Agent skill · writing content · samhvw8
prompt-enhancer
Prompt engineering and optimization for AI/LLMs. Capabilities: transform unclear prompts, reduce token usage, improve structure, add constraints, optimize for specific models, backward-compatible rewrites. Actions: improve, enhance, optimize, refactor, compress prompts. Keywords: prompt engineering, prompt optimization, token efficiency, LLM prompt, AI prompt, clarity, structure, system prompt, user prompt, few-shot, chain-of-thought, instruction tuning, prompt compression, token reduction, prompt rewrite, semantic preservation. Use when: improving unclear prompts, reducing token consumption, optimizing LLM outputs, restructuring verbose requests, creating system prompts, enhancing prompt clarity.
Why this skill is useful
Provides specific techniques and structured methods for optimizing prompts that the AI wouldn't reliably generate on its own.
What it needs
About 7k tokens when loaded. Last updated 2025-12-09. 10 stars on the source repository.
What this skill does
Prompt Enhancer Skill Purpose Transform user prompts into enhanced, production-ready versions that are concise, clean, and optimally structured for AI agents and sub-agents. Includes optimization techniques for reducing LLM output token usage while maintaining semantic accuracy and backward compatibility. When to Use This Skill Use this skill when: User explicitly asks to improve, enhance, or optimize a prompt User sends an unclear, verbose, or poorly structured prompt User mentions they want better results from AI interactions User asks for help writing prompts for agents or automation User's request lacks clarity or proper structure User wants to reduce LLM output tokens or API costs User needs to optimize JSON schema for token efficiency User requests compact output format while maintaining compatibility Core Principles 1. Conciseness: Remove unnecessary words while preserving intent 2. Structure: Use clear formatting with multiple lines and logical sections 3. XML Integration: Mix natural text with XML tags for clarity and parsing 4. Direct Mission: Main task/quest/mission should NOT be wrapped in XML elements 5. Clean Output: Return ONLY the enhanced prompt - no meta-commentary Enhancement Process Input Analysis Identify the core objective Extract key requirements and constraints Detect ambiguities or missing information Recognize the intended agent or use case Task-Based Technique Selection (Optional) Evaluate if the task would benefit from specific prompting techniques: Chain-of-Thought (CoT) Use for: Complex reasoning, math problems, logical deduction, step-by-step analysis Implementation: Add instruction to "think step by step" or "show your reasoning" Chain-of-Draft Use for: Writing tasks, content creation, iterative refinement Implementation: Request initial draft, then progressive improvements Few-Shot Learning Use for: Pattern-based tasks, specific formatting, consistent outputs Implementation: Include 2-3 examples showing input-output pairs ReAct (Reas …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills samhvw8/prompt-enhancer