rubysmithing

Use when any Ruby development request needs routing to the rubysmithing skill suite — code generation, scaffolding, AI/NLP components, TUI interfaces, refactoring, QA assessment, or YARD documentation. Entry point that delegates to the appropriate specialized sub-agent.

Use when generating convention-aware Ruby code outside scaffold, genai, TUI, refactor, report, or yardoc domains — classes, modules, Rake tasks, config wiring, boot layers, data pipelines, POROs, error hierarchies, parallel workers, content parsers, or Gemfile decisions.

Use when tracing why Ruby code fails, auditing for waste or dead code, or investigating before refactoring. Triggers on Zeitwerk NameError, circuit_breaker opening, slow Sequel queries, "root cause", "dead code", "muda", "gemba", or pre-refactor investigation requests.

Use as a prerequisite before generating Ruby code that uses non-stdlib gems: ruby_llm, sequel, async, bubbletea, dspy.rb, pgvector, huh, dry-schema, circuit_breaker, fast-mcp, lipgloss, bubbles, gum, ntcharts, glamour, harmonica, bubblezone. Returns verified method signatures and usage examples.

Use when building AI/NLP components in Ruby — LLM chatbots, tool-calling agents, RAG pipelines, vector search, embeddings, DSPy reasoning modules, MCP servers, local inference, NLP processors, or structured output. Runs rubysmithing-context as prerequisite.

Ruby-targeted analysis skill implementing Gemba Walk (code archaeology, docs-vs-reality gaps), Muda waste analysis (dead methods, N+1 queries, unused gems, over-engineering), Root-Cause Tracing (backward call-chain from symptom to source), and Five Whys (iterative causal drilling). Use when user asks "why is this failing", "trace this bug", "root cause", "what's wasting cycles", "dead code audit", "gemba", "muda", "pre-refactor investigation", or reports a Zeitwerk error, circuit_breaker trip, or slow query. Auto-selects method from context. Produces findings keyed to rubysmithing-refactor pattern names for direct handoff to /rubysmithing:refactor.

Gem API verification sub-skill for Ruby development. Automatically activates on first mention of any Ruby gem — especially ruby_llm, sequel, async, bubbletea, dspy.rb, pgvector, huh, dry-schema, circuit_breaker, fast-mcp, or informers — and resolves current method signatures and usage examples via Context7 MCP before code is generated. Results are cached for the session and persisted to SQLite across sessions. If Context7 resolution fails or is rate-limited, falls back to the tiered degradation protocol (stale cache → gem-registry ID → WARNING block) rather than silently guessing. Pairs with rubysmithing, rubysmithing-genai, and rubysmithing-tui as a prerequisite step.

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.

Convention-targeted Ruby refactoring sub-skill. Activates on any mention of: refactor, clean up, fix conventions, this code is messy, help me improve this, anti-patterns, rubocop violations, Zeitwerk compliance, autoload issue, make this idiomatic, extend self, frozen string literal missing, thread usage, hardcoded config, silent rescue, or missing namespace. Accepts pasted code snippets, uploaded files, or filesystem paths. Detects convention target from project config (RuboCop, StandardRB, Rubysmith) before applying changes. Produces pre-refactor audit + complete refactored file + change log. Applies Lite Mode bypass for scripts under ~50 lines where architectural mandates would be disproportionate.

Rubysmith QA assessment sub-skill implementing the SIFT Protocol V1.0. Activates on any mention of: assess, audit, review this project, code quality, convention violations, what's wrong with this code, score my code, how compliant is this, system design review, tech advisory, SIFT, Rubysmith QA, Caliber, Reek, dry-monads compliance, pipeline depth, god class, missing DI, or any request for a structured code quality report. Accepts pasted code, uploaded files, or filesystem paths. Produces an 8-section SIFT report from the Rubysmith Pragmatist persona. Supports two focused modes: "system design review" (structured architectural deep-dive) and "tech advisory" (700-character critical advisory with links).