Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From backend-security
Invokes llm-integrator agent to generate LLM integration patterns, RAG systems, and prompt engineering solutions for a required requirement and optional pattern.
How this command is triggered — by the user, by Claude, or both
Slash command
/backend-security:llm <requirement> [pattern]sonnetThis command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
# Llm Command LLM integration patterns, RAG systems, and prompt engineering ## Arguments **$1 (Required)**: requirement **$2 (Optional)**: pattern ## Examples Invoke the llm-integrator agent with: $ARGUMENTS
LLM integration patterns, RAG systems, and prompt engineering
$1 (Required): requirement
$2 (Optional): pattern
/llm "Build RAG system for docs" rag
/llm "Implement chat interface" streaming
Invoke the llm-integrator agent with: $ARGUMENTS
npx claudepluginhub dotclaude/marketplace --plugin backend-security/promptEngineers, tests, versions, and optimizes LLM prompts using patterns like few-shot, CoT, ReAct; produces YAML specs, MD prompts, examples, test suites, evaluations, and git commits. Also supports optimize, test, compare flags.
/prompt-optimizeOptimizes input prompts for LLMs using chain-of-thought, few-shot examples, constitutional AI self-critique, and model-specific patterns for production readiness.
/rag-setupScaffolds a production-ready RAG pipeline given a data source and preferred stack. Outputs ingest.py, rag_chain.py, and an operational checklist.
/devkit.prompt-optimizeOptimizes a given prompt using advanced techniques (CoT, few-shot, constitutional AI) with model-specific formatting. Saves the optimized prompt to optimized-prompt.md and produces an enhancement report.
/create-meta-promptGenerates optimized prompts for Claude-to-Claude pipelines following a research-plan-implement workflow.