shape

Convert vague user goals into testable acceptance criteria with codebase analysis.

Updated Apr 25, 2026
One-click install
npx skills add https://github.com/kurioscreative/skills --skill shape-kurioscreative
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: shape
Source: https://github.com/kurioscreative/skills/tree/main/skills/shape
Command: npx skills add https://github.com/kurioscreative/skills --skill shape-kurioscreative

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the issue of translating a high-level, unclear goal into a concrete, testable contract, enabling effective communication and execution between a human and AI agent.

Core Features & Use Cases

  • Converts Intent into Acceptance Criteria: Transforms an expressed goal into specific, machine-verifiable criteria.
  • Codebase Understanding and Context Exploration: Offers codebase analysis capabilities to ground the goal in reality.
  • Task Contract Creation: Generates a contract as a Markdown block, ready for execution by an AI agent.

Quick Start

Shape the goal "Refactor authentication process for better scalability" into a testable task contract.

Frequently Asked Questions about shape

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

FAQPage Schema
How do I convert vague software development goals into testable acceptance criteria?

To convert vague software development goals into testable acceptance criteria, you can use an agentic workflow to analyze your codebase and translate high-level intent into specific, machine-verifiable task contracts.

What is a task contract in an agentic workflow?

A task contract in an agentic workflow is a concrete, testable Markdown block that defines explicit acceptance criteria, ensuring human-to-machine handoffs have the clarity required for effective execution.

How do I clarify requirements for an AI agent before refactoring a codebase?

To clarify requirements for an AI agent before refactoring a codebase, you must transform ambiguous goals into explicit, machine-verifiable criteria grounded by analyzing the existing code structure.

Do I need an existing codebase to generate machine-testable contracts?

You do not need an existing codebase to generate machine-testable contracts, but utilizing codebase analysis capabilities helps validate and refine the acceptance criteria to ground the goal in reality.

Can I automatically validate acceptance criteria against my current codebase?

You can automatically validate acceptance criteria against your current codebase by leveraging codebase analysis features that refine the generated task contracts based on existing project context.

What's the best way to define machine-verifiable criteria for software development tasks?

The best way to define machine-verifiable criteria for software development tasks is converting expressed goals into a Markdown task contract, enabling clear communication and execution between human and AI agent.