langchain4j-ai-services-patterns
Provides declarative LangChain4j AI service patterns using interfaces and annotations. Supports Java LLM integration, conversational memory, chatbot development, and agents with tool integration and function calling.
Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Provides declarative LangChain4j AI service patterns using interfaces and annotations. Supports Java LLM integration, conversational memory, chatbot development, and agents with tool integration and function calling.
Creates web ACLs, tunes managed rules, and configures rate limits, IP and geographic rules, Bot Control, and Fraud Control. Covers client-IP recovery, spoofed-header removal, logging, and request sampling for application-layer protection.
Scans wiki pages for missing cross-references and adds wikilinks directly to the pages. Helps connect orphan pages and integrate newly ingested content into the knowledge graph.
Models game conversations as node-and-choice graphs with conditional branches and variables. Helps choose between Ink, Yarn Spinner, and a custom data-driven dialogue runner.
Addresses build size, browser stutter, battery use, and CDN or server compression for Unity web deployments. Covers resource stripping, shader variant reduction, KTX textures, quality settings, and web profiling.
Analyzes format string vulnerabilities that enable stack reads and arbitrary memory writes. Includes GOT or hook overwrites and leaks of canaries, libc addresses, and PIE addresses.
Provides vector store configuration patterns for LangChain4j RAG applications. Covers PostgreSQL/pgvector, Pinecone, MongoDB, Milvus, and Neo4j, including embedding storage and retrieval, hybrid search, and performance optimization.
Sets up cross-project log sinks and central log buckets to route logs from multiple projects, folders, or organizations. Supports read-time aggregation and troubleshooting of cross-project routing.
Provides LangChain4j patterns for implementing MCP servers and Java AI tools. Covers tool calling, MCP client integration with AI services, and securing tool exposure in agent workflows.
Guides systematic backtesting and stress testing of quantitative trading strategies. Covers parameter robustness, slippage modeling, bias prevention, avoiding overfitting, and interpreting backtest results.
Uses the OpenHue CLI to control Philips Hue lighting and scenes.
Covers XXE in XML, SVG, OOXML, SOAP, and parser-driven imports. Focuses on external entity resolution that may access files or internal network resources.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name