A sophisticated multi-layered prompt engineering system with analysis, optimization, customization, and validation engines for creating high-quality, domain-specific prompts
Creates optimized, domain-specific prompts using multi-layered analysis, advanced techniques like Chain-of-Thought, and validation engines for maximum AI effectiveness.
/plugin marketplace add menoncello/menon-market/plugin install studio-cc@menon-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
README.mdbun.lockclaude-test.jsexample.jsexemplos.jspackage.jsonsrc/constants.tssrc/engines/analysis-engine.tssrc/engines/customization-engine.tssrc/engines/optimization-engine.tssrc/engines/validation-engine.tssrc/index.tssrc/types.tssrc/utils/quality-utils.tssrc/utils/technique-utils.tssrc/utils/template-utils.tstest-manual.jsteste-rapido.jstests/analysis-engine.test.tstests/integration.test.tsA sophisticated multi-layered prompt engineering system that combines analysis, optimization, customization, and validation engines to create high-quality, domain-specific prompts with unparalleled precision and effectiveness.
import { AdvancedPromptCrafter } from './src/index.js';
const crafter = new AdvancedPromptCrafter();
// Analyze and improve an existing prompt
const improvedPrompt = await crafter.analyzeAndOptimize('Write a blog post about AI', {
mode: 'creative',
targetModel: 'claude-3-sonnet',
outputFormat: 'markdown',
});
// Generate a prompt from scratch
const newPrompt = await crafter.createPrompt({
task: 'Generate TypeScript code for a REST API',
domain: 'technical',
mode: 'code-generation',
requirements: {
include: ['types', 'validation', 'error-handling'],
exclude: ['external-apis'],
},
});
const crafter = new AdvancedPromptCrafter({
analysis: {
nlpProvider: 'openai',
analysisDepth: 'comprehensive',
userProfile: {
expertise: 'intermediate',
preferences: ['concise', 'structured'],
},
},
optimization: {
techniques: ['cot', 'tot', 'self-consistency'],
enableABTesting: true,
performanceThreshold: 0.85,
},
validation: {
qualityThreshold: 8.5,
enableBenchmarking: true,
metrics: ['clarity', 'specificity', 'completeness', 'efficiency'],
},
});
The Analysis Engine uses natural language processing to deconstruct prompts, identify improvement opportunities, and understand user intent through context parsing and goal clarification.
Applies advanced prompting techniques including Chain-of-Thought, Tree-of-Thought, and Self-Consistency to enhance prompt effectiveness and generate template frameworks.
Adapts prompts for specific domains, AI models, and output formats while ensuring compliance with regulatory requirements.
Evaluates prompts against quality metrics and implements continuous improvement through iterative refinement and benchmark testing.
Please read our Contributing Guide for details on our code of conduct and the process for submitting pull requests.
This project is licensed under the MIT License - see the LICENSE file for details.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.