メニュー
Design a correct relational schema: normalize to 3NF, denormalize only with measured evidence and a named consistency cost, push constraints (PK/FK/UNIQUE/CHECK/NOT NULL) into the database, and choose precise data types.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
SOC 職業分類に基づく
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。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/mcorbett51090/RavenClaude --skill relational-schema-designコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
Route everyday, well-defined work (single-file edits, test-writing, summarization, mechanical refactors, boilerplate) to a cheaper coding agent (Grok or Copilot CLI) instead of doing it in the main Claude session, escalating multi-file/architecture/debugging/security work to Claude. Opt-in via the `cheap_lane:` comfort-posture knob.
Authors, validates and packages a claude.ai Organization Skill — the intake questions, the trigger and scope exercises, then lint, pack and verify against measured platform constraints. Reach for this when someone wants to publish a Skill to their organization, or when an upload was rejected and the reason is unclear.
Drafts a reply to an inbound customer email, grounded in the account record and the published help-centre articles rather than in recall. Use when a customer emails about billing, a renewal or an outage, when a reply must cite current policy, or when a teammate asks for a first draft to edit.
| name | relational-schema-design |
| description | Design a correct relational schema: normalize to 3NF, denormalize only with measured evidence and a named consistency cost, push constraints (PK/FK/UNIQUE/CHECK/NOT NULL) into the database, and choose precise data types. |
3NF by default: each fact once, relationships via keys. Most 'we must denormalize' instincts are premature.
Only with a measured read benefit AND the write/consistency cost named — often a materialized view or covering index is better than redundant columns.
PK on every table, FK for every relationship, NOT NULL/UNIQUE/CHECK to make illegal states unrepresentable. The app is not a trustworthy enforcer.
Precise numeric/temporal/text; uuid/enum/jsonb where they fit. text for everything + naive timestamps are smells.