Prompt Engineering

Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.

Provides and generates LangChain4j tool and function calling patterns: annotates methods as tools with @Tool, configures tool executors, registers tools with AiServices, validates tool parameters, and handles tool execution errors. Use when building AI agents that call tools, define function specifications, manage tool responses, or integrate external APIs with LLM-driven applications.

Provides LangChain4j patterns for implementing MCP (Model Context Protocol) servers, creating Java AI tools, exposing tool calling capabilities, and integrating MCP clients with AI services. Use when building a Java MCP server, implementing tool calling in Java, connecting LangChain4j to external MCP servers, or securing tool exposure for agent workflows.

Query-driven targeted ingest from a specific AI agent's raw history. Use this skill when the user invokes /wiki-claude, /wiki-codex, /wiki-hermes, /wiki-openclaw, /wiki-copilot, /wiki-pi — with or without a search topic. Different from wiki-history-ingest (which bulk-ingests everything new): this skill finds sessions about a SPECIFIC TOPIC in a specific agent's history and ingests just those, then returns a synthesized answer immediately usable in the current session. Primary use case: you're working in agent A and want to pull in how you solved X in agent B's history. Cross-referencing, not archiving. Also trigger on: "what did I work on in codex about X", "search my claude sessions for Y", "pull in hermes knowledge about Z", "find that conversation where I did X in codex".

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.