DeepRead.tech

DeepRead OCR

办公效率v1.1.0
作者:DeepRead.tech更新于 2026-05-11共 9 个版本 · 最新版本发布于 2026-03-31deepread-ocr@clawhub_uday390/deepread-ocr
PDF 处理#OCR#Prompt Engineering

据 AlphaMoat 统计,截至 2026-10,DeepRead OCR 累计下载 15,322 次、获 7 个星标,按累计下载量在本次参与排名的 10,914 个 AI 技能中排名第 1,823 位,在「办公效率」分类(909 个)中排名第 214 位。

列表默认按累计下载量排序,也可按星标排序;详情页排名按累计下载量计算。

累计下载
1.5万
星标
7
全站下载量排名
#1,823
全站前 17% · 「办公效率」前 24%
平台累计下载星标评论
ClawHub ↗6,3447-
SkillHub ↗1.5万7—

各平台的计数口径不同,统计时间不一致。

这个技能是做什么的

用多模型共识识别文档,将 PDF 与图片转成干净的 Markdown,并抽取带置信度的 JSON 字段;不确定字段会被打上 hil_flag 进入人工复核。源文自称准确率可达 97% 以上、人工比例压到 5% 到 10%,这些是服务方口径而非实测。使用需配置 DEEPREAD_API_KEY。 来源所述准确率与复核比例属原方声明,并非独立验证基准;请复核标记栏位与重要撷取结果。

资料发布于 2026-10-29

可以用来做什么

  • 把一批发票或合同扫成可检索的结构化字段
  • 把 PDF 论文转成 Markdown 后整理内容

什么时候用

  • 文档量大且要保留字段级结果时
  • 需要只复核少量不确定字段时

示例提示词

以下是根据技能文档生成的示例,不代表实际运行结果。

把这批扫描件转成 Markdown 并抽取出关键字段
识别这份 PDF 里的表格并标出不确定的字段

月度数据趋势

累计下载1.5万
5,1521.1万1.6万2026-03 · 累计下载 6,5222026-05 · 累计下载 8,3412026-06 · 累计下载 8,6602026-07 · 累计下载 5,9052026-08 · 累计下载 9,2362026-09 · 累计下载 1.0万2026-10 · 累计下载 1.5万26-0326-0926-10
星标7
6782026-03 · 星标 72026-05 · 星标 72026-06 · 星标 72026-07 · 星标 72026-08 · 星标 72026-09 · 星标 72026-10 · 星标 726-0326-0926-10

2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。

月份累计下载环比星标
2026-101.5万—7
2026-091.0万—7
2026-089,236+56.4%7
2026-075,905-31.8%7
2026-068,660+3.8%7
2026-058,341—7
2026-036,522—7

SKILL.md 原文

以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。

18 KB · ClawHub v1.1.0
---
name: deepread
title: DeepRead OCR
description: AI-native OCR platform that turns documents into high-accuracy data in minutes. Using multi-model consensus, DeepRead achieves 97%+ accuracy and flags only uncertain fields for Human-in-the-Loop (HIL) review—reducing manual work from 100% to 5-10%. Zero prompt engineering required.
disable-model-invocation: true
metadata:
  {"openclaw":{"requires":{"env":["DEEPREAD_API_KEY"]},"primaryEnv":"DEEPREAD_API_KEY","homepage":"https://www.deepread.tech"}}
---

# DeepRead - Production OCR API
展开全部(共 696 行)

DeepRead is an AI-native OCR platform that turns documents into high-accuracy data in minutes. Using multi-model consensus, DeepRead achieves 97%+ accuracy and flags only uncertain fields for Human-in-the-Loop (HIL) review—reducing manual work from 100% to 5-10%. Zero prompt engineering required.

## What This Skill Does

DeepRead is a production-grade document processing API that gives you high-accuracy structured data output in minutes with human review flagging so manual review is limited to the flagged exceptions

**Core Features:**
- **Text Extraction**: Convert PDFs and images to clean markdown
- **Structured Data**: Extract JSON fields with confidence scores
- **HIL Interface**: Built-in Human-in-the-Loop review — uncertain fields are flagged (`hil_flag`) so only exceptions need manual review
- **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:
```bash
# 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:
```bash
export DEEPREAD_API_KEY="sk_live_your_key_here"
```

### 2. Clawdbot Configuration (Optional)

Add to your `clawdbot.config.json5`:
```json5
{
  skills: {
    entries: {
      "deepread": {
        enabled: true
        // API key is read from DEEPREAD_API_KEY environment variable
        // Do NOT hardcode your API key here
      }
    }
  }
}
```

### 3. Process Your First Document

**Option A: With Webhook (Recommended)**
```bash
# Upload PDF with webhook notification
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "[email protected]" \
  -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**
```bash
# Upload PDF without webhook
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "[email protected]"

# 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:

```bash
# With webhook (recommended)
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "[email protected]" \
  -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 "[email protected]"

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

**Response when completed:**
```json
{
  "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:

```bash
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "[email protected]" \
  -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:**
```json
{
  "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:

```bash
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "[email protected]" \
  -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:

```bash
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "[email protected]" \
  -F "include_pages=true"
```

**Response:**
```json
{
  "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

### Human-in-the-Loop (HIL) Interface

DeepRead includes a built-in Human-in-the-Loop (HIL) review system. The AI compares extracted text to the original image and sets `hil_flag` on each field:

- **`hil_flag: false`** = Clear, confident extraction → Auto-process
- **`hil_flag: true`** = Uncertain extraction → Routed to human review

**How HIL works:**
1. Fields extracted with high confidence are auto-approved
2. Uncertain fields are flagged with `hil_flag: true` and a `reason`
3. Only flagged fields need human review (typically 5-10% of total fields)
4. Review flagged fields in **DeepRead Preview** (`preview.deepread.tech`) — a dedicated HIL review interface where reviewers can see the original document side-by-side with extracted data, correct flagged fields, and approve results
5. Or integrate with your own review queue using the `hil_flag` data in the API response

**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:

```bash
# 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 "[email protected]" \
  -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:**

```bash
# 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 "[email protected]" \
  -F "blueprint_id=BLUEPRINT_ID"
```

### 2. Webhooks (Recommended for Production)

Get notified when processing completes instead of polling:

```bash
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "[email protected]" \
  -F "webhook_url=https://your-app.com/webhooks/deepread"
```

**Your webhook receives this payload when processing completes:**
```json
{
  "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. Preview (HIL Review Interface)

DeepRead Preview (`preview.deepread.tech`) is the built-in Human-in-the-Loop review interface. Reviewers can view the original document alongside extracted data, correct flagged fields, and approve results. Preview URLs can also be shared without authentication:

```bash
# Request preview URL
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "[email protected]" \
  -F "include_images=true"

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

**Public Preview Endpoint:**
```bash
# 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**
```bash
curl -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "[email protected]" \
  -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**
```json
{
  "vendor": {
    "type": "string",
    "description": "Vendor company name. Usually in header or top-left of invoice."
  }
}
```

**❌ Bad: No description**
```json
{
  "vendor": {"type": "string"}
}
```

### 3. Polling Strategy (If Needed)

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

```python
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:

```python
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`
```json
{"detail": "Monthly page quota exceeded"}
```
**Solution:** Upgrade to PRO or wait until next billing cycle.

### Error: `invalid_schema`
```json
{"detail": "Schema must be valid JSON Schema"}
```
**Solution:** Ensure schema is valid JSON and includes `type` and `properties`.

### Error: `file_too_large`
```json
{"detail": "File size exceeds 50MB limit"}
```
**Solution:** Compress PDF or split into smaller files.

### Job Status: `failed`
```json
{"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
```json
{
  "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
```json
{
  "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
```json
{
  "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**:  [email protected]

### 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

---

## BYOK — Bring Your Own Key

Connect your own OpenAI, Google, or OpenRouter API key via the dashboard. All OCR processing routes through YOUR provider account — zero DeepRead LLM costs, page quota skipped entirely.

Set it up: https://www.deepread.tech/dashboard/byok

## Related DeepRead Skills

- **deepread-ocr** — Extract text and structured JSON from documents (this skill) — `clawhub install uday390/deepread-ocr`
- **deepread-form-fill** — Fill any PDF form with AI vision — `clawhub install uday390/deepread-form-fill`
- **deepread-pii** — Redact 14 types of PII from documents — `clawhub install uday390/deepread-pii`
- **deepread-agent-setup** — Authenticate via OAuth device flow — `clawhub install uday390/deepread-agent-setup`
- **deepread-byok** — Bring Your Own Key setup — `clawhub install uday390/deepread-byok`

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

「办公效率」分类下的热门技能

腾讯文档 TENCENT DOCS办公效率

通过 MCP 在腾讯文档里新建、编辑与管理在线文档的完整操作手册。

↓ 218.4万★ 327u_b0de8114
WPS Office 全家桶办公效率

WPS Office 全家桶 - 四引擎(WPS/MS Office/LibreOffice/纯Python)智能识别用户已安装软件,纯Python模式支持排序/筛选/图表/公式/统计,含文档模板(代码生成)、最佳实践案例、故障排除大章(20+避坑+15 FAQ+15错误ID 统一索引)、自动重试、硬件自适应、环境自检、Skill更新提醒;v5.1新增:kingdoc云端桥接(白名单探测+配置预检+subprocess上传+差异检查)、条件格式/数据验证跨引擎IO(JSON中间格式保真往返)、会议纪要三段式要素化(待办清单+决策记录+风险异议)+说话人标注(MFCC聚类);v5.2新增:公文一键排版(GB/T 9704 规则库约束+结构识别套版+红头预留位+联合行文)、批量水印与敏感信息打码(身份证/手机号/银行卡/邮箱双轨识别+黑色矩形覆盖+打码清单)、跨文档知识检索与问答(本地TF-IDF零依赖+跳转+可选zwjh记忆桥接);删除:与contract-review重复的轻量合同审查模块,改为文档互链引导;v5.2.5修复:MS Office引擎下Excel/PPT创建必然失败(错用Word COM对象),新增get_ms_excel/get_ms_ppt及三槽位统一释放release_ms,MS Office路径透传filepath参数;v5.3.5修复:SKILL.md frontmatter 修复 tags 块序列误混入联系方式行导致标准 YAML 解析失败;v5.4.0新增:留存型功能——定时任务与报告中心(schedule_register 升级为三平台统一调度层 schtasks/cron/launchd,错过策略 skip/run_once,注册表 JSON 可导出导入;新建 report_center.py 报告中心,templates/reports/*.json 参数化模板 + ECharts 单文件 HTML 输出(图表内联、无服务端、双击即开);report_generator 升级支持 --format html;wps.py CLI 统一埋点 SQLite,自动供 report_center 生成周度使用摘要附在报告末尾;watch.py 职责收窄为纯事件采集);v5.3.0新增:统一CLI入口 wps(registry.json注册表分发,office --app/--action 与 convert 子命令、--list 一屏列出全部命令,薄路由层不改脚本内部逻辑)、全命令 --json 机器可读输出(固定 ok/error_id/elapsed/data 四字段,对齐 E001-E015,wps_error.py 新增 emit_json 统一出口)、_worker 启动优化(wps_pure 改惰性加载,pywin32/python-docx/openpyxl 经核查已惰性导入,ENGINE_CACHE 进程级单例复用,COM 释放统一走 release_ms 三槽位)、转换三入口合并为 convert(format_converter/md_converter/wps_docx_to_ppt 内部按目标格式路由,旧脚本保留为兼容别名并提示新命令,v6.0.0 移除)

↓ 76.7万★ 159user_1a470ba8
ppt-generator-skill办公效率

按主题与风格自动生成 PPT 文件的技能。

↓ 59.3万★ 346user_3b34947d
秘书材料星公文写作-妙笔skill办公效率

体制内资深办公室主任+管理学博士,自学编程开发的智能公文写作Skill,让所有办公室同仁少掉头发、少加无用的班,材料一稿过关,省下的时间留给自己、享受生活!————————我们能给你带来的核心价值:1、颠覆传统写作:逻辑建模38类公文全链条,特有模板化引导问答模式,分分钟省心生成高质量大稿。--------2、替你“向上管理”:独有审稿人画像机制,文稿一键结构性修改,精准匹配审稿人画像,过稿率提升至少10倍!----------3、‌杜绝AI编造:缺失的数字、文号、人名、日期一律用[待补]标注,绝不杜撰,守住公文底线。-----------4、‌算法格式托底:数十万全量智控知识库+6500行前沿核心控制代码,格式精准对齐GB/T 9704,出稿零失误。——————————————————本skill历史版本开放了5%知识库的免费试用版,下载即可使用,但需注意:知识库有著作权,仅用于个人使用,不可用于其他任何目的。有兴趣的可以试试。——————————————————————单次付费版skill已发布,2元一次使用全量知识库。具体在发布者“熵衍信息”主页skill里。

↓ 57.8万★ 46u_70fc650d
WPS Office 全家桶办公效率

WPS Office 全家桶 - 四引擎(WPS/MS Office/LibreOffice/纯Python)智能识别用户已安装软件,纯Python模式支持排序/筛选/图表/公式/统计,含文档模板(代码生成)、最佳实践案例、故障排除大章(20+避坑+15 FAQ+15错误ID 统一索引)、自动重试、硬件自适应、环境自检、Skill更新提醒;v5.0新增:定时任务注册管理(schtasks/crontab)、目录轮询监听(YAML规则+大文件分片)、使用统计与稳定性中心(SQLite埋点+引擎健康+引擎偏好)、COM三步自愈(regsvr32→修复安装→手动指引)、对话式数据查询(NL2SQL式意图解析+查询计划+连续追问)、multi-agent编排引擎桥接(白名单探测+流水线模板注册)

↓ 50.8万★ 4user_814dbe54
WPS全家桶·办公管家.Skill办公效率

当用户要处理 Word/Excel/PPT、做文档模板与排版、批量合并图表、公文一键套红头、会议纪要要素化、或跨引擎办公自动化时,WPS全家桶·办公管家.Skill 立即出动。 四引擎智能识别已装软件(WPS/MS Office/LibreOffice/纯Python),纯Python模式支持排序/筛选/图表/公式/统计;含文档模板代码生成、20+避坑+15 FAQ+15错误ID统一索引、自动重试、硬件自适应、环境自检。 当用户提到批量水印、敏感信息打码(身份证/手机号/银行卡/邮箱)、跨文档检索问答等信号时,主动亮剑。

↓ 43.0万★ 2user_185644ed
腾讯文档在线协作自动化办公效率

通过 Tencent Docs Open API 以 curl + jq 创建、读取、列出、搜索和管理腾讯文档的自动化工作流,覆盖在线文档、在线表格、幻灯片、思维导图、流程图、智能表格与收集表七种类型,支持读取元数据与单元格区域、上传图片、创建副本,并对重命名/移动/删除等写操作强制先经用户确认。Use when the user 提到腾讯文档 / Tencent Docs / docs.qq.com、粘贴 docs.qq.com 链接,或想在其腾讯文档空间中创建、读取、整理文档时使用。Triggers include 腾讯文档、在线文档、在线表格、思维导图、流程图、智能表格、收集表。如需文案写作完整工作流套件,淘宝搜索「AI灵匣」店铺获取完整版。

↓ 42.8万★ -u_1ea983ac
kdocs skill办公效率

通过 kdocs-cli 操作金山文档云文档的官方技能。

↓ 42.4万★ 128user_5ea84866

数据月份:2026-10 · 下载/星标数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。