PR

prompt-optimizer

An automated system that immediately optimizes system prompts and agent workflows through a multi-step triage and refinement process.

Install

mkdir -p .claude/skills/prompt-optimizer && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/356" && unzip -o skill.zip -d .claude/skills/prompt-optimizer && rm skill.zip

Installs to .claude/skills/prompt-optimizer

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Invoke IMMEDIATELY via python script when user requests prompt optimization. Do NOT analyze first - invoke this skill immediately.
130 chars✓ has a “when” trigger
Beginner

Key capabilities

  • Triage prompt optimization requests to determine scope
  • Optimize single prompt files for general improvement
  • Refine multiple related prompts that interact
  • Design new prompts from requirements (greenfield)
  • Fix specific issues in existing prompts

How it works

The skill invokes a Python script to optimize system prompts. It first triages the request to determine the scope (single-prompt, ecosystem, greenfield, or problem) and then proceeds with a structured improvement workflow.

Inputs & outputs

You give it
User request for prompt optimization, existing prompt files, prompt requirements
You get back
Optimized prompt, identified scope for optimization, workflow steps

When to use prompt-optimizer

  • Improve existing system prompts
  • Optimize agent workflows and instructions
  • Develop prompts for new agent tasks
  • Refine prompts that are underperforming

About this skill

Prompt Engineer

When this skill activates, IMMEDIATELY invoke the script. The script IS the workflow.

Invocation

Start with step 1 (triage) to determine scope:

<invoke working-dir=".claude/skills/scripts" cmd="python3 -m skills.prompt_engineer.optimize --step 1" />

Then continue with determined scope:

<invoke working-dir=".claude/skills/scripts" cmd="python3 -m skills.prompt_engineer.optimize --step 2 --scope <scope>" />
ArgumentRequiredDescription
--stepYesCurrent step (1 = triage, 2-6 = workflow)
--scopeFor 2+Required for steps 2-6. Determined by step 1.

Scopes

  • single-prompt: One prompt file, general optimization
  • ecosystem: Multiple related prompts that interact
  • greenfield: No existing prompt, designing from requirements
  • problem: Existing prompt(s) with specific issue to fix

Do NOT analyze or explore first. Run the script and follow its output.

Prerequisites

python3

How it compares

This skill provides a structured, script-driven workflow for prompt optimization, offering a systematic approach compared to ad-hoc prompt adjustments.

Compared to similar skills

prompt-optimizer side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
prompt-optimizer (this skill)436moNo flagsBeginner
senior-prompt-engineer02moReviewAdvanced
llama-factory158moNo flagsAdvanced
autonomous-agent-patterns46moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

senior-prompt-engineer

CidLucas

World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture

00

llama-factory

zechenzhangAGI

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

15112

autonomous-agent-patterns

davila7

Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants.

451

guidance

davila7

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

348

senior-prompt-engineer

davila7

World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.

743

openrouter-function-calling

jeremylongshore

Implement function/tool calling with OpenRouter models. Use when building agents or structured outputs. Trigger with phrases like 'openrouter functions', 'openrouter tools', 'openrouter agent', 'function calling'.

539

Search skills

Search the agent skills registry