Curated library of atomic skills and personas for Hanami, dry-rb, and ROM Ruby development. Covers actions, slices, repositories, relations, changesets, providers, DI, operations, TDD, CLI, views, routing, validation, and 10 orchestration personas. Shared Ruby process skills have moved to ruby-core-skills. Uses Markdown + Front-matter architecture.
95
95%
Does it follow best practices?
Impact
96%
1.20xAverage score across 45 eval scenarios
Passed
No known issues
hanakai-yaku turns AI coding assistants into disciplined Hanami collaborators.
A curated library of 35 atomic skills and 10 personas for Hanami, dry-rb, and ROM Ruby development that teach AI tools how to configure providers, implement dependency injection, write TDD tests, create repositories, design slices, and build operations — using Hanami conventions.
Status: Experimental — used to validate skill format portability across Ruby frameworks. Not actively maintained as a product. For production Rails AI tooling, see rails-ai-bridge.
The project is built around one non-negotiable rule:
Write test -> Run test -> Verify it FAILS for the right reason -> Implement -> Verify it PASSESThat TDD gate is encoded directly into the skills and personas.
This repo is one of 6 in a composable AI skill ecosystem:
| Repo | Role |
|---|---|
ruby-core-skills | 15 shared Ruby skills + process discipline |
rails-agent-skills | 28 Rails-specific skills + 9 agents |
hanakai-yaku | 35 Hanami/dry-rb skills + 10 personas |
agnostic-planning-skills | 10 planning skills + 4 personas |
agent-mcp-runtime | Rust CLI runtime (pack resolution, MCP) |
ruby-skill-bench | Benchmark/eval engine |
See the Ecosystem Overview for the full architecture.
This repo depends on ruby-core-skills. See Migration Guide.
Supported agent environments
| Reader | What you get | | Hanami developers | AI-assisted Hanami development: slices, repositories, operations, actions, views. | | dry-rb users | Guidance on operations, validation contracts, DI patterns, and type-safe design. | | ROM users | Repository patterns, relation design, changeset composition, migration safety. | | Team leads | Repeatable workflows for Hanami onboarding, TDD discipline, and slice architecture. |
Install skills via tessl.io:
npx tessl i igmarin/hanakai-yakuor with yarn
yarn dlx tessl i igmarin/hanakai-yakuInstall skills via skills.sh:
npx skills add igmarin/hanakai-yakuOr via GitHub CLI (v2.90.0+):
# Install the dependency first
gh skill install igmarin/ruby-core-skills
# Install all skills interactively
gh skill install igmarin/hanakai-yaku
# Install a specific skill
gh skill install igmarin/hanakai-yaku load-context --scope projectOr use directly as chat commands (@skill-name) in compatible AI tools (OpenCode, Cursor, Claude Code, Gemini CLI, Windsurf).
| Area | Purpose |
|---|---|
skills/ | Atomic Hanami skills organized by category: context, providers, actions, persistence, dry-rb, testing, slices, views. |
skills/personas/ | Orchestrating personas that chain skills into guided workflows. |
docs/ | Architecture, Persona guide, reference catalog, and calling conventions. |
CONTEXT.md | Domain glossary — the canonical vocabulary for Hanami concepts. |
Skills are invoked via chat commands:
| Method | Syntax | Example |
|---|---|---|
| Chat Command | @skill-name | @load-context |
@load-context # Discover the app's slices, providers, and routes
@configure-providers # Set up providers and settings
@implement-di # Configure dependency injection patterns
@hanami-setup # Full project onboarding workflow| Skill | Category | Description |
|---|---|---|
load-context | Context | Load the Hanami app structure before coding |
configure-providers | Providers | Set up Hanami providers, settings, and .env |
implement-di | Providers | Dependency injection patterns with dry-system |
| Persona | Description |
|---|---|
hanami-setup | Project onboarding: Context → Providers → DI → Verify |
See docs/reference/skill-catalog.md for the complete catalog.
Each skill is a single SKILL.md file with YAML frontmatter and a 6-section body:
1. Frontmatter (YAML) — name, description, metadata
2. Quick Reference — scannable table for fast lookup
3. HARD-GATE — non-negotiable blocking rules
4. Core Process — step-by-step procedure
5. Output Style — exact shape of artifacts
6. Integration — predecessor/successor skills| Need | Document |
|---|---|
| Understand the docs system | docs/index.md |
| Browse all skills | docs/reference/skill-catalog.md |
| Understand skill chaining | docs/reference/integration-matrix.md |
| Follow Persona guides | docs/persona-guide.md |
| Understand repository structure | docs/architecture.md |
When contributing skills, personas, or docs:
directory.json and CONTEXT.md.