← Back to Skills Marketplace
uday390

DeepRead Shipping Documents

by DeepRead.tech · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
35
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install deepread-shipping-docs
Description
Extract structured data from bills of lading, packing lists, and shipping manifests — shipper, consignee, carrier, tracking, containers, line items, weights...
README (SKILL.md)

DeepRead Shipping Documents

Turn bills of lading, packing lists, and shipping manifests into clean, typed JSON — shipper, consignee, carrier, tracking/BOL numbers, containers, and itemized contents with weights — with a needs_review flag on every field. Logistics paperwork, finally machine-readable.

This skill instructs the agent to POST documents to https://api.deepread.tech and poll for results. No system files are modified.

What You Get Back

{
  "schema_version": "dp02",
  "status": "completed",
  "extraction": {
    "fields": [
      {"key": "bol_number", "value": "BOL-99213", "needs_review": false, "location": {"page": 1}},
      {"key": "carrier", "value": "Blue Ocean Freight", "needs_review": false, "location": {"page": 1}},
      {"key": "shipper", "value": "Globex Mfg, Shenzhen", "needs_review": false, "location": {"page": 1}},
      {"key": "consignee", "value": "Initech Inc, Austin TX", "needs_review": false, "location": {"page": 1}},
      {"key": "ship_date", "value": "2026-03-28", "needs_review": false, "location": {"page": 1}},
      {"key": "container_numbers", "value": ["MSKU7654321"], "needs_review": false, "location": {"page": 1}},
      {"key": "total_weight_kg", "value": 1840.5, "needs_review": false, "location": {"page": 1}},
      {"key": "items", "value": [
        {"description": "Widgets, palletized", "quantity": 40, "weight_kg": 1600.0},
        {"description": "Spare parts", "quantity": 6, "weight_kg": 240.5}
      ], "needs_review": false, "location": {"page": 1}}
    ]
  }
}

Setup

open "https://www.deepread.tech/dashboard/?utm_source=clawhub"
export DEEPREAD_API_KEY="sk_live_your_key_here"

Schema

{
  "type": "object",
  "properties": {
    "document_type":  {"type": "string", "description": "Bill of Lading, Packing List, or Manifest"},
    "bol_number":     {"type": ["string","null"], "description": "Bill of lading / tracking number"},
    "carrier":        {"type": ["string","null"], "description": "Carrier / freight company"},
    "shipper":        {"type": "string", "description": "Shipper name and origin"},
    "consignee":      {"type": "string", "description": "Consignee name and destination"},
    "ship_date":      {"type": ["string","null"], "description": "Ship date (YYYY-MM-DD)"},
    "container_numbers": {"type": "array", "items": {"type": "string"}, "description": "Container / seal numbers"},
    "total_weight_kg":{"type": ["number","null"], "description": "Total gross weight in kg"},
    "incoterms":      {"type": ["string","null"], "description": "Incoterms, e.g. FOB, CIF"},
    "items": {
      "type": "array",
      "description": "Itemized contents",
      "items": {"type": "object", "properties": {
        "description": {"type": "string", "description": "Item / commodity description"},
        "quantity":    {"type": ["number","null"], "description": "Quantity / packages"},
        "weight_kg":   {"type": ["number","null"], "description": "Weight in kg"}
      }, "required": ["description"]}
    }
  }
}

Extract (cURL)

curl -s -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "[email protected]" \
  -F 'schema={"type":"object","properties":{"bol_number":{"type":"string"},"carrier":{"type":"string"},"shipper":{"type":"string"},"consignee":{"type":"string"},"items":{"type":"array","items":{"type":"object","properties":{"description":{"type":"string"},"quantity":{"type":"number"}}}}}}'

Use Cases

  • Freight & logistics — capture BOLs and manifests into a TMS without rekeying
  • Customs & compliance — extract commodities, weights, and incoterms for filings
  • Warehouse receiving — reconcile packing lists against received goods
  • Supply-chain visibility — track containers and shipments across documents

Tips

  • container_numbers as an array handles multi-container shipments cleanly.
  • Recurring carrier format? Build a blueprint at https://www.deepread.tech/dashboard/optimizer.
  • Check needs_review — handwritten weights/quantities are the usual flags.

Related DeepRead Skills

  • deepread-invoice — commercial invoices for shipments — clawhub install uday390/deepread-invoice
  • deepread-purchase-orders — match shipments to POs — clawhub install uday390/deepread-purchase-orders
  • deepread-ocr — general extraction — clawhub install uday390/deepread-ocr

Support


Get started free: https://www.deepread.tech/dashboard/?utm_source=clawhub

Usage Guidance
Install only in a trusted ClawHub maintainer environment. Review the autoreview helper before use, prefer --no-yolo unless full unsandboxed nested review is truly needed, and run staff moderation, email, package transfer, and production migration commands only with explicit user/operator approval and the documented dry-run, backup, and audit controls.
Capability Tags
requires-sensitive-credentials
Capability Assessment
Purpose & Capability
The artifacts are coherent for ClawHub maintenance, Convex development, migrations, auth setup, performance audits, and staff moderation. High-impact actions such as user bans, role changes, package transfers, staff email, and production migrations are explicitly tied to those purposes.
Instruction Scope
Most high-impact workflows include clear gates such as explicit targets, reasons, confirmations, dry runs, backups, and audit logging. The material exception is the autoreview helper, which defaults to running nested Codex with approval and sandbox bypass flags, an overbroad authority level for a review workflow even though it is disclosed and has a --no-yolo opt-out.
Install Mechanism
I found no hidden install-time persistence or obfuscated setup in the skill directories. Package install and npx commands are presented as user/workflow steps, not concealed execution.
Credentials
Use of ClawHub admin auth, GitHub CLI, Convex tools, provider credentials, and production deployment access is expected for the stated maintainer and Convex workflows, but these should be limited to trusted operators and repos.
Persistence & Privilege
The moderation and auth flows rely on local CLI auth tokens and privileged server APIs, and the autoreview script can launch a nested full-access agent process. I did not find evidence of stealth persistence, credential theft, or exfiltration.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install deepread-shipping-docs
  3. After installation, invoke the skill by name or use /deepread-shipping-docs
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Extract shipper, consignee, carrier, BOL/tracking, containers, and itemized contents with weights from bills of lading and packing lists. Per-field confidence flags.
Metadata
Slug deepread-shipping-docs
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is DeepRead Shipping Documents?

Extract structured data from bills of lading, packing lists, and shipping manifests — shipper, consignee, carrier, tracking, containers, line items, weights... It is an AI Agent Skill for Claude Code / OpenClaw, with 35 downloads so far.

How do I install DeepRead Shipping Documents?

Run "/install deepread-shipping-docs" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is DeepRead Shipping Documents free?

Yes, DeepRead Shipping Documents is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does DeepRead Shipping Documents support?

DeepRead Shipping Documents is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created DeepRead Shipping Documents?

It is built and maintained by DeepRead.tech (@uday390); the current version is v1.0.0.

💬 Comments