Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub ยท Developer Tools
Reducto
Reducto document processing API integration with managed API key authentication. Parse, extract, split, and edit documents. Use this skill when users want to...
skill openclawclawhub Free
Reducto document processing API integration with managed API key authentication. Parse, extract, split, and edit documents. Use this skill when users want to...
โฌ 0 downloads โ
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md, LICENSE.txt
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- 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.
New install
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.
Upgrade existing
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.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.0.0
Provenance
- Publisher
- byungkyu
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Reducto
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.
Quick Start
# Parse a document python <<'EOF' import urllib.request, os, json data = json.dumps({'document_url': 'https://example.com/document.pdf'}).encode() req = urllib.request.Request('https://gateway.maton.ai/reducto/parse', data=data, method='POST') req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}') req.add_header('Content-Type', 'application/json') print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2)) EOF
Base URL
https://gateway.maton.ai/reducto/{native-api-path} Replace {native-api-path} with the actual Reducto API endpoint path. The gateway proxies requests to platform.reducto.ai and automatically injects your API key.
Authentication
All requests require the Maton API key in the Authorization header: Authorization: Bearer $MATON_API_KEY Environment Variable: Set your API key as MATON_API_KEY: export MATON_API_KEY="YOUR_API_KEY"
Getting Your API Key
Sign in or create an account at maton.ai Go to maton.ai/settings Copy your API key
Connection Management
Manage your Reducto API key connections at https://ctrl.maton.ai.
List Connections
python <<'EOF' import urllib.request, os, json req = urllib.request.Request('https://ctrl.maton.ai/connections?app=reducto&status=ACTIVE') req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}') print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2)) EOF
Create Connection
python <<'EOF' import urllib.request, os, json data = json.dumps({'app': 'reducto'}).encode() req = urllib.request.Request('https://ctrl.maton.ai/connections', data=data, method='POST') req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}') req.add_header('Content-Type', 'application/json') print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2)) EOF
Get Connection
python <<'EOF' import urllib.request, os, json req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}') req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}') print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2)) EOF Response: { "connection": { "connection_id": "f7579208-276c-455f-9962-4635fca739b9", "status": "ACTIVE", "creation_time": "2026-02-28T00:12:24.797884Z", "last_updated_time": "2026-02-28T00:16:13.509841Z", "url": "https://connect.maton.ai/?session_token=...", "app": "reducto", "metadata": {}, "method": "API_KEY" } } Open the returned url in a browser to enter your Reducto API key.
Delete Connection
python <<'EOF' import urllib.request, os, json req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}', method='DELETE') req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}') print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2)) EOF
Specifying Connection
If you have multiple Reducto connections, specify which one to use with the Maton-Connection header: python <<'EOF' import urllib.request, os, json req = urllib.request.Request('https://gateway.maton.ai/reducto/parse') req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}') req.add_header('Maton-Connection', 'f7579208-276c-455f-9962-4635fca739b9') print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2)) EOF If omitted, the gateway uses the default (oldest) active connection.
Parse Document
Parse a document and extract structured content (text, tables, figures). Synchronous Parse POST /reducto/parse Content-Type: application/json { "document_url": "https://example.com/document.pdf" } Response: { "job_id": "04b8aa38-7eb3-4151-98b0-dbaea71358d9", "duration": 17.85, "pdf_url": "https://...", "studio_link": "https://studio.reducto.ai/job/...", "usage": { "num_pages": 15, "credits": 15.0 }, "result": { "chunks": [ { "content": "Extracted text content...", "blocks": [...] } ] } } Asynchronous Parse For long documents, use async to avoid timeouts: POST /reducto/parse_async Content-Type: application/json { "document_url": "https://example.com/document.pdf" } Response: { "job_id": "e234ba95-410a-4dd0-8a14-743dbfc49470" } Poll the job status with GET /reducto/job/{job_id}.
Extract Data
Extract specific fields from documents using a JSON schema. Synchronous Extract POST /reducto/extract Content-Type: application/json { "document_url": "https://example.com/document.pdf", "schema": { "type": "object", "properties": { "title": {"type": "string", "description": "The document title"}, "authors": {"type": "array", "items": {"type": "string"}, "description": "List of author names"} } } } Response: { "job_id": "36f01a34-7ef6-40da-9e74-7c14902b6182", "usage": { "num_pages": 15, "num_fields": 9, "credits": 45.0 }, "studio_link": "https://studio.reducto.ai/job/...", "result": [ { "title": "Document Title", "authors": ["Author One", "Author Two"] } ] } Asynchronous Extract POST /reducto/extract_async Content-Type: application/json { "document_url": "https://example.com/document.pdf", "schema": { "type": "object", "properties": { "title": {"type": "string"} } } } Response: { "job_id": "0cdb6a50-df92-438b-875b-8b5c72d5b089" }
Split Document
Divide documents into logical sections based on content categories. Synchronous Split POST /reducto/split Content-Type: application/json { "document_url": "https://example.com/document.pdf", "split_description": [ {"name": "abstract", "description": "The abstract section"}, {"name": "introduction", "description": "The introduction section"}, {"name": "conclusion", "description": "The conclusion section"} ] } Response: { "usage": { "num_pages": 15, "credits": 15.0 }, "result": { "section_mapping": { "abstract": [1], "introduction": [1, 2], "conclusion": [14, 15] }, "splits": [ { "name": "abstract", "pages": [1], "conf": "high" } ] } } Asynchronous Split POST /reducto/split_async Content-Type: application/json { "document_url": "https://example.com/document.pdf", "split_description": [ {"name": "abstract", "description": "The abstract section"} ] } Response: { "job_id": "381de5fe-e162-4039-9ef9-8522fb34056b" }
Edit Document
Fill forms and modify PDF/DOCX documents with natural language instructions. Synchronous Edit POST /reducto/edit Content-Type: application/json { "document_url": "https://example.com/form.pdf", "edit_instructions": "Fill in the name field with 'John Doe' and check the consent box" } Response: { "document_url": "https://presigned-url.s3.amazonaws.com/...", "form_schema": [...], "usage": { "num_pages": 2, "credits": 2.0 } } Asynchronous Edit POST /reducto/edit_async Content-Type: application/json { "document_url": "https://example.com/form.pdf", "edit_instructions": "Highlight all mentions of 'important' in red" } Response: { "job_id": "575189cb-8732-429a-ba8a-06de8ee03208" }
Upload File
Upload a document to Reducto and get a presigned URL for processing. POST /reducto/upload Content-Type: application/json {} Response: { "file_id": "reducto://18d574c7-4144-4f50-b7af-b8aba83ada5d", "presigned_url": "https://prod-storage.s3.amazonaws.com/...?AWSAccessKeyId=...&Signature=...&Expires=..." } Upload your file to the presigned_url using a PUT request, then use the file_id as document_url in parse/extract/split/edit requests.
Pipeline
Execute pre-configured processing pipelines. POST /reducto/pipeline Content-Type: application/json { "input": "https://example.com/document.pdf", "pipeline_id": "your-pipeline-id" } Note: pipeline_id must be a valid pipeline ID configured in your Reducto account via the Reducto Studio. Response: { "job_id": "...", "usage": { "num_pages": 15, "credits": 15.0 }, "result": { "parse": {...}, "extract": {...}, "split": {...}, "edit": {...} } }
Jobs
List Jobs GET /reducto/jobs Response: { "jobs": [ { "job_id": "8c25561f-247a-4843-b561-1eb94c3792d1", "status": "Completed", "type": "Parse", "created_at": "2026-02-27T23:11:39.787917", "num_pages": 15, "duration": 6.62 } ], "next_cursor": null } Get Job Status GET /reducto/job/{job_id} Response (Pending): { "status": "Pending", "result": null, "progress": 0.5, "reason": null } Response (Completed): { "status": "Completed", "result": { "job_id": "...", "duration": 17.85, "usage": {...}, "result": {...} }, "progress": null, "reason": null } Job status values: Pending, InProgress, Completed, Failed
Version
GET /reducto/version Response: "VERSION_GOES_HERE"
Document URL Formats
The document_url parameter accepts several formats: Public URL: https://example.com/document.pdf Presigned S3 URL: https://bucket.s3.amazonaws.com/key?... Reducto Upload: reducto://file-id (from /upload endpoint) Previous Job: jobid://job-id (reuse parsed content from previous job)
JavaScript
// Parse a document const response = await fetch( 'https://gateway.maton.ai/reducto/parse', { method: 'POST', headers: { 'Authorization': `Bearer ${process.env.MATON_API_KEY}`, 'Content-Type': 'application/json' }, body: JSON.stringify({ document_url: 'https://example.com/document.pdf' }) } ); const data = await response.json(); console.log(data.result.chunks);
Python
import os import requests # Extract data from a document response = requests.post( 'https://gateway.maton.ai/reducto/extract', headers={ 'Authorization': f'Bearer {os.environ["MATON_API_KEY"]}', 'Content-Type': 'application/json' }, json={ 'document_url': 'https://example.com/document.pdf', 'schema': { 'type': 'object', 'properties': { 'title': {'type': 'string'}, 'date': {'type': 'string'} } } } ) result = response.json() print(result['result'])
Async Job Polling
import os import time import requests # Start async parse response = requests.post( 'https://gateway.maton.ai/reducto/parse_async', headers={ 'Authorization': f'Bearer {os.environ["MATON_API_KEY"]}', 'Content-Type': 'application/json' }, json={'document_url': 'https://example.com/large-document.pdf'} ) job_id = response.json()['job_id'] # Poll for completion while True: status = requests.get( f'https://gateway.maton.ai/reducto/job/{job_id}', headers={'Authorization': f'Bearer {os.environ["MATON_API_KEY"]}'} ).json() print(f"Status: {status['status']}, Progress: {status.get('progress')}") if status['status'] == 'Completed': print(status['result']) break elif status['status'] == 'Failed': print(f"Failed: {status['reason']}") break time.sleep(2)
Notes
Synchronous endpoints may timeout for large documents; use async endpoints instead Upload presigned URLs expire quickly; upload files immediately after calling /upload The reducto:// prefix URLs from /upload can be used in subsequent parse/extract/split/edit calls Use jobid:// prefix to reuse parsed content from a previous job (saves processing time) Connection uses API_KEY authentication method (not OAuth) Credits are consumed based on page count and operation type
Error Handling
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
Troubleshooting: API Key Issues
Check that the MATON_API_KEY environment variable is set: echo $MATON_API_KEY Verify the API key is valid by listing connections: python <<'EOF' import urllib.request, os, json req = urllib.request.Request('https://ctrl.maton.ai/connections') req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}') print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2)) EOF
Troubleshooting: Invalid App Name
Ensure your URL path starts with reducto. For example: Correct: https://gateway.maton.ai/reducto/parse Incorrect: https://gateway.maton.ai/parse
Resources
Reducto Documentation Reducto API Reference Reducto Studio Maton Community Maton Support
Category context
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
1 Docs1 Files
- SKILL.md
- LICENSE.txt