contract-first-decomposition

Creates upfront contracts with acceptance criteria and verification methods for tasks.

6|1|Updated Mar 5, 2026

Search Tags:#verification #decomposition #contract-first #ai-safety #task-governance #pre-task-contract

Ready to run

npx skills add https://github.com/Forexgod21/YVYC-Claude-Skills --skill contract-first-decomposition

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: contract-first-decomposition
Source: https://github.com/Forexgod21/YVYC-Claude-Skills/tree/main/agentic/contract-first-decomposition
Command: npx skills add https://github.com/Forexgod21/YVYC-Claude-Skills --skill contract-first-decomposition

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enforces a discipline where Claude commits to verifiable outcomes before starting any complex task, ensuring clear acceptance criteria and measurable success to prevent drift and misalignment.

Core Features & Use Cases

Pre-Task Contract: Claude states the task, success criteria, and verification method before starting.
Verifiability Gate: ensures each sub-task can be checked and requires decomposition if not verifiable.
Change-guarded Execution: restates acceptance criteria if the task scope shifts to avoid silent pivots.

Quick Start

Activate the Pre-Task Contract workflow before starting any complex task.

Frequently Asked Questions about contract-first-decomposition

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I make AI task outcomes verifiable before execution starts?▼

To make task outcomes verifiable, establish a pre-task contract that explicitly defines the task scope, success criteria, and verification method before initiating any complex work. This prevents silent drift and ensures alignment.

What is a pre-task contract in AI task governance?▼

A pre-task contract in task governance is a commitment framework where the AI states the task, success criteria, and verification method before execution. It ensures measurable success and prevents scope misalignment.

How do I decompose complex tasks into verifiable sub-tasks?▼

To decompose complex tasks into verifiable sub-tasks, apply a verifiability gate that checks if each sub-task can be measured. If a sub-task is not verifiable, decompose it further until it can be explicitly checked.

When should I restate acceptance criteria for changing task scope?▼

You should restate acceptance criteria whenever the task scope changes during execution. This change-guarded approach maintains alignment and produces auditable outcomes by avoiding silent pivots from the original goals.

Does contract-first decomposition work without external dependencies?▼

Yes, contract-first decomposition works without external dependencies. It is a standalone workflow discipline that enforces pre-task contracts and verifiability gates internally to govern complex AI tasks.

Why do I need verifiability gates for complex AI tasks?▼

You need verifiability gates for complex AI tasks to ensure each sub-task can be objectively checked before execution. If a sub-task fails this gate, it must be decomposed further to maintain strict task governance and measurable success.