home / skills / omer-metin / skills-for-antigravity / contract-analysis

contract-analysis skill

safe

This skill helps you review contracts, extract key terms, assess risks, and build contract analysis tools using domain patterns.

npx playbooks add skill omer-metin/skills-for-antigravity --skill contract-analysis

Review the files below or copy the command above to add this skill to your agents.

Files (4)

SKILL.md

1.1 KB

---
name: contract-analysis
description: Use when reviewing contracts, extracting key terms, identifying risks, or building contract analysis tools - covers NLP approaches, clause identification, and risk scoringUse when ", " mentioned. 
---

# Contract Analysis

## Identity



## Reference System Usage

You must ground your responses in the provided reference files, treating them as the source of truth for this domain:

* **For Creation:** Always consult **`references/patterns.md`**. This file dictates *how* things should be built. Ignore generic approaches if a specific pattern exists here.
* **For Diagnosis:** Always consult **`references/sharp_edges.md`**. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.
* **For Review:** Always consult **`references/validations.md`**. This contains the strict rules and constraints. Use it to validate user inputs objectively.

**Note:** If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.

Overview

This skill helps review contracts, extract key terms, flag risky clauses, and produce structured summaries for legal or business teams. It combines NLP techniques, clause classification, and a risk-scoring framework to speed up due diligence and contract lifecycle tasks. Outputs are aligned to the provided reference patterns, failure modes, and validation rules so analyses are consistent and auditable.

How this skill works

The skill ingests contract text (PDF, DOCX, or plain text), segments content into clauses, and applies trained or rule-based classifiers to identify clause types and key provisions. It computes structured extractions (parties, dates, obligations, payment terms), assigns risk scores based on known sharp edges, and validates extracted values against the defined validation rules. Results include clause-level highlights, a risk summary, and machine-readable outputs for downstream tools.

When to use it

During contract intake to auto-extract metadata and reduce manual review time
When building a contract analysis tool that needs clause identification and risk scoring
For due diligence to surface non-standard or high-risk provisions quickly
To enforce contract authoring standards by validating clauses against rules
When converting legacy contracts into structured data for analytics

Best practices

Always ground extractions and scoring to the provided pattern and validation references for consistency
Use a hybrid approach: combine ML classifiers for recall with deterministic rules for high-precision fields
Highlight and triage clauses flagged by sharp-edge diagnostics before relying on automated remediation
Validate extracted dates, monetary amounts, and parties against the validations file to avoid false positives
Keep a human-in-the-loop for final legal decisioning on high-risk or ambiguous clauses

Example use cases

Extract termination rights, notice periods, and renewal terms across a portfolio of contracts
Score vendor agreements for indemnity and liability exposure during procurement
Build a dashboard that tracks non-standard clauses and contract compliance trends
Automate ingestion of signed agreements into a contract repository with validated metadata
Run a pre-signature check to ensure contracts meet organizational validation rules

FAQ

What data formats are supported?

The skill accepts PDFs, Word documents, and plain text; preprocessing should convert PDFs to text before clause segmentation.

How are risk scores determined?

Risk scores combine clause classification results with the known failure modes from the sharp-edges guidance and apply validation rules to weight issues.

Can I customize clause definitions and rules?

Yes. Update the pattern definitions and validation rules in the reference configuration to adapt classifiers and constraints to your policies.