菜单
Recompute and display the two database scores (Design & Integrity + Performance & Scale) from a findings JSON, without re-auditing. Use to re-show or refresh the scores after an audit, to re-score with a different paradigm profile, or to score a saved findings file.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Hainrixz/claude-db --skill score命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Audit a database schema, ORM model, or migrations for design and performance — produces two independent 0-100 scores (Design & Integrity + Performance & Scale) plus a prioritized, evidence-backed report. Read-only; never writes or migrates. Use when the user asks to audit, analyze, review, check, or score a database, schema, data model, migrations, indexes, keys, referential integrity, types, constraints, query patterns, partitioning, or connection pooling — for Postgres, MySQL, Mongo, DynamoDB, Cassandra, pgvector, ClickHouse, Neo4j, and friends.
Render a production-readiness GO/NO-GO grid for a database — runs a read-only audit, then maps the findings onto a fixed launch checklist (PITR/backups, RLS on tenant tables, FK indexes, money-as-numeric, timestamptz/UTC, connection pooling sized, migration reversibility, secrets-not-in-schema, charset/utf8mb4). Each row is PASS/WARN/FAIL/NEEDS-LIVE with the finding id, topped by a plain-language verdict. Read-only. Use when the user asks if a database is production-ready, ready to launch/ship, a go/no-go, a pre-launch or readiness checklist, or what to fix before going live.
Unified cross-paradigm anti-pattern catalog (M19) — relational and NoSQL smells that no single structural module owns cleanly: EAV / generic key-value tables, the "god table" with hundreds of columns, comma-separated lists in a column, polymorphic associations without FK, boolean-flag soup, Mongo unbounded array growth, deeply nested documents, the document fan-out / "join in app code" trap, Redis as a relied-on durable primary store. Each finding is re-homed to inherit the natural module's category. Feeds the Design & Integrity AND Performance & Scale scores depending on the smell.
基于 SOC 职业分类
正在显示 SKILL.md
| name | score |
| description | Recompute and display the two database scores (Design & Integrity + Performance & Scale) from a findings JSON, without re-auditing. Use to re-show or refresh the scores after an audit, to re-score with a different paradigm profile, or to score a saved findings file. |
| argument-hint | [findings.json] [--paradigm relational|document|key-value|wide-column|vector|time-series|graph] |
| allowed-tools | Read, Bash |
Recompute and show the two 0–100 scores from a set of findings by re-running scripts/score.mjs (pure, fully reproducible — it implements references/scoring-model.md).
$ARGUMENTS, score that file:
node scripts/score.mjs --findings <path> [--paradigm <p>].
The file is a JSON array of findings (or { "findings": [...] }) conforming to schema/finding.schema.json./claude-db:audit <target> first — do not invent findings.--paradigm flag selects the category profile (PROFILES in score.mjs); the default is relational. Re-scoring under a different profile is how you show, e.g., the same Mongo findings under the document profile (no foreign-key categories in the denominator).Show both scores with bands (A ≥ 90 · B ≥ 80 · C ≥ 70 · D ≥ 60 · F < 60), the per-category breakdown (value × weight, active?), any severity-gating cap (capped:true with the uncapped computed shown), and the needs_api count as score confidence. needs_api and speculative findings never cap. Two scores, never blended.