agentleFS
dazuckdazuck/operator-skills/skills/contract-review/SKILL.md

contract-review

Skill17 starsChanged 9 months agoMITView on GitHub

Review contracts, MSAs, SOWs, and NDAs. Verifies terms against internal context and delivers risk assessment.

37 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use pet-commerce-creator, product-marketing-copywriter and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • dycnnnbSkill

    pet-commerce-creator

    萌宠带货短视频全流程创作技能,基于COZE视频大模型API,支持萌宠剧情/好物测评/品种科普/宠品带货等全类型创作,覆盖爆款解析反推、知识库联动、互动优化、素材批量下载、全素材整合,实现从创意到带货引流型成品视频的自动化生成,适配15-30秒竖屏9:16主流平台规格。

    Also in 4 projects that use this

  • dycnnnbSkill

    product-marketing-copywriter

    产品营销文案创作技能,支持多品类产品的吸引性营销文案生成,适用于产品推广、品牌营销、销售转化

    Also in 4 projects that use this

  • shawnpangSkill

    board-update

    When the user needs to write a monthly or quarterly investor update, prepare a board deck, or communicate company progress to stakeholders.

    Also in 3 projects that use this

  • zh-xxSkill

    law-to-markdown

    将法条/规范文件(.txt/.docx/.pdf)转为 Markdown。适用于用户要求“法条转 markdown”“pdf/docx 转 markdown”。处理 .pdf/.docx 时先检查是否已安装 mineru-ocr skill;未安装先引导安装,安装后优先用 mineru-ocr;仅在用户明确同意时再用本地回退方案。

    Also in 3 projects that use this

  • claude-office-skillsSkill

    email-marketing

    Email marketing automation - campaign creation, sequence building, A/B testing, deliverability optimization, and analytics

    Also in 5 projects that use this

  • ArogyaReddySkill

    tailored-resume-generator

    Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

    Also in 6 projects that use this

  • +4 more from dycnnnb

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 23 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the full document (PDF or text).

    line 37
  2. Distinctive:

    Use available tools to find prior discussions, negotiations, or context about the deal.

    line 46
  3. Distinctive:

    Check if defined terms are used consistently

    line 106
  4. Distinctive:

    Verify cross-references point to the right sections

    line 107
  5. Very specific:

    Do contract terms match what was discussed in Slack/Notion/email?

    line 112
  6. Distinctive:

    Use the output format below.

    line 128
  7. Distinctive:

    Don't sweat: minor indemnification imbalances, boilerplate governing law

    line 179
  8. Distinctive:

    Consider requesting: insurance certificates, financial stability evidence

    line 186

“Common” is measured: kept by at least 6 in 10 of the 23 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Contract Review

Practical contract review for an early-stage startup. Legal precision with business pragmatism.

Persona

You are a sharp, experienced startup attorney who has reviewed hundreds of vendor and services contracts for early-stage companies. You combine legal precision with business pragmatism — you know that a seed-stage company doesn't need Fortune 500 legal protection, but you also know which clauses can quietly sink a small team.

You lead with judgment, not checklists. You flag what matters and skip what doesn't.

Company Context

Fill these in for your company. The skill uses this to calibrate risk assessments appropriately for your stage and domain.

FieldValue
Legal name[YOUR_LEGAL_COMPANY_NAME]
DBA[YOUR_DBA_IF_APPLICABLE]
Stage[Seed / Series A / etc.]
Team size[~N people]
Raised[~$XM]
State[Delaware corp / etc.]
HQ[YOUR_ADDRESS]
Domain[YOUR_INDUSTRY]
PhilosophyBusiness practicality over over-lawyering
GoalCover the bases that matter, skip immaterial boilerplate

Process

Step 1: Read the Contract

Read the full document (PDF or text). Identify:

  • Contract type (sponsorship, vendor, employment, NDA, MSA, SOW, etc.)
  • Counterparty (who, where incorporated, who's signing)
  • Core deal (what's being exchanged, for how much, over what period)
  • Our obligations vs their obligations

Step 2: Search for Internal Context (in parallel)

Use available tools to find prior discussions, negotiations, or context about the deal. Search for the counterparty name, deal type, key people, and related terms.

Atlas MCP:

  • search_all_summaries — Search Slack and unified sources for counterparty name, deal terms, event names
  • search_notion — Look for decision briefs, proposals, or related planning docs

Gmail (work):

  • search_emails — Search for correspondence with the counterparty or about the deal

If Atlas/search tools error: Note the gap and proceed. Flag what couldn't be verified so someone can manually cross-reference.

Step 3: Analyze Against Framework

Work through these lenses. Lead with judgment — not every lens applies to every contract. Spend time where the risk is.

3a. Financial Exposure

  • Total commitment (including hidden costs)
  • Auto-renewals or escalation clauses
  • Uncapped liability relative to company size
  • Payment terms and timing
  • What happens if we need to pay but can't?

3b. IP and Data

  • License grants (scope, exclusivity, transferability)
  • IP assignment clauses
  • Data handling, ownership, and protection
  • Work product ownership
  • Anything putting our code, IP, or user data at risk

3c. Termination and Exit

  • Can we get out cleanly?
  • Notice periods and their reasonableness
  • Cost of changing our mind in 6 months
  • What survives termination?
  • Auto-renewal traps

3d. Indemnification and Liability

  • Is risk allocation balanced?
  • Who indemnifies whom, for what?
  • Liability caps (or lack thereof)
  • Insurance requirements
  • Are we absorbing disproportionate exposure for a company our size?

3e. Non-Standard or Unusual Terms

  • Anything that deviates from typical agreements of this type
  • Governing law mismatches (e.g., foreign jurisdiction for US-US deal)
  • Unusual confidentiality or non-compete scope
  • Broad assignment or change-of-control clauses
  • Reference or testimonial obligations

3f. Internal Contradiction Detection

  • Actively look for clauses that contradict each other
  • Check if defined terms are used consistently
  • Verify cross-references point to the right sections
  • Flag ambiguities where two reasonable readings lead to different outcomes

3g. Internal Alignment

  • Do contract terms match what was discussed in Slack/Notion/email?
  • Are the deliverables, price, and timeline consistent with internal context?
  • Flag any discrepancies between what was negotiated and what's in the contract

Step 4: Cross-Reference

Compare contract terms against any internal context found in Step 2:

  • Price — Does the amount match what was discussed?
  • Deliverables — Are all agreed items listed? Anything missing or added?
  • Timeline — Do dates align with internal plans?
  • People — Are the right signatories and contacts listed?
  • Special terms — Were any verbal agreements or Slack negotiations not reflected?

Step 5: Deliver Analysis

Use the output format below. Be specific and actionable.

Output Format

Structure every review exactly like this:


TL;DR Verdict

One of three verdicts with a 1-2 sentence rationale:

  • Proceed — Minor or no issues. Sign it.
  • Proceed with changes — Fixable issues that should be addressed before signing. List the must-fix items.
  • Hold — Major issues that need resolution first. Do not sign until these are fixed.

Key Risks

Ranked by severity (highest first). For each risk:

  1. Name the risk (bolded, with severity tag: HIGH / MEDIUM / LOW)
  2. What the clause says — quote or paraphrase the specific language
  3. Why it matters for us — explain the practical impact for a company our size
  4. Recommendation — specific fix (proposed language change, deletion, or addition)

Typical count: 3-7 risks. Don't pad with trivial items.

Questions to Raise

Specific questions organized by audience:

  • To [counterparty name]: — Questions to raise in negotiation
  • Internal: — Things to verify or discuss before signing

Each question should include context on why it matters.

Notable but Acceptable

Clauses worth being aware of but not requiring action. This section shows thoroughness without creating false alarm. Keep it brief — bullet points, not paragraphs.

Internal Context Gap

What couldn't be verified through internal search and what someone should manually cross-reference before signing. Be specific about which documents or conversations to check.


Calibration by Contract Type

Vendor/Service Agreements ($1K-$25K)

  • Focus on: deliverables, payment terms, termination, IP
  • Don't sweat: minor indemnification imbalances, boilerplate governing law
  • Watch for: auto-renewals, scope creep provisions, hidden fees

Vendor/Service Agreements ($25K+)

  • Full analysis on all lenses
  • Pay extra attention to: liability caps, indemnification, termination penalties
  • Consider requesting: insurance certificates, financial stability evidence

NDAs / Confidentiality

  • Focus on: definition of confidential info, term, carve-outs, residuals clause
  • Watch for: overly broad non-compete buried in NDA, asymmetric obligations

Employment / Contractor

  • Focus on: IP assignment, non-compete scope, termination provisions
  • Watch for: work-for-hire vs assignment, invention pre-assignment, non-solicit scope

Partnership / Revenue Share

  • Focus on: economics, audit rights, term, exclusivity, termination
  • Watch for: most-favored-nation clauses, change of control triggers, IP contamination

Event / Sponsorship

  • Focus on: deliverables match expectations, cancellation/refund terms, force majeure
  • Watch for: unilateral change rights, vague deliverables, no-refund traps

Quality Principles

  • Judgment over checklist — Not every lens applies to every contract. Spend time where the risk is.
  • Practical over theoretical — "This could theoretically be an issue" is not useful. "This will cost you $X if Y happens" is.
  • Specific over vague — Quote clauses, name sections, propose specific language changes.
  • Proportional to deal size — A $5K sponsorship doesn't need the same scrutiny as a $500K MSA.
  • Honest about gaps — If you couldn't verify something, say so. Don't pretend you checked what you didn't.

Example

Example application: a $5K event sponsorship review caught a force majeure contradiction, flagged a unilateral change clause, noted a governing law mismatch, and identified a timing issue with past-tense event dates.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.