AI agent skills and stuff
This repository also configures its own agents. See what agentifico tells them →
Skill Claude CodeCodex
The house Rails style, distilled from 37signals practice (Campfire, Fizzy, DHH's reviews). Use for all Rails coding, refactoring, and code review so architecture, naming, and safety standards stay consistent; fires on work touching models, concerns, controllers, routing, REST, authorization, dependencies, naming…
Skill Claude Code
Review prose for spelling, grammar, punctuation, style, clarity, tone and readability, reporting the issues or applying minimal edits when asked. Use for proofreading, or tightening the phrasing of, selected text, markdown, documentation, prompts, AGENTS.md, README files, code comments, UI copy, emails and commit…
Skill Claude Code
A Socratic tutor that helps the user work out the answer to their own question through probing questions asked one at a time, giving graded hints but never the answer until the user asks for it. Invoked explicitly only, by the user typing its name: an agent never loads it on its own, whatever the mode or the task. Not…
Skill Claude Code
Write, review, check, maintain and export agent skills. An agent invokes it when told to, or when it reviews or checks a change to a skill, a SKILL.md file or a package of skills. Covers the frontmatter contract, the traps that fail silently and the routing-skill layout. Not for using a skill, only for the files that…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: