{
  "schemaVersion": "1.0",
  "item": {
    "slug": "reducto",
    "name": "Reducto",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/byungkyu/reducto",
    "canonicalUrl": "https://clawhub.ai/byungkyu/reducto",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/reducto",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=reducto",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "LICENSE.txt"
    ],
    "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": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/reducto"
    },
    "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/reducto",
    "agentPageUrl": "https://openagent3.xyz/skills/reducto/agent",
    "manifestUrl": "https://openagent3.xyz/skills/reducto/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/reducto/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": "Reducto",
        "body": "Access the Reducto document processing API with managed API key authentication. Parse documents, extract structured data, split documents into sections, and edit PDFs/DOCX files."
      },
      {
        "title": "Quick Start",
        "body": "# Parse a document\npython <<'EOF'\nimport urllib.request, os, json\ndata = json.dumps({'document_url': 'https://example.com/document.pdf'}).encode()\nreq = urllib.request.Request('https://gateway.maton.ai/reducto/parse', data=data, method='POST')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nreq.add_header('Content-Type', 'application/json')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF"
      },
      {
        "title": "Base URL",
        "body": "https://gateway.maton.ai/reducto/{native-api-path}\n\nReplace {native-api-path} with the actual Reducto API endpoint path. The gateway proxies requests to platform.reducto.ai and automatically injects your API key."
      },
      {
        "title": "Authentication",
        "body": "All requests require the Maton API key in the Authorization header:\n\nAuthorization: Bearer $MATON_API_KEY\n\nEnvironment Variable: Set your API key as MATON_API_KEY:\n\nexport MATON_API_KEY=\"YOUR_API_KEY\""
      },
      {
        "title": "Getting Your API Key",
        "body": "Sign in or create an account at maton.ai\nGo to maton.ai/settings\nCopy your API key"
      },
      {
        "title": "Connection Management",
        "body": "Manage your Reducto API key connections at https://ctrl.maton.ai."
      },
      {
        "title": "List Connections",
        "body": "python <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections?app=reducto&status=ACTIVE')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF"
      },
      {
        "title": "Create Connection",
        "body": "python <<'EOF'\nimport urllib.request, os, json\ndata = json.dumps({'app': 'reducto'}).encode()\nreq = urllib.request.Request('https://ctrl.maton.ai/connections', data=data, method='POST')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nreq.add_header('Content-Type', 'application/json')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF"
      },
      {
        "title": "Get Connection",
        "body": "python <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n\nResponse:\n\n{\n  \"connection\": {\n    \"connection_id\": \"f7579208-276c-455f-9962-4635fca739b9\",\n    \"status\": \"ACTIVE\",\n    \"creation_time\": \"2026-02-28T00:12:24.797884Z\",\n    \"last_updated_time\": \"2026-02-28T00:16:13.509841Z\",\n    \"url\": \"https://connect.maton.ai/?session_token=...\",\n    \"app\": \"reducto\",\n    \"metadata\": {},\n    \"method\": \"API_KEY\"\n  }\n}\n\nOpen the returned url in a browser to enter your Reducto API key."
      },
      {
        "title": "Delete Connection",
        "body": "python <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}', method='DELETE')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF"
      },
      {
        "title": "Specifying Connection",
        "body": "If you have multiple Reducto connections, specify which one to use with the Maton-Connection header:\n\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://gateway.maton.ai/reducto/parse')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nreq.add_header('Maton-Connection', 'f7579208-276c-455f-9962-4635fca739b9')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n\nIf omitted, the gateway uses the default (oldest) active connection."
      },
      {
        "title": "Parse Document",
        "body": "Parse a document and extract structured content (text, tables, figures).\n\nSynchronous Parse\n\nPOST /reducto/parse\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/document.pdf\"\n}\n\nResponse:\n\n{\n  \"job_id\": \"04b8aa38-7eb3-4151-98b0-dbaea71358d9\",\n  \"duration\": 17.85,\n  \"pdf_url\": \"https://...\",\n  \"studio_link\": \"https://studio.reducto.ai/job/...\",\n  \"usage\": {\n    \"num_pages\": 15,\n    \"credits\": 15.0\n  },\n  \"result\": {\n    \"chunks\": [\n      {\n        \"content\": \"Extracted text content...\",\n        \"blocks\": [...]\n      }\n    ]\n  }\n}\n\nAsynchronous Parse\n\nFor long documents, use async to avoid timeouts:\n\nPOST /reducto/parse_async\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/document.pdf\"\n}\n\nResponse:\n\n{\n  \"job_id\": \"e234ba95-410a-4dd0-8a14-743dbfc49470\"\n}\n\nPoll the job status with GET /reducto/job/{job_id}."
      },
      {
        "title": "Extract Data",
        "body": "Extract specific fields from documents using a JSON schema.\n\nSynchronous Extract\n\nPOST /reducto/extract\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/document.pdf\",\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"title\": {\"type\": \"string\", \"description\": \"The document title\"},\n      \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}, \"description\": \"List of author names\"}\n    }\n  }\n}\n\nResponse:\n\n{\n  \"job_id\": \"36f01a34-7ef6-40da-9e74-7c14902b6182\",\n  \"usage\": {\n    \"num_pages\": 15,\n    \"num_fields\": 9,\n    \"credits\": 45.0\n  },\n  \"studio_link\": \"https://studio.reducto.ai/job/...\",\n  \"result\": [\n    {\n      \"title\": \"Document Title\",\n      \"authors\": [\"Author One\", \"Author Two\"]\n    }\n  ]\n}\n\nAsynchronous Extract\n\nPOST /reducto/extract_async\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/document.pdf\",\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"title\": {\"type\": \"string\"}\n    }\n  }\n}\n\nResponse:\n\n{\n  \"job_id\": \"0cdb6a50-df92-438b-875b-8b5c72d5b089\"\n}"
      },
      {
        "title": "Split Document",
        "body": "Divide documents into logical sections based on content categories.\n\nSynchronous Split\n\nPOST /reducto/split\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/document.pdf\",\n  \"split_description\": [\n    {\"name\": \"abstract\", \"description\": \"The abstract section\"},\n    {\"name\": \"introduction\", \"description\": \"The introduction section\"},\n    {\"name\": \"conclusion\", \"description\": \"The conclusion section\"}\n  ]\n}\n\nResponse:\n\n{\n  \"usage\": {\n    \"num_pages\": 15,\n    \"credits\": 15.0\n  },\n  \"result\": {\n    \"section_mapping\": {\n      \"abstract\": [1],\n      \"introduction\": [1, 2],\n      \"conclusion\": [14, 15]\n    },\n    \"splits\": [\n      {\n        \"name\": \"abstract\",\n        \"pages\": [1],\n        \"conf\": \"high\"\n      }\n    ]\n  }\n}\n\nAsynchronous Split\n\nPOST /reducto/split_async\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/document.pdf\",\n  \"split_description\": [\n    {\"name\": \"abstract\", \"description\": \"The abstract section\"}\n  ]\n}\n\nResponse:\n\n{\n  \"job_id\": \"381de5fe-e162-4039-9ef9-8522fb34056b\"\n}"
      },
      {
        "title": "Edit Document",
        "body": "Fill forms and modify PDF/DOCX documents with natural language instructions.\n\nSynchronous Edit\n\nPOST /reducto/edit\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/form.pdf\",\n  \"edit_instructions\": \"Fill in the name field with 'John Doe' and check the consent box\"\n}\n\nResponse:\n\n{\n  \"document_url\": \"https://presigned-url.s3.amazonaws.com/...\",\n  \"form_schema\": [...],\n  \"usage\": {\n    \"num_pages\": 2,\n    \"credits\": 2.0\n  }\n}\n\nAsynchronous Edit\n\nPOST /reducto/edit_async\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/form.pdf\",\n  \"edit_instructions\": \"Highlight all mentions of 'important' in red\"\n}\n\nResponse:\n\n{\n  \"job_id\": \"575189cb-8732-429a-ba8a-06de8ee03208\"\n}"
      },
      {
        "title": "Upload File",
        "body": "Upload a document to Reducto and get a presigned URL for processing.\n\nPOST /reducto/upload\nContent-Type: application/json\n\n{}\n\nResponse:\n\n{\n  \"file_id\": \"reducto://18d574c7-4144-4f50-b7af-b8aba83ada5d\",\n  \"presigned_url\": \"https://prod-storage.s3.amazonaws.com/...?AWSAccessKeyId=...&Signature=...&Expires=...\"\n}\n\nUpload your file to the presigned_url using a PUT request, then use the file_id as document_url in parse/extract/split/edit requests."
      },
      {
        "title": "Pipeline",
        "body": "Execute pre-configured processing pipelines.\n\nPOST /reducto/pipeline\nContent-Type: application/json\n\n{\n  \"input\": \"https://example.com/document.pdf\",\n  \"pipeline_id\": \"your-pipeline-id\"\n}\n\nNote: pipeline_id must be a valid pipeline ID configured in your Reducto account via the Reducto Studio.\n\nResponse:\n\n{\n  \"job_id\": \"...\",\n  \"usage\": {\n    \"num_pages\": 15,\n    \"credits\": 15.0\n  },\n  \"result\": {\n    \"parse\": {...},\n    \"extract\": {...},\n    \"split\": {...},\n    \"edit\": {...}\n  }\n}"
      },
      {
        "title": "Jobs",
        "body": "List Jobs\n\nGET /reducto/jobs\n\nResponse:\n\n{\n  \"jobs\": [\n    {\n      \"job_id\": \"8c25561f-247a-4843-b561-1eb94c3792d1\",\n      \"status\": \"Completed\",\n      \"type\": \"Parse\",\n      \"created_at\": \"2026-02-27T23:11:39.787917\",\n      \"num_pages\": 15,\n      \"duration\": 6.62\n    }\n  ],\n  \"next_cursor\": null\n}\n\nGet Job Status\n\nGET /reducto/job/{job_id}\n\nResponse (Pending):\n\n{\n  \"status\": \"Pending\",\n  \"result\": null,\n  \"progress\": 0.5,\n  \"reason\": null\n}\n\nResponse (Completed):\n\n{\n  \"status\": \"Completed\",\n  \"result\": {\n    \"job_id\": \"...\",\n    \"duration\": 17.85,\n    \"usage\": {...},\n    \"result\": {...}\n  },\n  \"progress\": null,\n  \"reason\": null\n}\n\nJob status values: Pending, InProgress, Completed, Failed"
      },
      {
        "title": "Version",
        "body": "GET /reducto/version\n\nResponse:\n\n\"VERSION_GOES_HERE\""
      },
      {
        "title": "Document URL Formats",
        "body": "The document_url parameter accepts several formats:\n\nPublic URL: https://example.com/document.pdf\nPresigned S3 URL: https://bucket.s3.amazonaws.com/key?...\nReducto Upload: reducto://file-id (from /upload endpoint)\nPrevious Job: jobid://job-id (reuse parsed content from previous job)"
      },
      {
        "title": "JavaScript",
        "body": "// Parse a document\nconst response = await fetch(\n  'https://gateway.maton.ai/reducto/parse',\n  {\n    method: 'POST',\n    headers: {\n      'Authorization': `Bearer ${process.env.MATON_API_KEY}`,\n      'Content-Type': 'application/json'\n    },\n    body: JSON.stringify({\n      document_url: 'https://example.com/document.pdf'\n    })\n  }\n);\nconst data = await response.json();\nconsole.log(data.result.chunks);"
      },
      {
        "title": "Python",
        "body": "import os\nimport requests\n\n# Extract data from a document\nresponse = requests.post(\n    'https://gateway.maton.ai/reducto/extract',\n    headers={\n        'Authorization': f'Bearer {os.environ[\"MATON_API_KEY\"]}',\n        'Content-Type': 'application/json'\n    },\n    json={\n        'document_url': 'https://example.com/document.pdf',\n        'schema': {\n            'type': 'object',\n            'properties': {\n                'title': {'type': 'string'},\n                'date': {'type': 'string'}\n            }\n        }\n    }\n)\nresult = response.json()\nprint(result['result'])"
      },
      {
        "title": "Async Job Polling",
        "body": "import os\nimport time\nimport requests\n\n# Start async parse\nresponse = requests.post(\n    'https://gateway.maton.ai/reducto/parse_async',\n    headers={\n        'Authorization': f'Bearer {os.environ[\"MATON_API_KEY\"]}',\n        'Content-Type': 'application/json'\n    },\n    json={'document_url': 'https://example.com/large-document.pdf'}\n)\njob_id = response.json()['job_id']\n\n# Poll for completion\nwhile True:\n    status = requests.get(\n        f'https://gateway.maton.ai/reducto/job/{job_id}',\n        headers={'Authorization': f'Bearer {os.environ[\"MATON_API_KEY\"]}'}\n    ).json()\n\n    print(f\"Status: {status['status']}, Progress: {status.get('progress')}\")\n\n    if status['status'] == 'Completed':\n        print(status['result'])\n        break\n    elif status['status'] == 'Failed':\n        print(f\"Failed: {status['reason']}\")\n        break\n\n    time.sleep(2)"
      },
      {
        "title": "Notes",
        "body": "Synchronous endpoints may timeout for large documents; use async endpoints instead\nUpload presigned URLs expire quickly; upload files immediately after calling /upload\nThe reducto:// prefix URLs from /upload can be used in subsequent parse/extract/split/edit calls\nUse jobid:// prefix to reuse parsed content from a previous job (saves processing time)\nConnection uses API_KEY authentication method (not OAuth)\nCredits are consumed based on page count and operation type"
      },
      {
        "title": "Error Handling",
        "body": "StatusMeaning400Invalid request (missing required fields, invalid format)401Invalid or missing Maton API key404Resource not found422Validation error (check response body for details)4xx/5xxPassthrough error from Reducto API"
      },
      {
        "title": "Troubleshooting: API Key Issues",
        "body": "Check that the MATON_API_KEY environment variable is set:\n\necho $MATON_API_KEY\n\nVerify the API key is valid by listing connections:\n\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF"
      },
      {
        "title": "Troubleshooting: Invalid App Name",
        "body": "Ensure your URL path starts with reducto. For example:\n\nCorrect: https://gateway.maton.ai/reducto/parse\nIncorrect: https://gateway.maton.ai/parse"
      },
      {
        "title": "Resources",
        "body": "Reducto Documentation\nReducto API Reference\nReducto Studio\nMaton Community\nMaton Support"
      }
    ],
    "body": "Reducto\n\nAccess the Reducto document processing API with managed API key authentication. Parse documents, extract structured data, split documents into sections, and edit PDFs/DOCX files.\n\nQuick Start\n# Parse a document\npython <<'EOF'\nimport urllib.request, os, json\ndata = json.dumps({'document_url': 'https://example.com/document.pdf'}).encode()\nreq = urllib.request.Request('https://gateway.maton.ai/reducto/parse', data=data, method='POST')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nreq.add_header('Content-Type', 'application/json')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n\nBase URL\nhttps://gateway.maton.ai/reducto/{native-api-path}\n\n\nReplace {native-api-path} with the actual Reducto API endpoint path. The gateway proxies requests to platform.reducto.ai and automatically injects your API key.\n\nAuthentication\n\nAll requests require the Maton API key in the Authorization header:\n\nAuthorization: Bearer $MATON_API_KEY\n\n\nEnvironment Variable: Set your API key as MATON_API_KEY:\n\nexport MATON_API_KEY=\"YOUR_API_KEY\"\n\nGetting Your API Key\nSign in or create an account at maton.ai\nGo to maton.ai/settings\nCopy your API key\nConnection Management\n\nManage your Reducto API key connections at https://ctrl.maton.ai.\n\nList Connections\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections?app=reducto&status=ACTIVE')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n\nCreate Connection\npython <<'EOF'\nimport urllib.request, os, json\ndata = json.dumps({'app': 'reducto'}).encode()\nreq = urllib.request.Request('https://ctrl.maton.ai/connections', data=data, method='POST')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nreq.add_header('Content-Type', 'application/json')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n\nGet Connection\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n\n\nResponse:\n\n{\n  \"connection\": {\n    \"connection_id\": \"f7579208-276c-455f-9962-4635fca739b9\",\n    \"status\": \"ACTIVE\",\n    \"creation_time\": \"2026-02-28T00:12:24.797884Z\",\n    \"last_updated_time\": \"2026-02-28T00:16:13.509841Z\",\n    \"url\": \"https://connect.maton.ai/?session_token=...\",\n    \"app\": \"reducto\",\n    \"metadata\": {},\n    \"method\": \"API_KEY\"\n  }\n}\n\n\nOpen the returned url in a browser to enter your Reducto API key.\n\nDelete Connection\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}', method='DELETE')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n\nSpecifying Connection\n\nIf you have multiple Reducto connections, specify which one to use with the Maton-Connection header:\n\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://gateway.maton.ai/reducto/parse')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nreq.add_header('Maton-Connection', 'f7579208-276c-455f-9962-4635fca739b9')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n\n\nIf omitted, the gateway uses the default (oldest) active connection.\n\nAPI Reference\nParse Document\n\nParse a document and extract structured content (text, tables, figures).\n\nSynchronous Parse\nPOST /reducto/parse\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/document.pdf\"\n}\n\n\nResponse:\n\n{\n  \"job_id\": \"04b8aa38-7eb3-4151-98b0-dbaea71358d9\",\n  \"duration\": 17.85,\n  \"pdf_url\": \"https://...\",\n  \"studio_link\": \"https://studio.reducto.ai/job/...\",\n  \"usage\": {\n    \"num_pages\": 15,\n    \"credits\": 15.0\n  },\n  \"result\": {\n    \"chunks\": [\n      {\n        \"content\": \"Extracted text content...\",\n        \"blocks\": [...]\n      }\n    ]\n  }\n}\n\nAsynchronous Parse\n\nFor long documents, use async to avoid timeouts:\n\nPOST /reducto/parse_async\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/document.pdf\"\n}\n\n\nResponse:\n\n{\n  \"job_id\": \"e234ba95-410a-4dd0-8a14-743dbfc49470\"\n}\n\n\nPoll the job status with GET /reducto/job/{job_id}.\n\nExtract Data\n\nExtract specific fields from documents using a JSON schema.\n\nSynchronous Extract\nPOST /reducto/extract\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/document.pdf\",\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"title\": {\"type\": \"string\", \"description\": \"The document title\"},\n      \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}, \"description\": \"List of author names\"}\n    }\n  }\n}\n\n\nResponse:\n\n{\n  \"job_id\": \"36f01a34-7ef6-40da-9e74-7c14902b6182\",\n  \"usage\": {\n    \"num_pages\": 15,\n    \"num_fields\": 9,\n    \"credits\": 45.0\n  },\n  \"studio_link\": \"https://studio.reducto.ai/job/...\",\n  \"result\": [\n    {\n      \"title\": \"Document Title\",\n      \"authors\": [\"Author One\", \"Author Two\"]\n    }\n  ]\n}\n\nAsynchronous Extract\nPOST /reducto/extract_async\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/document.pdf\",\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"title\": {\"type\": \"string\"}\n    }\n  }\n}\n\n\nResponse:\n\n{\n  \"job_id\": \"0cdb6a50-df92-438b-875b-8b5c72d5b089\"\n}\n\nSplit Document\n\nDivide documents into logical sections based on content categories.\n\nSynchronous Split\nPOST /reducto/split\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/document.pdf\",\n  \"split_description\": [\n    {\"name\": \"abstract\", \"description\": \"The abstract section\"},\n    {\"name\": \"introduction\", \"description\": \"The introduction section\"},\n    {\"name\": \"conclusion\", \"description\": \"The conclusion section\"}\n  ]\n}\n\n\nResponse:\n\n{\n  \"usage\": {\n    \"num_pages\": 15,\n    \"credits\": 15.0\n  },\n  \"result\": {\n    \"section_mapping\": {\n      \"abstract\": [1],\n      \"introduction\": [1, 2],\n      \"conclusion\": [14, 15]\n    },\n    \"splits\": [\n      {\n        \"name\": \"abstract\",\n        \"pages\": [1],\n        \"conf\": \"high\"\n      }\n    ]\n  }\n}\n\nAsynchronous Split\nPOST /reducto/split_async\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/document.pdf\",\n  \"split_description\": [\n    {\"name\": \"abstract\", \"description\": \"The abstract section\"}\n  ]\n}\n\n\nResponse:\n\n{\n  \"job_id\": \"381de5fe-e162-4039-9ef9-8522fb34056b\"\n}\n\nEdit Document\n\nFill forms and modify PDF/DOCX documents with natural language instructions.\n\nSynchronous Edit\nPOST /reducto/edit\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/form.pdf\",\n  \"edit_instructions\": \"Fill in the name field with 'John Doe' and check the consent box\"\n}\n\n\nResponse:\n\n{\n  \"document_url\": \"https://presigned-url.s3.amazonaws.com/...\",\n  \"form_schema\": [...],\n  \"usage\": {\n    \"num_pages\": 2,\n    \"credits\": 2.0\n  }\n}\n\nAsynchronous Edit\nPOST /reducto/edit_async\nContent-Type: application/json\n\n{\n  \"document_url\": \"https://example.com/form.pdf\",\n  \"edit_instructions\": \"Highlight all mentions of 'important' in red\"\n}\n\n\nResponse:\n\n{\n  \"job_id\": \"575189cb-8732-429a-ba8a-06de8ee03208\"\n}\n\nUpload File\n\nUpload a document to Reducto and get a presigned URL for processing.\n\nPOST /reducto/upload\nContent-Type: application/json\n\n{}\n\n\nResponse:\n\n{\n  \"file_id\": \"reducto://18d574c7-4144-4f50-b7af-b8aba83ada5d\",\n  \"presigned_url\": \"https://prod-storage.s3.amazonaws.com/...?AWSAccessKeyId=...&Signature=...&Expires=...\"\n}\n\n\nUpload your file to the presigned_url using a PUT request, then use the file_id as document_url in parse/extract/split/edit requests.\n\nPipeline\n\nExecute pre-configured processing pipelines.\n\nPOST /reducto/pipeline\nContent-Type: application/json\n\n{\n  \"input\": \"https://example.com/document.pdf\",\n  \"pipeline_id\": \"your-pipeline-id\"\n}\n\n\nNote: pipeline_id must be a valid pipeline ID configured in your Reducto account via the Reducto Studio.\n\nResponse:\n\n{\n  \"job_id\": \"...\",\n  \"usage\": {\n    \"num_pages\": 15,\n    \"credits\": 15.0\n  },\n  \"result\": {\n    \"parse\": {...},\n    \"extract\": {...},\n    \"split\": {...},\n    \"edit\": {...}\n  }\n}\n\nJobs\nList Jobs\nGET /reducto/jobs\n\n\nResponse:\n\n{\n  \"jobs\": [\n    {\n      \"job_id\": \"8c25561f-247a-4843-b561-1eb94c3792d1\",\n      \"status\": \"Completed\",\n      \"type\": \"Parse\",\n      \"created_at\": \"2026-02-27T23:11:39.787917\",\n      \"num_pages\": 15,\n      \"duration\": 6.62\n    }\n  ],\n  \"next_cursor\": null\n}\n\nGet Job Status\nGET /reducto/job/{job_id}\n\n\nResponse (Pending):\n\n{\n  \"status\": \"Pending\",\n  \"result\": null,\n  \"progress\": 0.5,\n  \"reason\": null\n}\n\n\nResponse (Completed):\n\n{\n  \"status\": \"Completed\",\n  \"result\": {\n    \"job_id\": \"...\",\n    \"duration\": 17.85,\n    \"usage\": {...},\n    \"result\": {...}\n  },\n  \"progress\": null,\n  \"reason\": null\n}\n\n\nJob status values: Pending, InProgress, Completed, Failed\n\nVersion\nGET /reducto/version\n\n\nResponse:\n\n\"VERSION_GOES_HERE\"\n\nDocument URL Formats\n\nThe document_url parameter accepts several formats:\n\nPublic URL: https://example.com/document.pdf\nPresigned S3 URL: https://bucket.s3.amazonaws.com/key?...\nReducto Upload: reducto://file-id (from /upload endpoint)\nPrevious Job: jobid://job-id (reuse parsed content from previous job)\nCode Examples\nJavaScript\n// Parse a document\nconst response = await fetch(\n  'https://gateway.maton.ai/reducto/parse',\n  {\n    method: 'POST',\n    headers: {\n      'Authorization': `Bearer ${process.env.MATON_API_KEY}`,\n      'Content-Type': 'application/json'\n    },\n    body: JSON.stringify({\n      document_url: 'https://example.com/document.pdf'\n    })\n  }\n);\nconst data = await response.json();\nconsole.log(data.result.chunks);\n\nPython\nimport os\nimport requests\n\n# Extract data from a document\nresponse = requests.post(\n    'https://gateway.maton.ai/reducto/extract',\n    headers={\n        'Authorization': f'Bearer {os.environ[\"MATON_API_KEY\"]}',\n        'Content-Type': 'application/json'\n    },\n    json={\n        'document_url': 'https://example.com/document.pdf',\n        'schema': {\n            'type': 'object',\n            'properties': {\n                'title': {'type': 'string'},\n                'date': {'type': 'string'}\n            }\n        }\n    }\n)\nresult = response.json()\nprint(result['result'])\n\nAsync Job Polling\nimport os\nimport time\nimport requests\n\n# Start async parse\nresponse = requests.post(\n    'https://gateway.maton.ai/reducto/parse_async',\n    headers={\n        'Authorization': f'Bearer {os.environ[\"MATON_API_KEY\"]}',\n        'Content-Type': 'application/json'\n    },\n    json={'document_url': 'https://example.com/large-document.pdf'}\n)\njob_id = response.json()['job_id']\n\n# Poll for completion\nwhile True:\n    status = requests.get(\n        f'https://gateway.maton.ai/reducto/job/{job_id}',\n        headers={'Authorization': f'Bearer {os.environ[\"MATON_API_KEY\"]}'}\n    ).json()\n\n    print(f\"Status: {status['status']}, Progress: {status.get('progress')}\")\n\n    if status['status'] == 'Completed':\n        print(status['result'])\n        break\n    elif status['status'] == 'Failed':\n        print(f\"Failed: {status['reason']}\")\n        break\n\n    time.sleep(2)\n\nNotes\nSynchronous endpoints may timeout for large documents; use async endpoints instead\nUpload presigned URLs expire quickly; upload files immediately after calling /upload\nThe reducto:// prefix URLs from /upload can be used in subsequent parse/extract/split/edit calls\nUse jobid:// prefix to reuse parsed content from a previous job (saves processing time)\nConnection uses API_KEY authentication method (not OAuth)\nCredits are consumed based on page count and operation type\nError Handling\nStatus\tMeaning\n400\tInvalid request (missing required fields, invalid format)\n401\tInvalid or missing Maton API key\n404\tResource not found\n422\tValidation error (check response body for details)\n4xx/5xx\tPassthrough error from Reducto API\nTroubleshooting: API Key Issues\nCheck that the MATON_API_KEY environment variable is set:\necho $MATON_API_KEY\n\nVerify the API key is valid by listing connections:\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n\nTroubleshooting: Invalid App Name\n\nEnsure your URL path starts with reducto. For example:\n\nCorrect: https://gateway.maton.ai/reducto/parse\nIncorrect: https://gateway.maton.ai/parse\nResources\nReducto Documentation\nReducto API Reference\nReducto Studio\nMaton Community\nMaton Support"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/byungkyu/reducto",
    "publisherUrl": "https://clawhub.ai/byungkyu/reducto",
    "owner": "byungkyu",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/reducto",
    "downloadUrl": "https://openagent3.xyz/downloads/reducto",
    "agentUrl": "https://openagent3.xyz/skills/reducto/agent",
    "manifestUrl": "https://openagent3.xyz/skills/reducto/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/reducto/agent.md"
  }
}