From hone
Initializes hone in current project: creates .plans/ directory and hone.config.yml with default Claude/opencode agent config. Reports status and next steps for docs/PRD.
How this skill is triggered — by the user, by Claude, or both
Slash command
/hone:initThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Initialize hone for this project:
Initialize hone for this project:
.plans/ directory exists. If not, create it..plans/hone.config.yml exists. If not, create it with this default content:version: 2
agent: claude
claude:
models: {}
opencode:
models: {}
agentsDocsDir: '.agents/'
Report what was created:
If anything was created, show next steps:
npx claudepluginhub oskarhane/hone-ai --plugin honeAutomatically configure Claude Code best practices for new projects: directory skeleton, AGENTS.md, hooks, and interactive placeholders fill. Invoke via `/init-project`.
Initializes new or existing projects for AI-assisted development: runs full-tree discovery, identifies domain, writes plan, generates artifacts, and reviews output end-to-end.
Bootstraps a new project by interviewing the developer (name, description, stack, optional hooks/skills), then scaffolding directory structure, CLAUDE.md, config files, and first commit.