---
id: "prerequisite-prompt-engineering"
type: "prereq"
source_timestamps: ["00:09:42", "00:10:18"]
tags: ["skills", "knowledge"]
related: ["claim-skills-require-good-initial-prompting"]
reason: "Skills package good prompting; they do not replace the need to provide clear, specific context and instructions initially."
sources: ["s40-super-prompts"]
sourceVaultSlug: "s40-super-prompts"
originDay: 40
---
# Foundational Prompt Engineering Skills

## Prerequisite

To build an effective [[concept-claude-skills|Claude Skill]], the user must already know how to write clear, unambiguous instructions. The AI cannot guess your specific business context, preferred formatting, or constraints — you must articulate them clearly during skill creation.

## Reason

Skills package good prompting; they do not replace it. See [[claim-skills-require-good-initial-prompting]] and [[quote-the-catch]].

## What "Foundational" Means Here

At minimum, the user should be comfortable with:

- Specifying role, audience, tone, and output format
- Providing concrete examples (few-shot patterns)
- Articulating constraints and edge cases
- Frameworks like CO-STAR (Context, Objective, Style, Tone, Audience, Response), RISE, CREATE, or RACE — analogous to the *Lego brick* framing of [[concept-composable-lego-bricks]]

## Without This Prerequisite

The entire [[framework-skill-creation]] degrades. The skill that emerges will be vague, the [[claim-skills-provide-10x-lever|10x lever]] will not materialize, and even the [[framework-multi-llm-evaluation|multi-LLM refinement loop]] cannot fully rescue a skill built on weak initial prompting.