Stats
Actions
Tags
From rubysmithing
AI/NLP component scaffolder and advisor for Ruby projects. Activates on any mention of: LLM chat, chatbot, agent, tool-calling, function calling, RubyLLM::Agent, RubyLLM::Tool, streaming, RAG, retrieval augmented generation, vector search, semantic search, embedding, pgvector, DSPy, reasoning module, chain of thought, ReAct, MCP server, MCP tool, model context protocol, ruby_llm, RubyLLM, NLP, entity extraction, named entity recognition, sentence segmentation, chunking, document processing, local inference, informers, spaCy, ruby-spacy, prompt pipeline, or structured output. Detects whether request is scaffolding (generate file) or advisory (explain approach). Always runs rubysmithing-context as a prerequisite step before generating any library-specific code. Single focused file output; specs only on explicit request.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rubysmithing:rubysmithing-genaiThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Scaffolder and advisor for AI/NLP components in the Ruby terminal-native stack.
Scaffolder and advisor for AI/NLP components in the Ruby terminal-native stack. Generates single focused implementation files or explains integration patterns.
Before generating any implementation code:
Activate rubysmithing-context for every gem involved in this task.
This is not optional — generate no library-specific code until API syntax is confirmed
or a [WARNING: Unverified API Syntax] block has been injected.
Identify architectural plane: reasoning, retrieval, NLP, or transport?
Confirm async context: will this run inside an Async block?
If yes → non-blocking patterns required.
Confirm circuit breaker requirement: applies to all external LLM API calls in Standard Mode. Omit in Lite Mode (task ≤ ~50 lines).
Scaffolding — triggered by: create, build, implement, generate, scaffold, write me a. Output: single focused file, Zeitwerk-compliant path, complete implementation.
Advisory — triggered by: how do I, explain, what's the best way, compare, should I use. Output: recommendation + minimal snippet. No full file unless asked.
Compound prompts (e.g., "refactor this RAG pipeline AND build a TUI for it"): Split the request. Handle the GenAI component here. State explicitly: "Handling the RAG pipeline component. The TUI dashboard component should be addressed with rubysmithing-tui."
Load references/genai-patterns.md for implementation patterns:
RubyLLM::Agent configuration, RubyLLM::Tool class definitions, chatbot,
RAG ingestion/retrieval/full pipeline, DSPy modules, MCP server,
embedding generator (remote vs local), NLP processor, async+circuit breaker wrapper.
Generate RSpec specs only when explicitly requested:
spec/[path_matching_lib_file]_spec.rbnpx claudepluginhub b08x/rubysmithing --plugin rubysmithingProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.