b08x/ruby-dev

v6.1.0MIT

Task-driven Ruby development toolkit: project scaffolding, data pipelines, multi-database (Ohm/Sequel/pgvector) modeling, GenAI components, RubyLLM client integration, typed LLM programs with dspy.rb, classical NLP toolkit, TUIs, desktop GUIs (glimmer-dsl-libui), diagnostics, refactoring, performance optimization, decode-style documentation comments (coverage via decode, code-graph queries and semantic lint via rubydex), and SIFT quality audits — routed by the rubyist orchestrator, which dispatches 5 phase subagents (specifier, implementer, cleaner, hardener, verifier) that load domain skills on demand.

GitHub

skills

evals

Use when evaluating the ruby-dev plugin itself — establishing or extending a reproducible baseline, designing eval challenges with planted ground truth, building or running the ruby-dev-evals harness, scoring specialist output, checking rubyist gateway protocol compliance, calibrating an LLM judge, or turning eval findings into prompt fixes. Trigger on 'baseline eval', 'evaluate the plugin', 'eval harness', 'does the plugin beat bare', 'gateway compliance', 'regression test the prompts', 'ruby-dev-evals'.

Read SKILL.md at the source

Pinned to revision 88338d98c444, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.