skills.rest
LKB-99
LKB-99COMMUNITY
Explore all skills by this author →
GitHub

prompt-engineering

Optimize LLM prompts using chain-of-thought, few-shot, and refinement techniques.

Updated Aug 27, 2026
Search Tags:#chain-of-thought#llm#prompt-engineering#prompt-design#prompt-optimization#few-shot-learning
One-click install
npx skills add https://github.com/LKB-99/manus-auto-skills --skill prompt-engineering-lkb-99
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: prompt-engineering
Source: https://github.com/LKB-99/manus-auto-skills/tree/main/prompt-engineering
Command: npx skills add https://github.com/LKB-99/manus-auto-skills --skill prompt-engineering-lkb-99

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Advanced prompt engineering techniques to consistently elicit high-quality reasoning and outputs from LLMs, reducing manual trial-and-error.

Core Features & Use Cases

  • Chain-of-Thought prompting for transparent, step-by-step reasoning.
  • Few-shot learning workflows to bootstrap model behavior with minimal examples.
  • Prompt optimization techniques, including instruction prompts, role prompts, and negative prompts applied to coding, data analysis, and content generation.

Quick Start

Describe your goal, pick a technique (CoT, few-shot, or optimization), and craft prompts to test and refine results.

Frequently Asked Questions about prompt-engineering

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

FAQPage Schema
How do I use chain-of-thought prompting to improve LLM reasoning?▼

Chain-of-thought prompting improves LLM reasoning by instructing the model to break down complex problems into transparent, step-by-step logical sequences before generating the final output.

What is the best way to guide LLM behavior with few-shot learning?▼

Few-shot learning guides LLM behavior by providing minimal, targeted examples within the prompt to bootstrap the model's understanding of the desired task format and output style.

How do I optimize LLM prompts for coding and data analysis tasks?▼

Optimize LLM prompts for coding and data analysis by applying instruction prompts, role prompts, and negative prompts to refine model behavior and consistently elicit high-quality outputs.

Why does my LLM output require so much manual trial-and-error to get right?▼

LLM output requires manual trial-and-error when prompts lack advanced engineering techniques like chain-of-thought reasoning, few-shot examples, and structural optimization to consistently direct the model.

Do I need specific scripts or assets to start with prompt optimization?▼

You do not need specific scripts to start prompt optimization; describe your goal, pick a technique like chain-of-thought or few-shot, and craft prompts to test and refine results.

Related Skills

Explore More Software Engineering Skills→
ilamanovilamanov

create-learning-map

Generate interactive Obsidian learning maps from user-defined goals and prerequisite assessments.

Community
Advanced
Wesley1600Wesley1600

chain-of-thought

Inject XML-tagged thinking blocks into prompts for step-by-step reasoning.

Community
Advanced
jonnabiojonnabio
6

instructor

Extract structured data from LLM responses with Pydantic validation.

Community
Advanced
librefanglibrefang
10

llm-finetuning

Fine-tune large language models with LoRA and QLoRA for domain adaptation.

Official
Advanced