Token导航 LogoToken导航

Agent Skill · 研究检索

legal-cog(法律齿轮)

legal-cog 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

legal-cog 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 61,288。

总安装 353周安装 15GitHub Stars 52下载 124核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:legal-cog(法律齿轮)
来源仓库:https://github.com/aaaaqwq/claude-code-skills
仓库路径:skills/legal-cog
安装命令:
npx skills add https://github.com/aaaaqwq/claude-code-skills --skill legal-cog
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/aaaaqwq/claude-code-skills --skill legal-cog

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

legal-cog 结合 CellCog SDK 生成立法级推理与法律文书。支持创建合规性强的 PDF 格式合同、协议等专业文档。集成前沿 AI 智能实现复杂法律逻辑分析与文本生成。legal-cog 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

依赖 cellcog 技能完成 SDK 初始化与 API 调用配置。需遵守相关 API 使用条款并确保输出内容经人工复核。

来源仓库内路径:skills/legal-cog

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/aaaaqwq/claude-code-skills --skill legal-cog;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

legal-cog 怎么安装?

在终端执行 npx skills add https://github.com/aaaaqwq/claude-code-skills --skill legal-cog。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

legal-cog 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

legal-cog 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

legal-cog 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

legal-cog 用的人多吗?

公开数据是累计安装 353 次,近一周安装 15 次,下载 124 次,GitHub 52 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

legal-cog 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
legal-cog

法律齿轮 · 本页

35352需要联网未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Legal Cog - AI Legal Documents Powered by CellCog

Legal demands two things: frontier-level reasoning and precision document generation. CellCog delivers both.

Legal is the frontier of human intelligence — and it's done best when powered by the frontier of AI intelligence. #1 on DeepResearch Bench (Feb 2026) for the deep reasoning that legal work requires, paired with state-of-the-art PDF generation for documents that look as professional as the thinking behind them.


Prerequisites

This skill requires the cellcog skill for SDK setup and API calls.

clawhub install cellcog

Read the cellcog skill first for SDK setup. This skill shows you what's possible.

Quick pattern (v1.0+):

result = client.create_chat(
    prompt="[your legal document request]",
    notify_session_key="agent:main:main",
    task_label="legal-task",
    chat_mode="agent"
)

Important Note

CellCog generates legal documents using frontier AI reasoning and research. However, AI-generated legal documents should be reviewed by a qualified attorney before execution — especially for high-value contracts, regulated industries, or jurisdiction-specific requirements. CellCog provides an excellent starting point that saves significant time and cost, but human legal review remains important for critical documents.


What You Can Create

Contracts & Agreements

Professional contracts with proper clause structure:

  • Freelance Agreements: "Create a freelance services agreement for a web development project"
  • Employment Contracts: "Draft an employment contract for a senior engineer in California"
  • Consulting Agreements: "Create a consulting agreement with milestone-based payments"
  • Partnership Agreements: "Draft a partnership agreement for a 60/40 equity split startup"
  • Licensing Agreements: "Create a software licensing agreement for SaaS distribution"

Example prompt:

"Create a freelance contractor agreement: Client: Acme Corp (Delaware C-Corp) Contractor: Jane Smith (Web Developer, sole proprietor) Project: E-commerce website redesign Duration: 3 months (March 1 – May 31, 2026) Payment: $15,000 (50% upfront, 50% on completion) Include: Scope of work, deliverables, payment terms, IP ownership (work-for-hire), confidentiality, non-solicitation, termination clauses, dispute resolution (arbitration). Professional legal formatting with numbered clauses."

NDAs & Confidentiality

Protect your information:

  • Mutual NDA: "Create a mutual NDA between two companies exploring a partnership"
  • Employee NDA: "Draft an employee confidentiality agreement with non-compete"
  • Investor NDA: "Create an NDA for sharing financial information with potential investors"
  • Vendor NDA: "Draft a one-way NDA for a vendor accessing our customer data"

Terms & Policies

Legal foundations for digital products:

  • Terms of Service: "Create terms of service for a SaaS platform"
  • Privacy Policy: "Draft a GDPR and CCPA-compliant privacy policy for a mobile app"
  • Cookie Policy: "Create a cookie consent policy for a European-facing website"
  • Acceptable Use Policy: "Draft an acceptable use policy for a community platform"
  • EULA: "Create an end-user license agreement for desktop software"
  • Return Policy: "Draft a refund and return policy for an e-commerce store"

Example prompt:

"Create a comprehensive privacy policy for: Company: HealthTrack (health & fitness mobile app) Data collected: Name, email, health metrics, workout data, location (optional) Third parties: Stripe (payments), Firebase (analytics), AWS (hosting) Jurisdictions: Must comply with GDPR (EU users), CCPA (California), and HIPAA (health data) Include: Data collection, use, storage, sharing, user rights, data deletion, breach notification, children's privacy (13+ only), and contact information. Professional formatting, clear language (not impenetrable legalese)."

Legal Research & Compliance

Research-powered legal intelligence:

  • Regulatory Research: "Research GDPR requirements for AI-powered SaaS products"
  • Compliance Checklists: "Create a SOC 2 compliance checklist for a startup"
  • Legal Memos: "Draft a legal memo on intellectual property considerations for AI-generated content"
  • Jurisdiction Analysis: "Compare contractor vs. employee classification rules across US states"

Startup Legal Documents

Essential documents for founders:

  • SAFE Notes: "Create a SAFE note template for a pre-seed round"
  • Founder Agreements: "Draft a co-founder agreement with vesting schedules"
  • Advisor Agreements: "Create an advisor agreement with 0.5% equity and 2-year vesting"
  • Board Resolutions: "Draft a board resolution for approving a new equity plan"

Why CellCog for Legal?

The Two Pillars

1. Intelligence — Legal work requires deep reasoning about context, jurisdiction, edge cases, and implications. CellCog's #1 ranking on DeepResearch Bench means it reasons about legal nuances at a level other AI tools can't match.

2. Document Generation — Legal documents need precise formatting, proper clause numbering, consistent terminology, and professional presentation. CellCog's state-of-the-art PDF generation produces documents that look like they came from a top law firm.

Generic AICellCog Legal Cog
Generic contract templatesJurisdiction-aware, context-specific drafting
Basic text outputProfessional PDF with proper legal formatting
Surface-level clausesDeep reasoning about edge cases and implications
One formatContracts, policies, memos, research — all from one platform

Chat Mode for Legal

ScenarioRecommended Mode
Single contract, NDA, or policy"agent"
Complex multi-document legal packages"agent"
Deep regulatory research or compliance analysis"agent team"

Use "agent" for most legal documents. CellCog handles contracts, policies, and standard legal documents excellently in agent mode.

Use "agent team" for complex legal research — multi-jurisdiction compliance analysis, regulatory deep-dives, or when the legal reasoning itself is the deliverable.


Tips for Better Legal Documents

  1. Specify jurisdiction: "A contract" is vague. "A Delaware-governed contract for California-based parties" gives CellCog the legal context it needs.
  2. Name the parties clearly: Include entity types (LLC, Corp, sole proprietor) and locations.
  3. Define the deal terms: Payment amounts, timelines, equity splits, deliverables — the more specific, the better.
  4. State what clauses matter: "Include IP assignment, non-compete, and arbitration" focuses the document.
  5. Indicate formality level: "Standard startup-friendly language" vs. "formal corporate tone" changes the output significantly.

平台分布

Codex

36.06%
按下载量换算45

Claude

31.2%
按下载量换算39

Cursor

20.95%
按下载量换算26

Gemini CLI

8.91%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills