← 返回 Skills 市场
manas-io-ai

LegalDoc AI

作者 manas-io-ai · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
3604
总下载
5
收藏
9
当前安装
1
版本数
在 OpenClaw 中安装
/install legaldoc-ai
功能描述
Automate extraction, analysis, summarization, legal research, and deadline tracking of contracts and legal documents for law firms and professionals.
使用说明 (SKILL.md)

LegalDoc AI

Version: 1.0.0
Category: Legal / Professional Services
Author: Manas AI
License: Commercial

Overview

LegalDoc AI is a comprehensive legal document automation skill that helps law firms and legal professionals streamline document review, contract analysis, legal research, and deadline management. Designed for attorneys, paralegals, and legal operations teams.

Capabilities

1. Contract Clause Extraction

Extract and analyze specific clauses from contracts:

  • Indemnification clauses
  • Limitation of liability
  • Termination provisions
  • Force majeure
  • Confidentiality/NDA terms
  • Non-compete/non-solicitation
  • Intellectual property assignments
  • Governing law & jurisdiction
  • Dispute resolution (arbitration/litigation)
  • Payment terms & penalties
  • Representations & warranties
  • Change of control provisions

2. Document Summarization

Generate executive summaries for legal documents:

  • Contract summaries with key terms highlighted
  • Case brief generation
  • Deposition summary
  • Discovery document digest
  • Regulatory filing summaries
  • M&A due diligence summaries

3. Legal Research Queries

AI-powered legal research assistance:

  • Case law search and analysis
  • Statutory interpretation
  • Regulatory guidance lookup
  • Precedent identification
  • Jurisdiction-specific research
  • Citation verification

4. Deadline Tracking

Automated legal deadline management:

  • Statute of limitations tracking
  • Filing deadline extraction
  • Court date monitoring
  • Contract milestone alerts
  • Regulatory compliance dates
  • Discovery deadlines

Commands

Clause Extraction

legaldoc extract clauses \x3Cfile_path>
legaldoc extract clauses \x3Cfile_path> --type indemnification,liability
legaldoc extract clauses \x3Cfile_path> --output json|markdown|table
legaldoc compare clauses \x3Cfile1> \x3Cfile2> --type all

Document Summary

legaldoc summarize \x3Cfile_path>
legaldoc summarize \x3Cfile_path> --type executive|detailed|bullet
legaldoc summarize \x3Cfile_path> --length short|medium|long
legaldoc summarize \x3Cfile_path> --focus obligations|risks|terms

Legal Research

legaldoc research "\x3Cquery>"
legaldoc research "\x3Cquery>" --jurisdiction CA|NY|TX|federal
legaldoc research "\x3Cquery>" --type case_law|statute|regulation
legaldoc research citations \x3Cfile_path> --verify

Deadline Management

legaldoc deadlines extract \x3Cfile_path>
legaldoc deadlines list --upcoming 30d
legaldoc deadlines add "\x3Cdescription>" --date YYYY-MM-DD --matter \x3Cmatter_id>
legaldoc deadlines alert --email \x3Caddress> --days-before 7,3,1

Document Comparison

legaldoc compare \x3Cfile1> \x3Cfile2>
legaldoc compare \x3Cfile1> \x3Cfile2> --type redline|summary|clause-by-clause
legaldoc compare versions \x3Cfile_path> --show-history

Supported File Types

  • PDF (including scanned with OCR)
  • Microsoft Word (.doc, .docx)
  • Plain text (.txt)
  • Rich Text Format (.rtf)
  • HTML documents
  • Markdown (.md)

Configuration

# ~/.legaldoc/config.yaml
default_jurisdiction: "federal"
output_format: "markdown"
ocr_enabled: true
deadline_alerts:
  enabled: true
  email: "[email protected]"
  slack_webhook: "https://hooks.slack.com/..."
  days_before: [7, 3, 1]
matter_management:
  enabled: true
  system: "clio"  # or "mycase", "practicepanther", "custom"
  api_key: "${CLIO_API_KEY}"

Environment Variables

Variable Description Required
LEGALDOC_API_KEY LegalDoc AI API key Yes
WESTLAW_API_KEY Westlaw research API (optional) No
LEXIS_API_KEY LexisNexis API (optional) No
COURTLISTENER_API_KEY CourtListener free API No
CLIO_API_KEY Clio matter management No
LEGALDOC_STORAGE_PATH Local document storage No

Data Privacy & Security

  • No document storage: Documents are processed in-memory and never stored on external servers
  • End-to-end encryption: All API communications use TLS 1.3
  • SOC 2 Type II compliant: Enterprise security standards
  • HIPAA ready: For healthcare-related legal matters
  • Attorney-client privilege: Designed to maintain privilege protections
  • Audit logging: Full audit trail of all operations

Output Formats

Clause Extraction Output (JSON)

{
  "document": "Master_Services_Agreement.pdf",
  "extracted_at": "2026-01-31T10:30:00Z",
  "clauses": [
    {
      "type": "indemnification",
      "section": "8.1",
      "page": 12,
      "text": "Client shall indemnify and hold harmless...",
      "risk_level": "high",
      "notes": "Broad indemnification with no carve-outs",
      "suggested_revision": "Consider adding carve-outs for gross negligence..."
    }
  ]
}

Summary Output (Markdown)

# Executive Summary: Master Services Agreement

**Parties:** Acme Corp (Client) ↔ TechVendor Inc (Provider)
**Effective Date:** January 1, 2026
**Term:** 3 years with auto-renewal

## Key Terms
- **Contract Value:** $2.4M over term
- **Payment:** Net 30, quarterly invoicing
- **Termination:** 90-day notice for convenience

## Risk Assessment
🔴 **High Risk:** Unlimited liability for data breaches
🟡 **Medium Risk:** Broad IP assignment clause
🟢 **Low Risk:** Standard force majeure provisions

## Critical Deadlines
- First payment due: February 1, 2026
- Annual review: December 1, 2026
- Renewal notice deadline: October 1, 2028

Integration Points

Practice Management Systems

  • Clio
  • MyCase
  • PracticePanther
  • Rocket Matter
  • CosmoLex

Document Management

  • NetDocuments
  • iManage
  • Dropbox Business
  • Google Drive
  • SharePoint

Communication

  • Email (SMTP)
  • Slack
  • Microsoft Teams
  • SMS alerts

Best Practices

  1. Always verify extracted clauses against source documents
  2. Use jurisdiction flags for research queries to ensure relevance
  3. Set up deadline alerts with multiple reminder intervals
  4. Review AI suggestions before incorporating into final documents
  5. Maintain audit logs for compliance and malpractice protection

Pricing Tiers

Tier Documents/Month Research Queries Price
Solo 50 100 $99/mo
Small Firm 200 500 $299/mo
Mid-Size 1,000 2,500 $799/mo
Enterprise Unlimited Unlimited Custom

Support

Changelog

v1.0.0 (2026-01-31)

  • Initial release
  • Contract clause extraction (12 clause types)
  • Document summarization
  • Legal research integration
  • Deadline tracking system
安全使用建议
This package is broadly consistent with a legal-document tool, but there are important inconsistencies and privacy questions to resolve before installation: - Storage vs. privacy: SKILL.md/README claim documents are "processed in-memory" and "never stored on external servers," yet the included deadline_tracker writes a local SQLite DB (~/.legaldoc/deadlines.db) and config supports local storage paths. Expect local persistence of extracted metadata; clarify whether any documents or extracts are ever sent to the skill vendor's servers and where LEGALDOC_API_KEY is used. - Environment variables & metadata mismatch: The registry snapshot you were given claims no required env vars, but SKILL.md and clawdhub.json require LEGALDOC_API_KEY (and optionally CLIO/WESTLAW/LEXIS/COURTLISTENER). Treat LEGALDOC_API_KEY as sensitive — ask the author what that key grants access to and whether it is necessary for offline/local usage. - Network behavior: The skill includes legal_research integration and lists network integrations (CourtListener, Westlaw, LexisNexis, Slack, email, SMS). Inspect execution/legal_research.py and execution/legaldoc.py for exact endpoints and ensure only intended APIs are contacted. If you need strong data control, run the skill in an isolated environment or block outbound network access and test local-only features first. - Dependencies & binaries: The code may call external binaries (pdftotext) if Python libraries are missing. Ensure required Python packages are installed from trusted sources and install any system PDF tools from your OS package manager rather than running arbitrary install scripts. - Compliance claims: The README/manifest assert SOC2/HIPAA/GDPR/compliance. Those are marketing claims unless you can verify with attestation or an enterprise on-premise deployment contract. Ask the vendor for evidence (SOC2 report, data processing agreement, where data is processed and stored). - Hardening recommendations: (1) Review legal_research.py and legaldoc.py for exact network endpoints and logging; (2) configure a dedicated service account/API key with minimal privileges; (3) set LEGALDOC_DEADLINES_DB to a location you control and inspect stored data; (4) if handling privileged client data, prefer an on-premise deployment or sandbox network to prevent unintended exfiltration; (5) request clarification from the author about the storage/processing discrepancy. If you want, I can scan the remaining truncated files (execution/legaldoc.py and legal_research.py) for outbound endpoints, secrets handling, and any other surprises — that will reduce uncertainty and may change the confidence level.
功能分析
Type: OpenClaw Skill Name: legaldoc-ai Version: 1.0.0 The skill bundle is classified as benign. It provides comprehensive legal document automation features, including document parsing, local database persistence for deadlines, and external API calls to legitimate legal research services (CourtListener). The use of `subprocess.run` for `pdftotext` and for orchestrating its own Python components (`legaldoc.py` executing `clause_extractor.py`, etc.) is a standard and legitimate practice for CLI tools. All network communications are directed to explicitly named, reputable services, and environment variables are used appropriately for API keys. The `SKILL.md` and `README.md` files are purely instructional and do not contain any prompt injection attempts or hidden malicious instructions for an AI agent. The requested permissions (`file_read`, `file_write`, `network_http`) are consistent with the skill's stated purpose and implemented functionality.
能力评估
Purpose & Capability
Name, README, SKILL.md, clawdhub.json and the included scripts (clause_extractor, document_summarizer, legal_research, deadline_tracker) are coherent with a legal document automation / research / deadline-tracking tool. Declared permissions (file_read, file_write, network_http) and required Python deps align with the stated capabilities.
Instruction Scope
SKILL.md claims 'No document storage' and that documents are processed in-memory, but the included deadline_tracker implements a persistent SQLite DB (~/.legaldoc/deadlines.db) and the config references local storage paths. SKILL.md also instructs use of webhooks, API keys (LEGALDOC_API_KEY, optional Westlaw/Lexis/CourtListener/CLIO), and alerting (email/Slack/SMS) which implies network transmission of metadata or document extracts. The skill's instructions and templates include sensitive endpoints (Slack webhook) and encourage configuring API keys — expected for integrated research/notification features, but contradict the 'no storage' and 'processed in-memory' claim.
Install Mechanism
There is no install spec (instruction-only from platform POV), but the bundle includes code and a requirements.txt listing Python libraries (pypdf, python-docx, etc.). The code falls back to calling system tools like pdftotext via subprocess if libraries are missing — this requires an external binary and could fail or prompt installs. No remote downloads or obscure URLs were found in the provided files.
Credentials
SKILL.md and clawdhub.json declare LEGALDOC_API_KEY as required (plus optional research provider keys and CLIO API key). However, the top-level registry summary provided with the evaluation lists 'Required env vars: none' and 'Primary credential: none' — that's inconsistent. The number and type of env vars requested are plausible for the advertised integrations, but the mismatch in metadata is a red flag. The skill also uses environment/config to determine storage location (LEGALDOC_DEADLINES_DB / LEGALDOC_STORAGE_PATH), which grants local file-write access.
Persistence & Privilege
The skill does not set always:true and does not request elevated platform privileges, but it persists data locally (SQLite DB in ~/.legaldoc by default) and requires file_write permission. Autonomous invocation is allowed (platform default). Combine persistence with network_http permission — the skill can store deadlines locally and also transmit data to configured integration endpoints (research APIs, Slack, email).
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install legaldoc-ai
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /legaldoc-ai 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
LegalDoc AI 1.0.0 – Initial Release - Introduces contract clause extraction supporting 12 common clause types - Adds document summarization for contracts, cases, and regulatory filings - Integrates AI-powered legal research (case law, statutes, regulation) - Includes automated deadline tracking and alerts for legal matters
元数据
Slug legaldoc-ai
版本 1.0.0
许可证
累计安装 9
当前安装数 9
历史版本数 1
常见问题

LegalDoc AI 是什么?

Automate extraction, analysis, summarization, legal research, and deadline tracking of contracts and legal documents for law firms and professionals. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 3604 次。

如何安装 LegalDoc AI?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install legaldoc-ai」即可一键安装,无需额外配置。

LegalDoc AI 是免费的吗?

是的,LegalDoc AI 完全免费(开源免费),可自由下载、安装和使用。

LegalDoc AI 支持哪些平台?

LegalDoc AI 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 LegalDoc AI?

由 manas-io-ai(@manas-io-ai)开发并维护,当前版本 v1.0.0。

💬 留言讨论