sqlsure
sqlsure/sqlsure
sqlsure is a deterministic semantic SQL validator designed to catch silent errors like double-counting and unsafe sums before queries are executed against a database.
98 3Apache-2.0Updated 2026-07-18
83
GreatOverview
This skill evaluates SQL query text against declared schema facts, dbt manifests, or database introspections without relying on LLMs or database connections. It provides fast, deterministic checks for issues like fan-out double-counting, missing join keys, and exposure of sensitive data, allowing AI agents or CI pipelines to automatically inspect and correct queries before execution.
Capabilities
- ▸Validates SQL against semantic rules (fan-out, chasm, additivity, semi-additivity, join keys, cross joins)
- ▸Generates machine-actionable fix suggestions for failed queries
- ▸Introspects schemas from SQLite, Postgres, MySQL, or dbt manifests
- ▸Operates completely offline with zero data access or telemetry
Best for
Preventing AI agents from executing flawed text-to-SQL queries that pass syntax checks but contain semantic errors., Auditing dbt repositories and query logs for join cardinality mismatches and hidden aggregation bugs., Integrating into CI pipelines to block merges of pull requests containing double-counting or unsafe sums.
Works with
Claude CodeCursorGitHub CopilotChatGPTOpenCode
Evoa Score breakdown= Σ (score × weight)
83Task usefulness20%77 → +15.4
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%95 → +14.3
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%100 → +15.0
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%46 → +5.5
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%100 → +15.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%90 → +9.0
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%51 → +4.1
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%100 → +5.0
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total83.3 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Performs static analysis exclusively on query text using local schema definitions. Requires no active database connection and transmits no telemetry or data externally.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.