ワンクリックで
grain-todo-list
grain-todo-list には ObneyAI から収集した 16 個の skills があり、リポジトリ単位の職業カバレッジとサイト内 skill 詳細ページを表示します。
このリポジトリの skills
Give your AI agents something more useful than a prompt. Velocity through clarity.
Visual quality gate — screenshot each primary screen, critique it against the baseline rubric, and refine the components until it passes. Use before declaring a build done.
Implement command handlers that validate state, emit events, and return signals using the Grain framework
Create scheduled background jobs that run on cron schedules
Implement query handlers that read from event-sourced read models and render hiccup
Build read models by reducing events into queryable state with defreadmodel
Define Malli schemas for commands, events, and queries using defschemas
Create a complete Grain domain service with schemas, read models, commands, queries, views, and tests
Implement event-driven side effects that react to domain events
Build the app's reusable UI component library (its visual language) on the foundation.ui primitives + DaisyUI, and compose screens from it
Build Hiccup view functions for Datastar pages as thin compositions of the app's component library
Connect to the project's nREPL server using the nrepl MCP tool
Generate tests from Allium specifications. Use when the user wants to propagate tests, generate test files from a spec, write tests for a specification, create property-based tests, produce state machine tests, check test coverage against spec obligations, or understand what tests a specification requires.
Run the E2E QA test suite against the live application using Playwright MCP and nREPL. Use when testing the app end-to-end.
Run the project test suite with the build tool's test task
Verify a build's acceptance checks against the LIVE app — the correct Playwright MCP snapshot→ref→act contract, signing in to an auth app, and when to assert via nREPL instead of the browser. Use whenever you verify acceptance as a real user (Definition of done