Skills Directory
Reusable, audited skills for BoxLang & the Ortus ecosystem.
Use this skill when consuming or exposing MCP (Model Context Protocol) servers with bx-ai: the MCP() BIF for HTTP URLs and stdio child processes (MCP( { command: [ ... ] } )), MCPResponse, discovery and tool calls, giving MCP tools to agents and models (mcpServers, withMCPServer, withMCPServers, prefix, toolFilter, closeMCPServers), stdio lifecycle, restarts, timeouts and security (allowedCommands, commandGuard), client events and stats, creating MCP servers with MCPServer(), and securing them (withRateLimit, withTrustedProxies, withAllowedIPs, withApiKeyProvider, withBasicAuth).
Use this skill when configuring or selecting named bx-ai profiles (a named provider, model, params, options and API key): the profiles setting, defaultProfile, options.profile in aiChat()/aiEmbed(), profile in aiModel()/aiAgent()/aiService(), switching an agent with withProfile() or for one run, listing with aiProfiles()/aiProfile()/aiProviders(), the embeddings defaults, and API key rules.
Use this skill when configuring AI models with aiModel(): selecting providers, the full provider list with capabilities and API key resolution, setting default parameters, using aiService(), and pre-configuring providers in module settings (provider, apiKey, defaultParams, providers).
ortus-boxlang
Use this skill when working with audio in bx-ai: text-to-speech with aiSpeak(), streaming speech with aiSpeakStream() (voice agents, telephony, browser playback), speech-to-text with aiTranscribe(), audio translation with aiTranslate(), choosing audio providers (Cartesia, ElevenLabs, OpenAI, Mistral, Gemini, Grok, Groq), voice gender keywords, and audio events and settings.
Use this skill when creating AI tools (function calling) with aiTool(): parameter descriptions, tool registries, using tools with aiChat() and agents, the aiToolRegistry() BIF (register, scanClass with @AITool annotations, built-in tool sets), aiGlobalSkills(), and best practices for tool design.
ortus-boxlang
Use this skill when connecting AI agents to a browser with bx-playwright: accessibility snapshots in ai mode with element refs (page.snapshot, ref=e12 selectors), playwright().aiTools() for bx-ai agents, aiToolDefinitions() and models.AiBrowser for other frameworks, the Playwright MCP server (bxplaywright mcp), recording BoxLang code with bxplaywright codegen, and API self-description with help().
Use this skill when building AI agents with aiAgent(): instructions, custom models, tools, skills (always-on and lazy), MCP servers, memory, fluent configuration, sub-agents and multi-agent hierarchies, streaming, middleware (logging, retry, guardrails, flight recorder), human in the loop approvals with suspend/resume, run control (cancelRun/steerRun), and gateways (aiGateway, aiGatewaySession).
Use this skill when building AI pipelines with BoxLang AI: aiMessage() templates, aiModel() steps, aiTransform() steps and extractors, aiParallel(), chaining with .to() and .transform(), the _input system variable, multi-model pipelines, streaming pipelines, and structured output in pipelines.
Use this skill when building RAG (Retrieval-Augmented Generation) systems with BoxLang AI: aiDocuments() loaders, chunking and toMemory() ingestion, aiEmbed() embeddings and providers, vector memory stores, retrieval with getRelevant(), and exposing retrieval to agents as a tool.
Use this skill when implementing memory in BoxLang AI: aiMemory() types (window, summary, session, file, cache, jdbc, hybrid, vector stores), multi-tenant isolation with userId and conversationId, the memory API, using memory with agents, and choosing the right memory type.
Use this skill when writing BoxLang AI chat code: aiChat(), aiChatAsync(), aiChatStream(), aiMessage(), params (temperature, max_tokens, model), options (provider, apiKey, returnFormat, timeout), provider selection, return formats, multi-turn conversations, normalized reasoning, and error handling.
Use this skill when integrating AI capabilities into a ColdBox application using the BoxLang AI library (bx-ai module) -- including simple chat, streaming (see coldbox-sse-streaming for first-class SSE), pipelines, agents, RAG with vector memory, document loading, tool calling, auto-scaffolding a REST API for an IAiRunnable with route( ... ).toAi(), exposing an AI Gateway over HTTP with route( ... ).toAiGateway() for platform webhooks and human-in-the-loop approvals, and injecting the AI service into handlers or models.
coldbox