enozunu - a cross-provider skills/agents materializer for code agent.

by
Enozunu(役小角) is a cross-provider skills / agents materializer for AI agent tooling. Enozunu separates Skill and agent sources from the target-native files generated in each project. Reuse Skills and agents declaratively. Declare sources and selections instead of copying configuration files between projects. Tool authors can publish the artifacts and an Enozunu-compatible manifest declaration instead of implementing their own setup mechanism.

Add a comment

Replies

Best
Maker
📌
Enozunu manages where AI-agent configuration comes from and where it is materialized. You declare sources once in enozunu.kdl, and Enozunu resolves them and writes them into each target AI's native paths. The supported target AIs are Claude and Codex. Both select from the same source pool, and each selection is materialized into that target's native path. For the exact placement of each artifact, see the supported targets guide.

In 0.2.0, `enozunu` support generating instruction files(AGENTS.md or CLAUDE.md).

Based on the specified document, `enozunu` generate the instructions by adding skill information along with its conditions.

In 0.3.0, `same-as` alias is supported on `instructions` and `use-skills`.

It is enabled to reuse definitions about instruction and skills.

    instructions {
      claude {
         git {
          url ""
          branch "main"
          path "instructions/base.md"
        }       
      }
      codex same-as="provider.instructions.claude"
    }
  consumer {
    claude {
      use-skills "documentation-writing" {
        when "updating documentation"
        when "writing or modifying code comments"
      }
    }
    codex {
      use-skills same-as="consumer.claude.use-skills"
    }
  }

Windows supported from 0.4.0.

It is provided by

scoop bucket add philomagi 
scoop install enozunu