list of high-quality patterns by category."
      },
      {
        "title": "Important Notes",
        "body": "The command is fabric-ai, not fabric.\nFirst-time setup: run fabric-ai -S to configure API keys.\nIf pattern list is empty: run fabric-ai -U to update patterns.\nUse -s (stream) for most calls to avoid long waits."
      },
      {
        "title": "Basic usage",
        "body": "echo \"input text\" | fabric-ai -p <pattern>"
      },
      {
        "title": "Stream output (recommended)",
        "body": "echo \"input text\" | fabric-ai -p <pattern> -s"
      },
      {
        "title": "Process a YouTube video",
        "body": "fabric-ai -y \"https://youtube.com/watch?v=...\" -p extract_wisdom -s"
      },
      {
        "title": "Process a web page",
        "body": "fabric-ai -u \"https://example.com/article\" -p summarize -s"
      },
      {
        "title": "Specify model",
        "body": "echo \"input\" | fabric-ai -p <pattern> -m gpt-4o"
      },
      {
        "title": "Chinese output",
        "body": "echo \"input\" | fabric-ai -p <pattern> -g zh -s"
      },
      {
        "title": "Chain patterns (pipe output to next pattern)",
        "body": "echo \"input\" | fabric-ai -p extract_wisdom | fabric-ai -p summarize"
      },
      {
        "title": "Reasoning strategy (requires setup)",
        "body": "echo \"input\" | fabric-ai -p <pattern> --strategy cot -s"
      },
      {
        "title": "Process an image (multimodal)",
        "body": "echo \"describe this image\" | fabric-ai -p <pattern> -a /path/to/image.png -s"
      },
      {
        "title": "Use context",
        "body": "echo \"input\" | fabric-ai -p <pattern> -C my_context -s"
      },
      {
        "title": "Session continuity",
        "body": "echo \"input\" | fabric-ai -p <pattern> --session my_session -s"
      },
      {
        "title": "Save output to file",
        "body": "echo \"input\" | fabric-ai -p extract_wisdom -o output.md"
      },
      {
        "title": "Copy output to clipboard",
        "body": "echo \"input\" | fabric-ai -p extract_wisdom -c"
      },
      {
        "title": "Dry run (preview without calling API)",
        "body": "fabric-ai -p <pattern> --dry-run"
      },
      {
        "title": "List all available patterns",
        "body": "fabric-ai -l"
      },
      {
        "title": "Template Variables",
        "body": "Patterns can contain {{variable}} placeholders. Pass values with -v:\n\n# Single variable\necho \"input\" | fabric-ai -p <pattern> -v=\"#role:expert\"\n\n# Multiple variables\necho \"input\" | fabric-ai -p <pattern> -v=\"#role:expert\" -v=\"#points:30\""
      },
      {
        "title": "Custom Patterns",
        "body": "Create custom patterns at ~/.config/fabric/patterns/<name>/system.md.\n\nEach pattern directory contains a system.md file with the system prompt."
      },
      {
        "title": "Feeding File Content",
        "body": "cat file.txt | fabric-ai -p <pattern> -s\ncat file1.md file2.md | fabric-ai -p <pattern> -s"
      },
      {
        "title": "Tips",
        "body": "Prefer -s (stream) for interactive use — output appears incrementally.\nChain patterns for multi-step processing (extract → summarize → translate).\nUse -g zh when the user wants Chinese output.\nUse -o file.md to save output, -c to copy to clipboard.\nUse --dry-run to inspect what will be sent before making API calls.\nRun fabric-ai -U periodically to get new community patterns."
      }
    ],
    "body": "Fabric Bridge\n\nRun Fabric AI patterns via the fabric-ai CLI. Each pattern is a reusable system prompt for a specific task.\n\nSee references/popular-patterns.md for a curated list of high-quality patterns by category.\n\nImportant Notes\nThe command is fabric-ai, not fabric.\nFirst-time setup: run fabric-ai -S to configure API keys.\nIf pattern list is empty: run fabric-ai -U to update patterns.\nUse -s (stream) for most calls to avoid long waits.\nCore Commands\nBasic usage\necho \"input text\" | fabric-ai -p <pattern>\n\nStream output (recommended)\necho \"input text\" | fabric-ai -p <pattern> -s\n\nProcess a YouTube video\nfabric-ai -y \"https://youtube.com/watch?v=...\" -p extract_wisdom -s\n\nProcess a web page\nfabric-ai -u \"https://example.com/article\" -p summarize -s\n\nSpecify model\necho \"input\" | fabric-ai -p <pattern> -m gpt-4o\n\nChinese output\necho \"input\" | fabric-ai -p <pattern> -g zh -s\n\nChain patterns (pipe output to next pattern)\necho \"input\" | fabric-ai -p extract_wisdom | fabric-ai -p summarize\n\nReasoning strategy (requires setup)\necho \"input\" | fabric-ai -p <pattern> --strategy cot -s\n\nProcess an image (multimodal)\necho \"describe this image\" | fabric-ai -p <pattern> -a /path/to/image.png -s\n\nUse context\necho \"input\" | fabric-ai -p <pattern> -C my_context -s\n\nSession continuity\necho \"input\" | fabric-ai -p <pattern> --session my_session -s\n\nSave output to file\necho \"input\" | fabric-ai -p extract_wisdom -o output.md\n\nCopy output to clipboard\necho \"input\" | fabric-ai -p extract_wisdom -c\n\nDry run (preview without calling API)\nfabric-ai -p <pattern> --dry-run\n\nList all available patterns\nfabric-ai -l\n\nTemplate Variables\n\nPatterns can contain {{variable}} placeholders. Pass values with -v:\n\n# Single variable\necho \"input\" | fabric-ai -p <pattern> -v=\"#role:expert\"\n\n# Multiple variables\necho \"input\" | fabric-ai -p <pattern> -v=\"#role:expert\" -v=\"#points:30\"\n\nCustom Patterns\n\nCreate custom patterns at ~/.config/fabric/patterns/<name>/system.md.\n\nEach pattern directory contains a system.md file with the system prompt.\n\nFeeding File Content\ncat file.txt | fabric-ai -p <pattern> -s\ncat file1.md file2.md | fabric-ai -p <pattern> -s\n\nTips\nPrefer -s (stream) for interactive use — output appears incrementally.\nChain patterns for multi-step processing (extract → summarize → translate).\nUse -g zh when the user wants Chinese output.\nUse -o file.md to save output, -c to copy to clipboard.\nUse --dry-run to inspect what will be sent before making API calls.\nRun fabric-ai -U periodically to get new community patterns."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/koriyoshi2041/fabric-bridge",
    "publisherUrl": "https://clawhub.ai/koriyoshi2041/fabric-bridge",
    "owner": "koriyoshi2041",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/fabric-bridge",
    "downloadUrl": "https://openagent3.xyz/downloads/fabric-bridge",
    "agentUrl": "https://openagent3.xyz/skills/fabric-bridge/agent",
    "manifestUrl": "https://openagent3.xyz/skills/fabric-bridge/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/fabric-bridge/agent.md"
  }
}