Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Contract Reviewer

ASecurity

Systematic contract review assistance — clause extraction, risk flagging, and comparison — use when analyzing agreements.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsrustgosecurity

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill contract-reviewer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Contract Reviewer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Contract Reviewer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-contract-reviewer/badge)](https://www.skillsdirectory.com/skills/aicodedecode-contract-reviewer)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: contract-reviewer
description: Systematic contract review assistance — clause extraction, risk flagging, and comparison — use when analyzing agreements.
category: document-processing
---

## Overview

Contract review is pattern recognition over dense text: find the clauses that
matter (liability, termination, IP, payment), flag deviations from your
standard positions, and compare versions. This skill covers a systematic review
workflow — what to extract, what to flag, and how to stay in the proper lane
between assistance and legal advice.

## When to use

- Reviewing vendor agreements, MSAs, NDAs, or employment contracts
- Extracting key terms (dates, amounts, obligations) into structured summaries
- Comparing contract versions (redlines) clause by clause
- Building a clause library / standard positions for your organization
- Triaging a stack of contracts by risk level

## Core concepts

**Review against a playbook, not from scratch.** Define your standard positions
once (acceptable liability caps, payment terms, termination rights, governing
law preferences) — then every review is "compare to playbook, flag deviations".
Without a playbook, reviews are inconsistent and slow.

**The high-risk clause checklist.** Liability/limitation of liability,
indemnification, termination (for convenience? notice period?), IP ownership
and licensing, confidentiality scope and duration, payment terms and late
fees, warranties and disclaimers, governing law and dispute resolution,
auto-renewal, assignment/change-of-control, data protection/security
obligations. Every contract gets checked against this list — missing clauses
are as important as bad ones.

**Extract, then analyze.** First pass: pull structured facts (parties,
effective date, term, renewal, key amounts, notice addresses). Second pass:
clause-by-clause risk assessment. Structured extraction makes the analysis
comparable across contracts and auditable later.

**Redlines need three-way awareness.** Comparing v1 → v2 shows what changed;
but you also need v2 → playbook (does the change fix or worsen the deviation?).
Track both deltas, and never review a redline without the clean current draft
for context.

**Assistance, not advice.** Automated review accelerates issue-spotting; it
doesn't replace legal judgment. Flag uncertainty explicitly, route
high-risk deviations to counsel, and never present machine output as a legal
conclusion.

## Practical workflow

1. **Normalize the input:** convert to clean text/Markdown preserving clause
   numbering and structure (see pdf-to-markdown, docx-pro); confirm nothing
   was lost in conversion.
2. **Extract key terms** into a structured summary: parties, dates, term &
   renewal, financials, governing law, notice provisions.
3. **Walk the clause checklist** section by section; for each, record: present/
   absent, matches playbook / deviates (how), risk level.
4. **Flag the critical few:** unlimited liability, one-sided indemnification,
   IP assignment of your work product, auto-renewal without notice,
   termination without cause denied to you — these get escalated, not just
   noted.
5. **For redlines:** produce a clause-level diff summary (what changed, in
   whose favor, playbook impact) — not just a raw diff dump.
6. **Output a review memo:** summary of terms, issues by severity with clause
   references, suggested fallback language from the playbook, and open
   questions for counsel.

## Common pitfalls

- **Reviewing without the playbook** — every review becomes a fresh opinion;
  build the standard positions first.
- **Missing what's absent** — no limitation of liability, no termination
  clause, no data processing terms: absence is a finding, not a neutral.
- **Trusting conversion blindly** — clause numbers shifted by bad PDF
  extraction make references wrong; verify structure before analysis.
- **Over-flagging trivia** — a 40-item "issues" list where 35 are stylistic
  trains people to ignore the review; severity-rank ruthlessly.
- **Presenting analysis as legal advice** — label outputs as review assistance,
  keep counsel in the loop for decisions, know your jurisdiction's rules about
  unauthorized practice of law, and never present machine output as a legal
  conclusion.
- **No version discipline** — reviewing "the contract" without confirming
  which draft/version; always anchor to a specific document version.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →