skills.rest
Shavakan
ShavakanCOMMUNITY
Explore all skills by this author →
GitHub

prompt-engineer

Transforms vague requests into precise, actionable LLM prompts with optimized token usage.

2|Updated Nov 4, 2025
Search Tags:#prompt engineering#technical writing#LLM#efficiency#AI optimization#content creation#prompt analysis
One-click install
npx skills add https://github.com/Shavakan/claude-marketplace --skill prompt-engineer-shavakan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: prompt-engineer
Source: https://github.com/Shavakan/claude-marketplace/tree/main/skills/prompt-engineer
Command: npx skills add https://github.com/Shavakan/claude-marketplace --skill prompt-engineer-shavakan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Crafting effective LLM prompts is an art and a science. This Skill eliminates vague, inefficient, or poorly structured prompts, ensuring your AI interactions are precise, token-efficient, and yield high-quality results. It also clarifies ambiguous writing requests before execution.

Core Features & Use Cases

  • Prompt Creation & Optimization: Builds new prompts from requirements and refines existing ones for clarity, context, and token efficiency.
  • Anti-Pattern Detection: Identifies and corrects common prompt engineering mistakes like conflicting instructions or vague success criteria.
  • Technical Writing Enforcement: Proactively clarifies ambiguous writing requests (e.g., "document this") by asking for target location, format, and audience.
  • Use Case: You're struggling to get a consistent output from an LLM. Activate this Skill to analyze your prompt, identify weaknesses, and suggest concrete improvements, transforming your vague instructions into a powerful, optimized prompt.

Quick Start

Review and optimize the attached prompt for generating marketing copy for a new product launch. Ensure it's concise and effective.

Frequently Asked Questions about prompt-engineer

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

FAQPage Schema
How do I optimize an LLM prompt for better output quality?▼

Prompt optimization resolves ambiguity and removes inefficiencies by clarifying audience, format, and success criteria, then restructuring instructions with precise delimiters and concise reasoning to yield higher-quality LLM responses with reduced token waste.

What's the best way to debug a prompt that's giving inconsistent results?▼

Prompt debugging analyzes your instructions for common anti-patterns like conflicting directives or vague success criteria, identifying weaknesses and suggesting concrete improvements to transform inconsistent outputs into reliable, deterministic results.

How do I write a technical writing request that an LLM can execute precisely?▼

Technical writing clarification proactively gathers target location, format, and audience before drafting, converting ambiguous requests like 'document this' into actionable specifications that eliminate rework and ensure consistent execution.

Can I reduce token consumption in my existing prompts?▼

Token efficiency optimization removes redundancy and unnecessary verbosity from prompts through structured output tags and concise reasoning patterns, lowering token cost while maintaining output quality and deterministic behavior.

Why do my LLM instructions keep producing different outputs?▼

Inconsistent LLM outputs stem from vague success criteria, conflicting instructions, or missing context. Prompt analysis identifies these anti-patterns and enforces structured activation protocols with deterministic reasoning to ensure reliable, repeatable results.

How do I create a new prompt from scratch that an LLM will follow consistently?▼

Prompt creation from requirements involves proactive clarification of ambiguities, structured output specifications using delimiters or XML-like tags, and practical functional requirements that transform vague needs into precise, token-efficient instructions for consistent LLM execution.

Related Skills

Explore More Content & Communication Skills→
IntegralistIntegralist
2

task

Clarify user intent through structured dialogue prompts before task execution.

Community
Basic
LudwigAJLudwigAJ

prompt-engineering-expert

Refine vague prompts into clear instructions for AI agents.

Community
Advanced
petrkindlmannpetrkindlmann
64

ai-system-testing

Validate AI features by testing prompts, tool calls, and nondeterministic outputs.

Community
Advanced
EngineerWithAIEngineerWithAI
4

llm-evaluation

Evaluate LLM applications with automated metrics, human feedback, and benchmarking.

Official
Advanced