deepread（deepread 命令行） Skills下载安装命令和教程

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手，先确认命令和权限，再让它执行。

请帮我安装这个 Agent Skill：deepread（deepread 命令行）
来源仓库：https://github.com/sundial-org/awesome-openclaw-skills
仓库路径：skills/deepread
安装命令：
npx skills add https://github.com/sundial-org/awesome-openclaw-skills --skill deepread
安装前请先检查当前环境是否支持对应 CLI，并向我确认将要执行的命令、安装目录、联网范围和文件读写权限；确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill；本站只展示命令，不托管安装包，也不自动执行。

skills.shnpx skills

npx skills add https://github.com/sundial-org/awesome-openclaw-skills --skill deepread

简介

deepread 提供生产级文档 OCR 处理能力，支持 PDF 结构化提取与质量评估。

适合处理合同、报表等复杂文档，自动识别需人工复核的关键字段。
输出带置信度评分的 JSON 数据，显著减少人工校验工作量。
依赖本地部署环境，需确保 CUDA 和 PyTorch 版本兼容性。
deepread 属于待分类类 Skill，可作为该场景下的辅助能力补充。

SKILL.md

DeepRead - Production OCR API

OCR that never fails silently. Process PDFs and extract structured data with AI-powered confidence scoring that tells you exactly which fields need human review.

What This Skill Does

DeepRead is a production-grade document processing API that reduces human review from 100% to ~10% through intelligent quality assessment.

Core Features:

Text Extraction: Convert PDFs to clean markdown
Structured Data: Extract JSON fields with confidence scores
Quality Flags: AI determines which fields need human verification (hil_flag)
Multi-Pass Processing: Multiple validation passes for maximum accuracy
Multi-Model Consensus: Cross-validation between models for reliability
Free Tier: 2,000 pages/month (no credit card required)

Setup

1. Get Your API Key

Sign up and create an API key:

# Visit the dashboard
https://www.deepread.tech/dashboard

# Or use this direct link
https://www.deepread.tech/dashboard/?utm_source=clawdhub

Save your API key:

export DEEPREAD_API_KEY="sk_live_your_key_here"

2. Clawdbot Configuration (Optional)

Add to your clawdbot.config.json5:

{
  skills: {
    entries: {
      "deepread": {
        enabled: true,
        apiKey: "sk_live_your_key_here"
      }
    }
  }
}

3. Process Your First Document

Option A: With Webhook (Recommended)

# Upload PDF with webhook notification
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@document.pdf" \
  -F "webhook_url=https://your-app.com/webhooks/deepread"

# Returns immediately
{
  "id": "550e8400-e29b-41d4-a716-446655440000",
  "status": "queued"
}

# Your webhook receives results when processing completes (2-5 minutes)

Option B: Poll for Results

# Upload PDF without webhook
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@document.pdf"

# Returns immediately
{
  "id": "550e8400-e29b-41d4-a716-446655440000",
  "status": "queued"
}

# Poll until completed
curl https://api.deepread.tech/v1/jobs/550e8400-e29b-41d4-a716-446655440000 \
  -H "X-API-Key: $DEEPREAD_API_KEY"

Usage Examples

Basic OCR (Text Only)

Extract text as clean markdown:

# With webhook (recommended)
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@invoice.pdf" \
  -F "webhook_url=https://your-app.com/webhook"

# OR poll for completion
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@invoice.pdf"

# Then poll
curl https://api.deepread.tech/v1/jobs/JOB_ID \
  -H "X-API-Key: $DEEPREAD_API_KEY"

Response when completed:

{
  "id": "550e8400-...",
  "status": "completed",
  "result": {
    "text": "# INVOICE\n\n**Vendor:** Acme Corp\n**Total:** $1,250.00..."
  }
}

Structured Data Extraction

Extract specific fields with confidence scoring:

curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@invoice.pdf" \
  -F 'schema={
    "type": "object",
    "properties": {
      "vendor": {
        "type": "string",
        "description": "Vendor company name"
      },
      "total": {
        "type": "number",
        "description": "Total invoice amount"
      },
      "invoice_date": {
        "type": "string",
        "description": "Invoice date in MM/DD/YYYY format"
      }
    }
  }'

Response includes confidence flags:

{
  "status": "completed",
  "result": {
    "text": "# INVOICE\n\n**Vendor:** Acme Corp...",
    "data": {
      "vendor": {
        "value": "Acme Corp",
        "hil_flag": false,
        "found_on_page": 1
      },
      "total": {
        "value": 1250.00,
        "hil_flag": false,
        "found_on_page": 1
      },
      "invoice_date": {
        "value": "2024-10-??",
        "hil_flag": true,
        "reason": "Date partially obscured",
        "found_on_page": 1
      }
    },
    "metadata": {
      "fields_requiring_review": 1,
      "total_fields": 3,
      "review_percentage": 33.3
    }
  }
}

Complex Schemas (Nested Data)

Extract arrays and nested objects:

curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@invoice.pdf" \
  -F 'schema={
    "type": "object",
    "properties": {
      "vendor": {"type": "string"},
      "total": {"type": "number"},
      "line_items": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "description": {"type": "string"},
            "quantity": {"type": "number"},
            "price": {"type": "number"}
          }
        }
      }
    }
  }'

Page-by-Page Breakdown

Get per-page OCR results with quality flags:

curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@contract.pdf" \
  -F "include_pages=true"

Response:

{
  "result": {
    "text": "Combined text from all pages...",
    "pages": [
      {
        "page_number": 1,
        "text": "# Contract Agreement\n\n...",
        "hil_flag": false
      },
      {
        "page_number": 2,
        "text": "Terms and C??diti??s...",
        "hil_flag": true,
        "reason": "Multiple unrecognized characters"
      }
    ],
    "metadata": {
      "pages_requiring_review": 1,
      "total_pages": 2
      }
  }
}

When to Use This Skill

✅ Use DeepRead For:

Invoice Processing: Extract vendor, totals, line items
Receipt OCR: Parse merchant, items, totals
Contract Analysis: Extract parties, dates, terms
Form Digitization: Convert paper forms to structured data
Document Workflows: Any process requiring OCR + data extraction
Quality-Critical Apps: When you need to know which extractions are uncertain

❌ Don't Use For:

Real-time Processing: Processing takes 2-5 minutes (async workflow)
Batch >2,000 pages/month: Upgrade to PRO or SCALE tier

How It Works

Multi-Pass Pipeline

PDF → Convert → Rotate Correction → OCR → Multi-Model Validation → Extract → Done

The pipeline automatically handles:

Document rotation and orientation correction
Multi-pass validation for accuracy
Cross-model consensus for reliability
Field-level confidence scoring

Quality Review (hil_flag)

AI compares extracted text to the original image and sets hil_flag:

hil_flag: false = Clear, confident extraction → Auto-process
hil_flag: true = Uncertain extraction → Human review required

AI flags extractions when:

Text is handwritten, blurry, or low quality
Multiple possible interpretations exist
Characters are partially visible or unclear
Field not found in document

This is multimodal AI determination, not rule-based.

Advanced Features

1. Blueprints (Optimized Schemas)

Create reusable, optimized schemas for specific document types:

# List your blueprints
curl https://api.deepread.tech/v1/blueprints \
  -H "X-API-Key: $DEEPREAD_API_KEY"

# Use blueprint instead of inline schema
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@invoice.pdf" \
  -F "blueprint_id=660e8400-e29b-41d4-a716-446655440001"

Benefits:

20-30% accuracy improvement over baseline schemas
Reusable across similar documents
Versioned with rollback support

How to create blueprints:

# Create a blueprint from training data
curl -X POST https://api.deepread.tech/v1/optimize \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "utility_invoice",
    "description": "Optimized for utility invoices",
    "document_type": "invoice",
    "initial_schema": {
      "type": "object",
      "properties": {
        "vendor": {"type": "string", "description": "Vendor name"},
        "total": {"type": "number", "description": "Total amount"}
      }
    },
    "training_documents": ["doc1.pdf", "doc2.pdf", "doc3.pdf"],
    "ground_truth_data": [
      {"vendor": "Acme Power", "total": 125.50},
      {"vendor": "City Electric", "total": 89.25}
    ],
    "target_accuracy": 95.0,
    "max_iterations": 5
  }'

# Returns: {"job_id": "...", "blueprint_id": "...", "status": "pending"}

# Check optimization status
curl https://api.deepread.tech/v1/blueprints/jobs/JOB_ID \
  -H "X-API-Key: $DEEPREAD_API_KEY"

# Use blueprint (once completed)
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@invoice.pdf" \
  -F "blueprint_id=BLUEPRINT_ID"

2. Webhooks (Recommended for Production)

Get notified when processing completes instead of polling:

curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@invoice.pdf" \
  -F "webhook_url=https://your-app.com/webhooks/deepread"

Your webhook receives this payload when processing completes:

{
  "job_id": "550e8400-...",
  "status": "completed",
  "created_at": "2025-01-27T10:00:00Z",
  "completed_at": "2025-01-27T10:02:30Z",
  "result": {
    "text": "...",
    "data": {...}
  },
  "preview_url": "https://preview.deepread.tech/abc1234"
}

Benefits:

No polling required
Instant notification when done
Lower latency
Better for production workflows

3. Public Preview URLs

Share OCR results without authentication:

# Request preview URL
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@document.pdf" \
  -F "include_images=true"

# Get preview URL in response
{
  "result": {
    "text": "...",
    "data": {...}
  },
  "preview_url": "https://preview.deepread.tech/Xy9aB12"
}

Public Preview Endpoint:

# No authentication required
curl https://api.deepread.tech/v1/preview/Xy9aB12

Rate Limits & Pricing

Free Tier (No Credit Card)

2,000 pages/month
10 requests/minute
Full feature access (OCR + structured extraction + blueprints)

Paid Plans

PRO: 50,000 pages/month, 100 requests/minute @ $99/mo
SCALE: Custom volume pricing (contact sales)

Upgrade: https://www.deepread.tech/dashboard/billing?utm_source=clawdhub

Rate Limit Headers

Every response includes quota information:

X-RateLimit-Limit: 2000
X-RateLimit-Remaining: 1847
X-RateLimit-Used: 153
X-RateLimit-Reset: 1730419200

Best Practices

1. Use Webhooks for Production

✅ Recommended: Webhook notifications

curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@document.pdf" \
  -F "webhook_url=https://your-app.com/webhook"

Only use polling if:

Testing/development
Cannot expose a webhook endpoint
Need synchronous response

2. Schema Design

✅ Good: Descriptive field descriptions

{
  "vendor": {
    "type": "string",
    "description": "Vendor company name. Usually in header or top-left of invoice."
  }
}

❌ Bad: No description

{
  "vendor": {"type": "string"}
}

3. Polling Strategy (If Needed)

Only if you can't use webhooks, poll every 5-10 seconds:

import time
import requests

def wait_for_result(job_id, api_key):
    while True:
        response = requests.get(
            f"https://api.deepread.tech/v1/jobs/{job_id}",
            headers={"X-API-Key": api_key}
        )
        result = response.json()

        if result["status"] == "completed":
            return result["result"]
        elif result["status"] == "failed":
            raise Exception(f"Job failed: {result.get('error')}")

        time.sleep(5)

4. Handling Quality Flags

Separate confident fields from uncertain ones:

def process_extraction(data):
    confident = {}
    needs_review = []

    for field, field_data in data.items():
        if field_data["hil_flag"]:
            needs_review.append({
                "field": field,
                "value": field_data["value"],
                "reason": field_data.get("reason")
            })
        else:
            confident[field] = field_data["value"]

    # Auto-process confident fields
    save_to_database(confident)

    # Send uncertain fields to review queue
    if needs_review:
        send_to_review_queue(needs_review)

Troubleshooting

Error: `quota_exceeded`

{"detail": "Monthly page quota exceeded"}

Solution: Upgrade to PRO or wait until next billing cycle.

Error: `invalid_schema`

{"detail": "Schema must be valid JSON Schema"}

Solution: Ensure schema is valid JSON and includes type and properties.

Error: `file_too_large`

{"detail": "File size exceeds 50MB limit"}

Solution: Compress PDF or split into smaller files.

Job Status: `failed`

{"status": "failed", "error": "PDF could not be processed"}

Common causes:

Corrupted PDF file
Password-protected PDF
Unsupported PDF version
Image quality too low for OCR

Example Schema Templates

Invoice Schema

{
  "type": "object",
  "properties": {
    "invoice_number": {
      "type": "string",
      "description": "Unique invoice ID"
    },
    "invoice_date": {
      "type": "string",
      "description": "Invoice date in MM/DD/YYYY format"
    },
    "vendor": {
      "type": "string",
      "description": "Vendor company name"
    },
    "total": {
      "type": "number",
      "description": "Total amount due including tax"
    },
    "line_items": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "description": {"type": "string"},
          "quantity": {"type": "number"},
          "price": {"type": "number"}
        }
      }
    }
  }
}

Receipt Schema

{
  "type": "object",
  "properties": {
    "merchant": {
      "type": "string",
      "description": "Store or merchant name"
    },
    "date": {
      "type": "string",
      "description": "Transaction date"
    },
    "total": {
      "type": "number",
      "description": "Total amount paid"
    },
    "items": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": {"type": "string"},
          "price": {"type": "number"}
        }
      }
    }
  }
}

Contract Schema

{
  "type": "object",
  "properties": {
    "parties": {
      "type": "array",
      "items": {"type": "string"},
      "description": "Names of all parties in the contract"
    },
    "effective_date": {
      "type": "string",
      "description": "Contract start date"
    },
    "term_length": {
      "type": "string",
      "description": "Duration of contract"
    },
    "termination_clause": {
      "type": "string",
      "description": "Conditions for termination"
    }
  }
}

Support & Resources

GitHub: https://github.com/deepread-tech
Issues: https://github.com/deepread-tech/deep-read-service/issues
Email: hello@deepread.tech

Important Notes

Processing Time: 2-5 minutes (async, not real-time)
Async Workflow: Use webhooks (recommended) or polling
Rate Limits: 10 req/min on free tier
File Size Limit: 50MB per file
Supported Formats: PDF, JPG, JPEG, PNG

Ready to start? Get your free API key at https://www.deepread.tech/dashboard/?utm_source=clawdhub

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明，方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用；具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.26%

按下载量换算43

Claude

29.29%

按下载量换算35

Cursor

18.59%

按下载量换算22

Gemini CLI

9.71%

按下载量换算12

安全审计

Gen Agent Trust Hub

通过

Socket

未通过

Snyk

可疑

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置，应进入高风险复核队列，默认不自动发布。

安装前确认

本站仅展示第三方公开信息，不托管安装包，不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果，不能写成本站确认安全。当前只有一个来源，正式发布前建议补源仓库或其他目录站核验。

来源信息

GitHub 仓库

github.com

/sundial-org/awesome-openclaw-skills

SKILL.md 来源

github.com

/sundial-org/awesome-openclaw-skills/tree/main/skills/deepread

skills-sh

skills.sh

/sundial-org/awesome-openclaw-skills/deepread

继续浏览同类 Skills

更多待分类 Skills（11,209）返回 Skills 目录

上一个 Skill

deepline-feedback（深层反馈）

deepline-feedback 用于处理音频、语音、转写和声音素材相关任务，适合在 Local Agent 中需要整理音频流程、转写内容或生成配音素材时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。

下一个 Skill

deepreader（deepreader 命令行）

deepreader 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息，适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。

deepread（deepread 命令行）

安装方式

简介

SKILL.md

DeepRead - Production OCR API

What This Skill Does

Setup

1. Get Your API Key

2. Clawdbot Configuration (Optional)

3. Process Your First Document

Usage Examples

Basic OCR (Text Only)

Structured Data Extraction

Complex Schemas (Nested Data)

Page-by-Page Breakdown

When to Use This Skill

✅ Use DeepRead For:

❌ Don't Use For:

How It Works

Multi-Pass Pipeline

Quality Review (hil_flag)

Advanced Features

1. Blueprints (Optimized Schemas)

2. Webhooks (Recommended for Production)

3. Public Preview URLs

Rate Limits & Pricing

Free Tier (No Credit Card)

Paid Plans

Rate Limit Headers

Best Practices

1. Use Webhooks for Production

2. Schema Design

3. Polling Strategy (If Needed)

4. Handling Quality Flags

Troubleshooting

Error: quota_exceeded

Error: invalid_schema

Error: file_too_large

Job Status: failed

Example Schema Templates

Invoice Schema

Receipt Schema

Contract Schema

Support & Resources

Important Notes

适合场景

能力概览

平台分布

安全审计

权限和风险

来源信息

继续浏览同类 Skills

Error: `quota_exceeded`

Error: `invalid_schema`

Error: `file_too_large`

Job Status: `failed`