AI agent skills for prompt engineering
Prompt skills are meta-skills: they teach the agent how to write and evaluate instructions, including its own. The useful ones insist on an eval before a rewrite, because 'this prompt feels better' is how prompt work becomes unfalsifiable. Expect them to cover the structural things — where examples go, what the model should do when it cannot comply — rather than a list of magic phrases.
People land here searching for “claude code prompt engineering skill”, “agent skill to write prompts”, “llm eval skill”.
83 prompt engineering skills Refine in search →
-
roedyrustam Skill AI Prompt Engineering ExpertExpert guide for systematic Prompt Engineering, Chain-of-Thought, few-shot prompting, structured output (JSON mode), prompt versioning, and LLM evaluation / Panduan ahli rekayasa prompt dan evaluasi LLM.
-
majiayu000 Bundle Using LLM SpecialistLLM specialist router to prompt engineering, fine-tuning, RAG, evaluation, and safety skills.
567 -
gabrielmoreira Skill Prompt Engineer 2Prompt engineering expert for chain-of-thought, few-shot learning, evaluation, and LLM optimization
17 -
whd4 Skill Prompt EngineerDesigns and optimizes prompts for LLM-powered applications, covering system prompt architecture, context management, output formatting, and evaluation.
Audited 0 -
jeffallan Bundle Prompt EngineerDesigns, optimizes, and evaluates prompts for LLMs, including structured outputs, chain-of-thought, and evaluation frameworks.
Audited 10.4k - majiayu000 Bundle LLM Engineering
Patterns for building LLM applications - prompt engineering, RAG pipelines, cost optimization, multi-model routing, and evaluation. Auto-triggers when working with AI/LLM code.
567 -
borghei Bundle Senior Prompt EngineerPrompt engineering and LLM evaluation. Use when optimizing prompts, designing prompt templates, evaluating LLM outputs, building agentic systems, implementing RAG, creating few- shot examples, or designing structured-output workflows.
-
iceflower Skill Prompt EngineeringPrompt engineering best practices for LLM-powered applications including prompt design patterns, structured output, evaluation, safety, and cost optimization. Use when building or reviewing AI-powered features that interact with LLMs.
Audited -
omer-metin Bundle Prompt EngineerExpert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when "prompt engineering, system prompt, few-shot, chain of thought, prompt design, LLM prompt, instruction tuning, prompt template, output format, prompts, llm, gpt, claude, system-prompt, few-shot, chain-of-thought, evaluation" mentioned.
128 -
onfire7777 Bundle OracleSpecialist agent for AI/ML design and evaluation. Covers prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, and cost optimization.
- majiayu000 Bundle Prompt Engineering Helper
Prompt Engineering Helper
567 -
cloudthinker-ai Skill LLM Evaluation FrameworkUse when performing llm evaluation framework — provides a structured framework for evaluating large language models (LLMs) for production use. Covers task-specific benchmarking, safety testing, cost analysis, latency measurement, prompt engineering evaluation, and comparison across models to select the optimal LLM for a given use case.
7 -
ashutoshsrivastava17 Skill Prompt EvalEvaluate and improve prompts for LLM-based features — test for quality, consistency, safety, edge cases, and cost efficiency. Compare prompt variants with structured evaluation criteria. TRIGGER when: user says /prompt-eval, "prompt evaluation", "evaluate prompt", "prompt testing", "prompt quality", or "prompt review".
-
danstrem2 Skill Prompt EngineerExpert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when: prompt engineering, system prompt, few-shot, chain of thought, prompt design.
2 -
martinholovsky Bundle Prompt EngineeringExpert skill for prompt engineering and task routing/orchestration. Covers secure prompt construction, injection prevention, multi-step task orchestration, and LLM output validation for JARVIS AI assistant.
-
diegosouzapw Bundle Prompt Engineer 3Use when designing prompts for LLMs, optimizing model performance, building evaluation frameworks, or implementing advanced prompting techniques like chain-of-thought, few-shot learning, or structured outputs.
54 - majiayu000 Bundle Prompt Engineer 9
Use when designing prompts for LLMs, optimizing model performance, building evaluation frameworks, or implementing advanced prompting techniques like chain-of-thought, few-shot learning, or structured outputs.
567 - majiayu000 Bundle Fine Tuning 3
LLM fine-tuning and prompt-tuning techniques
567 - majiayu000 Bundle LLM Evaluation 5
LLM testing and evaluation tools including promptfoo, trulens, and evals frameworks
567 -
jmagly-ai-writing-guide Skill Prompt EngineerProduction prompt engineering — write, iterate, and refine prompts with built-in eval loop feedback
- gabrielmoreira Bundle Prompt Engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.
17 - majiayu000 Bundle Prompt Evaluation
Prompt testing, metrics, and A/B testing frameworks
567 -
techwavedev Skill Prompt EngineeringExpert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.
-
arjumaan Skill Prompt EngineeringExpert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.
1
How to install a prompt engineering skill
- Compare the skills. Read the prompt engineering skills below — each page shows the full SKILL.md, its safety verdict, and the capabilities it declares.
- Install it. Run npx skillmds@latest add <owner>/<name>. The CLI writes the skill into every agent directory it detects, or use --agent to pin one.
- Use it. Restart your agent. It loads the skill on demand the next time you ask for something that matches — you do not have to name the skill.
What makes a good prompt engineering skill?
Prompt skills are meta-skills: they teach the agent how to write and evaluate instructions, including its own. The useful ones insist on an eval before a rewrite, because 'this prompt feels better' is how prompt work becomes unfalsifiable. Expect them to cover the structural things — where examples go, what the model should do when it cannot comply — rather than a list of magic phrases.
Every skill listed here is a plain SKILL.md file in the format Anthropic documents for Agent Skills, read unchanged by Cursor, OpenAI Codex and 60+ agents. Each passes a safety review before it is publicly listed; the verdict and declared capabilities are on every skill's page.
Frequently asked questions
What is an agent skill for prompt engineering?
Prompt skills are meta-skills: they teach the agent how to write and evaluate instructions, including its own. The useful ones insist on an eval before a rewrite, because 'this prompt feels better' is how prompt work becomes unfalsifiable. Expect them to cover the structural things — where examples go, what the model should do when it cannot comply — rather than a list of magic phrases.
Are prompt engineering skills model-specific?
Some are. Structural advice transfers across models; specifics like tool-call formats, system-prompt conventions and caching behaviour do not. A skill built around one provider's API should say which one in its description.
Which agents can use these prompt engineering skills?
Any agent that reads SKILL.md files: Claude Code, Claude.ai, Cursor, OpenAI Codex, Windsurf, OpenCode and 60+ others. The format is not vendor-specific, so the same file works everywhere — each agent just keeps its skills in a different directory, listed at /agents.
Are these prompt engineering skills free?
Yes. Searching, reading and installing skills on SkillMD is free and needs no account. Individual skills carry their own licence, shown on each skill's page.