Prompt Engineering

SkillAI & models

Comprehensive prompt engineering framework for designing, optimizing, and iterating LLM prompts. Use when creating prompts, optimizing existing prompts, or improving AI instructions.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Prompt Engineering skill

What this skill tells your AI

The instructions your AI receives, as published by sabahattink/antigravity-fullstack-hq in skills/prompt-engineering/SKILL.md and read by ahel’s review.

Workflow

User Request
|
+-- "Create a prompt" --> EXPLORATION PHASE
+-- "Optimize this prompt" --> OPTIMIZATION PHASE
+-- "Fix this issue" --> ANALYSIS PHASE

Phase 1: Exploration

Before creating any prompt, understand:

  • What task will this prompt accomplish?
  • Who will use it?
  • What does success look like?
  • What are the constraints?

Phase 2: Analysis

Task Classification

DimensionOptions
ComplexitySimple vs multi-step
OutputCreative vs analytical vs structured
StakesHigh vs experimental

Strategy Selection

Task TypeApproach
SimpleDirect instructions
ComplexChain-of-thought
CreativeRole setting
StructuredFormat specs + examples

Phase 3: Implementation

Version 1 - Minimal

  • Core instructions only
  • Test basic functionality

Version 2 - Enhanced

  • Add examples
  • Clarify ambiguities
  • Add constraints

Version 3+ - Optimized

  • Refine wording
  • Remove redundancy

Key Techniques

Role Setting

As an experienced code reviewer, analyze...

Chain-of-Thought

Think step-by-step:
1. First, identify...
2. Then, analyze...
3. Finally, conclude...

Few-Shot Learning

Example 1:
Input: "Great product"
Output: { "sentiment": "positive" }

Now analyze: "It was okay"

Explicit Constraints

- Limit to 3 paragraphs
- Focus on technical aspects only
- Do not include pricing

Prompt Template

## Context
[Background information]

## Role (Optional)
You are a [ROLE] with expertise in [DOMAIN].

## Task
[Clear instruction]

## Constraints
- Constraint 1
- Constraint 2

## Output Format
[Format specification]

## Examples (Optional)
[Input/Output examples]

Common Mistakes

MistakeFix
Vague instructionsBe specific
No examplesAdd 1-2 examples
Too many rulesSimplify
No format specDefine output structure

Signals

GitHub stars
30
Forks
9
Last commit
Aug 2026
Advanced
Catalog kind
skill
Gateway key
prompt-engineering-sabahattink
Source
github.com/sabahattink/antigravity-fullstack-hq