跳到正文
cccskills
免费在 GitHub 公开

contract-review

Reviews and negotiates commercial agreements — MSAs, SOWs, order forms, NDAs, vendor and data-processing agreements — identifying material risk, proposing positions, and recommending a path rather than listing issues. Use this to review a contract before signature, prepare a negotiation position, build fallback positions and approval thresholds, or assess exposure in terms already agreed.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

  • SKILL.md3.6 KB
  • references/sources.md872 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Contract review

Not legal advice. This structures a commercial review and identifies what needs qualified counsel. Jurisdiction-specific questions, litigation, employment, financing, and M&A go to a licensed attorney.

Review in risk order

Read for these first. Everything else is negotiable detail.

  1. Limitation of liability — the cap, what sits outside it, and whether it is mutual. An uncapped indemnity or a carve-out for a broad category can exceed the contract's entire value.
  2. Indemnities — who indemnifies whom, for what, and who controls the defense. Read the scope against what you actually do; indemnifying for a use you cannot control is the trap.
  3. IP and data rights — who owns what is created, what rights each side gets to the other's data, and what survives termination. Ambiguity here surfaces years later at the worst moment.
  4. Term and termination — auto-renewal, notice windows, termination for convenience, and what happens to data and obligations afterward. Missed notice windows are the most common self-inflicted contract loss.
  5. Payment and change — when payment is due, what triggers a change order, and whether scope can move without price moving.
  6. Warranties and service levels — what you have committed to deliver, and whether operations can actually deliver it. Commitments that outrun capability are made in contracts and discovered in incidents.

Position, do not merely flag

An issues list moves the work back to the business. For each material point, state: the risk in plain terms, its realistic impact, the preferred position, an acceptable fallback, and what is a genuine walk-away.

Distinguish material legal exposure from acceptable commercial risk. Treating every deviation as a blocker trains people to route around review, which is the worst outcome available.

Make it scalable

Beyond a handful of contracts, the leverage is in the system: standard templates, a clause library with pre-approved fallbacks, thresholds below which the business signs without review, and a written escalation path. Review every contract personally and you become the bottleneck the process was meant to prevent.

Sources

references/sources.md in this skill lists the outside authorities that settle the questions here — what each one is authoritative for, and what you may do with it. Check them before answering on anything they cover, and cite what you used. Most are free to read and not free to reproduce; the use note on each is binding.

Tooling

Contract lifecycle management: Ironclad, Icertis, Agiloft, DocuSign CLM, LinkSquares, and similar. Signature alone — DocuSign, Dropbox Sign, PandaDoc — is a different and much smaller purchase.

The value in CLM is the clause library and the searchable repository, not the approval workflow. If you cannot answer "which of our contracts cap indemnity below the fee paid" in a minute, that is the gap worth buying against.

Never

  • Approve terms whose operational obligations you have not confirmed are achievable.
  • Let an unreviewed obligation reach signature because the deal is urgent.
  • Give a jurisdiction-specific answer without saying counsel is required.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Designs and audits who can reach what — authentication, authorization models, privileged access, service credentials, and joiner-mover-leaver process. Use this to design a permissions model, run an access review, reduce standing privilege, handle offboarding, set up SSO or MFA, manage service and machine credentials, or diagnose why permissions have sprawled.

中文简介正在准备中。当前显示原文说明。

cbrock84/headcount20742026年10月19日 更新

Concentrates marketing and sales effort on a named set of accounts rather than on volume — qualifying whether the model fits your economics at all, building the account list and the buying group inside each, tiering effort against account value, coordinating so the account experiences one campaign rather than several, and measuring account progression instead of leads. Use this to decide whether to run an account-based program, build one, or work out why an existing one produces activity and no pipeline.

中文简介正在准备中。当前显示原文说明。

cbrock84/headcount20742026年10月19日 更新

Gets new users from signup to first real value — signup flow, onboarding, time-to-value, and the early experience that determines whether someone becomes a user or a lapsed account. Use this to design or fix signup and onboarding, diagnose why signups do not convert to active use, reduce time-to-value, or decide what a new user must accomplish first.

中文简介正在准备中。当前显示原文说明。

cbrock84/headcount20742026年10月19日 更新

Designs orchestrator-and-subagent hierarchies for a repository — splitting agents by exclusive write surface, pairing every producer with an independent auditor, and enforcing the split with a script that runs in CI. Use this whenever the user wants to set up, expand, audit, or fix a multi-agent or subagent structure for a codebase; asks how to divide work between agents; wants agent charters, roles, or a surface map written; or is hitting agents that collide on the same files, review their own work, or drift from their remit. Also use when sizing a roster or deciding whether a new agent is justified.

中文简介正在准备中。当前显示原文说明。

cbrock84/headcount20742026年10月19日 更新

Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory exposure, or when deciding whether an AI system is fit for a consequential decision.

中文简介正在准备中。当前显示原文说明。

cbrock84/headcount20742026年10月19日 更新

Produces executive-level research — market sizing, competitor mapping, trend analysis, and strategic intelligence — grounded in cited sources with the confidence in each claim made explicit. Use this to analyze a market or industry, map competitors, evaluate a market-entry or build-versus-buy decision, produce a research brief, or assemble evidence for a decision. Also use when comparing options that need a structured, evidence-based verdict rather than an opinion.

中文简介正在准备中。当前显示原文说明。

cbrock84/headcount20742026年10月19日 更新

查看 cbrock84 的全部技能

报告此技能的问题