メニュー
Install @effect/* packages safely. Use whenever adding a new Effect ecosystem dependency.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | install-effect-package |
| description | Install @effect/* packages safely. Use whenever adding a new Effect ecosystem dependency. |
| user-invocable | false |
When installing any @effect/* package, always use npm install --force:
npm install --force @effect/package-name
--legacy-peer-deps?The --legacy-peer-deps flag corrupts the lockfile by removing existing @effect/* peer dependencies (e.g., @effect/rpc, @effect/sql, @effect/experimental). The corruption is silent — npm install succeeds but the lockfile is broken, and you only discover the damage later when other Effect packages fail to resolve.
--force installs the package while preserving the existing dependency tree.
Break a PRD into native GitHub sub-issues attached to the parent PRD. Project-local variant of /to-issues, adapted for this repo's PRD-as-parent + native sub-issues + agent:implement multi-session workflow. Argument is the parent PRD issue number.
Optimize slow React Router loaders by eliminating redundant DB queries, creating slim query variants, and parallelizing independent fetches. Use proactively when writing or reviewing loader code that calls domain operations services (e.g. CourseOperationsService, VideoOperationsService), or when triaging a slow page load.
Survey the codebase, pick ONE high-leverage deepening opportunity (filtering out anything already proposed), and publish it as a PRD-shaped GitHub issue via /to-prd-project. Designed to run unattended in the daily architecture-review workflow.
Turn the current conversation context into a PRD and publish it as a GitHub issue that is ready to receive sub-issues from /to-issues-project. Project-local variant of /to-prd, adapted for this repo's PRD-as-parent-issue + sub-issues + agent:implement workflow.
Generate or update documentation for the AI Hero API by reading the source code at ~/repos/ai/course-builder. Use when user wants to document, update docs for, or understand the AI Hero API endpoints.
End-to-end implementation workflow. Use when user wants to implement a feature, fix a bug, or make changes and have everything validated and committed.