Token导航 LogoToken导航

Agent Skill · 研究检索

contract-redline(合同红线)

contract-redline 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。

contract-redline 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,权限为只读;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 56,510。

总安装 449周安装 18GitHub Stars 56下载 145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:contract-redline(合同红线)
来源仓库:https://github.com/vm0-ai/vm0-skills
仓库路径:skills/contract-redline
安装命令:
npx skills add https://github.com/vm0-ai/vm0-skills --skill contract-redline
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/vm0-ai/vm0-skills --skill contract-redline

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。

contract-redline 提供基于组织谈判手册的合同逐条审阅与修订建议。适合在 Codex、Claude、Cursor、Gemini CLI 中进行 SaaS、采购或服务协议的风险排查时使用。可输出带追踪标记的替换语言、风险评级及协商话术,辅助法务决策。

需用户预先配置 playbook 文件或遵循主流商业惯例作为分析基准。强调仅作辅助参考,最终条款效力取决于签约方合意与法律管辖有效性。

来源仓库内路径:skills/contract-redline

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/vm0-ai/vm0-skills --skill contract-redline;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

contract-redline 怎么安装?

在终端执行 npx skills add https://github.com/vm0-ai/vm0-skills --skill contract-redline。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

contract-redline 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。

contract-redline 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

contract-redline 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。

contract-redline 用的人多吗?

公开数据是累计安装 449 次,近一周安装 18 次,下载 145 次,GitHub 56 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。

contract-redline 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。
  • 标注为只读权限,试用阶段不容易误改本地文件。

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。
  • 只想先试试效果、不希望它改动本地文件的人。

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
contract-redline

合同红线 · 本页

44956只读未明确通过

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

Pre-Review Setup

Organizational Playbook

Before any analysis begins, look for a negotiation playbook configured in the user's local settings. A playbook codifies the organization's preferred positions, tolerable bands, and hard limits for every major provision category.

When no playbook exists:

  • Propose building one collaboratively with the user
  • If the user wants to proceed immediately, anchor the analysis to mainstream commercial norms as your reference point

Contextual Framing

Every review must start by establishing three things:

  1. Agreement category -- Determine whether this is a SaaS subscription, professional services engagement, software license, channel partnership, procurement arrangement, or another structure. The category dictates which provisions carry the most weight.
  2. Client posture -- Establish whether the organization sits on the buying side, selling side, licensing side, or partnership side. Protective language that benefits one party harms the other.
  3. Holistic reading -- Read the entire document end-to-end before marking up any single provision. Provisions operate as an interconnected system. An aggressive indemnity clause may be counterbalanced by a strong liability cap elsewhere.

Provision-by-Provision Analysis

Liability Caps and Damage Exclusions

What to examine:

  • Total cap structure: fixed dollar figure, fee multiple, or absence of any ceiling
  • Symmetry of the cap between the parties
  • Exceptions carved out from the cap and which party they favor
  • Whether indirect, consequential, special, and punitive damages are waived
  • Mutuality of the damages waiver
  • Exceptions to the damages waiver
  • Cap measurement window: per-incident, annual, or lifetime aggregate

Typical problems:

  • Cap pegged to a small fraction of fees (for example, three months of spend on a modest-value deal)
  • One-sided exceptions that hollow out the cap for the drafter's benefit
  • Sweeping exception language like "any breach of this Agreement" that renders the cap meaningless
  • Asymmetric damages waiver leaving one party exposed to consequential loss claims

Indemnification Provisions

What to examine:

  • Reciprocity: does each side indemnify the other, or is it one-directional
  • Triggering events: IP infringement, data incidents, personal injury, warranty breaches
  • Relationship to the liability cap: subject to cap, partially capped, or unlimited
  • Procedural mechanics: timely notice, who controls the defense, settlement authority
  • Duty of the protected party to minimize harm
  • Survival period after the agreement ends

Typical problems:

  • One-directional IP indemnification when both parties contribute intellectual property
  • Catch-all "any breach" triggers that effectively eliminate the liability ceiling
  • No right for the indemnifying party to direct the legal defense
  • Open-ended survival with no time boundary

Intellectual Property Rights

What to examine:

  • Background IP ownership: each party must retain what they brought in
  • Foreground IP: who owns work product created during the engagement
  • Work-for-hire designations and whether their reach is proportionate
  • License grants: breadth, exclusivity, geographic scope, sublicense rights
  • Open source exposure
  • Feedback provisions that grant rights over suggestions or improvements

Typical problems:

  • Overbroad assignment language that could sweep in the customer's pre-existing assets
  • Work-for-hire clauses extending well beyond the specific deliverables
  • Perpetual, irrevocable feedback licenses with no practical limit
  • License scope that exceeds what the business relationship actually requires

Data Protection Provisions

What to examine:

  • Whether a Data Processing Agreement or Addendum is needed and present
  • Controller/processor role allocation
  • Sub-processor engagement rights and change-notification obligations
  • Breach reporting window (must enable the controller to satisfy the 72-hour GDPR deadline)
  • International transfer safeguards: Standard Contractual Clauses, adequacy findings, binding corporate rules
  • Data return or destruction duties upon contract end
  • Security standards and the controller's audit entitlements
  • Processing purpose restrictions

Typical problems:

  • Personal data in scope but no DPA attached
  • Unrestricted sub-processor authorization with no advance notice
  • Breach notification window that exceeds regulatory deadlines
  • No transfer protections for data crossing international borders
  • Vague or missing data deletion commitments

Duration, Renewal, and Exit

What to examine:

  • Length of the initial commitment and any renewal periods
  • Auto-renewal mechanics and the window for opting out
  • Convenience termination: availability, required notice, early exit penalties
  • Cause-based termination: what qualifies as cause, whether a cure window exists
  • Post-termination obligations: data handback, transition support, surviving provisions
  • Wind-down logistics and timeline

Typical problems:

  • Extended initial lock-in with no convenience exit
  • Auto-renewal paired with a narrow opt-out window (such as 30 days before an annual renewal)
  • Termination for cause with no opportunity to remedy the breach
  • Weak or nonexistent transition assistance language
  • Survival provisions that effectively perpetuate core obligations

Dispute Resolution and Governing Law

What to examine:

  • Applicable law and jurisdiction selection
  • Resolution pathway: courts, arbitration, mandatory mediation step
  • Litigation venue and personal jurisdiction
  • Arbitral institution, procedural rules, and seat (if arbitration applies)
  • Jury trial waiver
  • Class action waiver
  • Fee-shifting for the prevailing party

Typical problems:

  • Inconvenient or obscure venue selection
  • Compulsory arbitration under rules that advantage the drafter
  • Jury waiver without compensating procedural safeguards
  • No graduated escalation mechanism before formal proceedings

Deviation Rating System

GREEN -- Within Bounds

The provision matches or improves upon the organization's baseline position. Any variation is commercially sensible and does not meaningfully shift risk.

Illustrations:

  • Liability cap set at 18 months of fees when the baseline calls for 12 months (favorable to the buyer)
  • Mutual confidentiality term of 2 years against a 3-year baseline (shorter but reasonable)
  • Governing law in a reputable commercial jurisdiction near the preferred one

Response: Note for transparency. No negotiation warranted.

YELLOW -- Push Back

The provision sits outside the baseline but within a zone where negotiation is realistic. The position is seen in the market but is not the organization's preference. Warrants attention and discussion, though not immediate escalation.

Illustrations:

  • Liability cap at 6 months of fees against a 12-month baseline (below standard yet negotiable)
  • One-directional IP indemnification when the baseline is mutual (common but not preferred)
  • Auto-renewal opt-out of 60 days when the baseline is 90 days
  • Acceptable but non-preferred governing law jurisdiction

Response: Draft specific replacement language. Supply a fallback if the primary ask is refused. Estimate the business consequence of accepting the term as-is versus negotiating.

RED -- Escalate Immediately

The provision breaches the acceptable range, trips a defined escalation trigger, or introduces material exposure. Requires review by senior counsel, outside legal advisors, or a business decision-maker with sign-off authority.

Illustrations:

  • No liability cap at all, or no limitation of liability provision
  • Unilateral, uncapped, broadly-scoped indemnification
  • Assignment of the organization's background intellectual property
  • Personal data processing with no DPA offered
  • Unreasonable restrictive covenants or exclusivity demands
  • Hostile jurisdiction combined with mandatory arbitration

Response: Articulate the precise exposure. Offer market-standard replacement language. Quantify potential downside. Recommend the appropriate escalation path.

Crafting Effective Redlines

Principles for producing markup that advances the negotiation:

  1. Supply exact text -- Deliver language that can be inserted verbatim, not abstract guidance.
  2. Stay commercially reasonable -- Aggressive overreach slows deals. Be firm on critical protections and pragmatic elsewhere.
  3. Include professional rationale -- Attach a concise justification suitable for sharing with opposing counsel.
  4. Offer a Plan B -- For every YELLOW item, provide a secondary position in case the first request is declined.
  5. Rank by importance -- Signal which markups are essential and which are strategic asks.
  6. Match the relationship context -- Calibrate tone depending on whether the counterparty is a new vendor, a long-standing partner, or a commodity supplier.

Markup Format

Present each proposed change as follows:

**Provision**: [Section number and title]
**Existing text**: "[verbatim excerpt from the agreement]"
**Proposed replacement**: "[specific new language]"
**Justification**: [One to two sentences explaining the rationale, appropriate for external sharing]
**Importance**: [Essential / Strongly Preferred / Optional]
**Fallback**: [Alternative position if the primary request is declined]

Negotiation Prioritization

Organize all proposed markups into three tiers to guide negotiation strategy:

Tier 1 -- Non-Negotiable (Walk-Away Items)

Provisions where the organization cannot execute the agreement without resolution:

  • Absent or grossly inadequate liability protections
  • Missing data protection requirements for regulated information
  • IP terms that jeopardize core business assets
  • Clauses that conflict with the organization's regulatory obligations

Tier 2 -- High Priority (Strong Preferences)

Provisions that materially affect the risk profile but allow room for negotiation:

  • Liability cap adjustments within the acceptable band
  • Indemnification scope and reciprocity improvements
  • Flexibility around termination and exit rights
  • Audit, inspection, and compliance verification rights

Tier 3 -- Strategic Concessions (Trading Material)

Provisions that strengthen the position but can be yielded to secure more important wins:

  • Preferred governing law when the alternative is still acceptable
  • Notice period fine-tuning
  • Minor definitional refinements
  • Insurance documentation requirements

Negotiation approach: Open with Tier 1 demands. Offer Tier 3 concessions as currency to lock in Tier 2 outcomes. Never yield on Tier 1 without escalating to authorized decision-makers.

平台分布

Codex

36.29%
按下载量换算53

Claude

29.92%
按下载量换算43

Cursor

16.78%
按下载量换算24

Gemini CLI

8.14%
按下载量换算12

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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