prompt-engineering-patterns

Codify prompt engineering patterns for lean, auditable multi-agent workflows.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Motium-AI/claude-code-toolkit --skill prompt-engineering-patterns-motium-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prompt-engineering-patterns
Source: https://github.com/Motium-AI/claude-code-toolkit/tree/main/config/skills/prompt-engineering-patterns
Command: npx skills add https://github.com/Motium-AI/claude-code-toolkit --skill prompt-engineering-patterns-motium-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill captures and codifies prompt-engineering patterns to help teams design lean, auditable skills and prompts, reducing token waste and avoiding prompt bloat.

Core Features & Use Cases

  • Four Buckets framework guidance for WRITE, SELECT, COMPRESS, ISOLATE.
  • Deletion Test methodology to prune irrelevant lines from prompts and SKILL.md.
  • Context Failure Diagnosis and Isolation for multi-agent prompts.
  • Auditing CLAUDE.md and designing subagent prompts for robust workflows.

Quick Start

Draft a new SKILL.md that applies the Deletion Test to a sample prompt and references the /heavy and /isolation patterns.

Frequently Asked Questions about prompt-engineering-patterns

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

FAQPage Schema
How do I reduce prompt bloat in multi-agent workflows?

To reduce prompt bloat in multi-agent workflows, apply the Deletion Test methodology to prune irrelevant lines and use context isolation patterns. This ensures prompts remain lean, auditable, and safe for deployment.

What is the Deletion Test for prompt engineering?

The Deletion Test is a prompt engineering methodology used to prune irrelevant lines from prompts and SKILL.md files. It helps teams design lean, auditable skills by systematically removing unnecessary context that does not contribute to the task.

How do I audit CLAUDE.md for prompt optimization?

To audit CLAUDE.md for prompt optimization, apply the Four Buckets framework to evaluate WRITE, SELECT, COMPRESS, and ISOLATE actions. This identifies token waste and reinforces safe, effective prompt structures.

What is the Four Buckets framework for context engineering?

The Four Buckets framework guides context engineering through WRITE, SELECT, COMPRESS, and ISOLATE actions. It provides structured guidance for designing lean prompts and managing context effectively across multi-agent workflows.

How do I diagnose context failures in multi-agent prompts?

To diagnose context failures in multi-agent prompts, apply context isolation techniques to separate concerns and identify conflicting instructions. This approach ensures robust workflow design and prevents cross-agent context contamination.

Can I use prompt engineering patterns to design new skills?

Yes, you can use prompt engineering patterns to design new skills by drafting a SKILL.md that applies the Deletion Test and references isolation patterns. This approach ensures skills are lean, audit-ready, and free of prompt bloat.