Back to directory

AI agents Rules / Skills from Programming Books

A set of installable rule and skill files for coding agents distilled from well-known software-engineering books on refactoring, architecture, and domain-driven design.

AI agents Rules / Skills from Programming Books

AI agents Rules / Skills from Programming Books packages guidance from classic software-engineering books, including titles on clean code, refactoring, domain-driven design, clean architecture, and data-intensive systems, into rule sets that Codex, Cursor, and Claude Code can load. Each book's material ships in three tool-agnostic Markdown sizes: a compact version for tight context budgets, a version recommended for everyday use, and a full canonical reference.

An open skills command-line tool installs every book's rules as a skill with one command, lists available skills without installing them, or installs a single selected topic such as refactoring, and each installed skill loads its recommended rule set by default while keeping the full text available as deeper reference.

It is released under the MIT license as universal, tool-agnostic project rules.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.