dsql

Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django/Hibernate/Rails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow, DSQL foreign key, DSQL OCC retry, DSQL multi-region, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

70%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized with strong, validated workflows and dense actionable MCP guidance, but it is undermined by a missing mcp/ subtree referenced throughout (notably safe_query.py) and some redundancy between the limits table, Error Scenarios, and capability bullets. Fixing the broken mcp references would lift actionability and progressive disclosure.

Suggestions

Add the missing mcp/ files (mcp-setup.md, mcp-tools.md, .mcp.json, tools/input-validation.md, tools/safe_query.py) or repoint those references to existing files so the safe_query.build() workflow gate is actually resolvable.

Dedupe the AWS service-limits table against the Error Scenarios block (e.g., reference the table from Error Scenarios instead of restating defaults) to tighten conciseness.

Surface the unused bundled files (references/examples/* and references/auth/connectivity-tools.md, scaling-guide.md) in the Reference Files index so all delivered material is discoverable.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient (terse per-file When/Contains stubs, tight Quick Start, dense MUST rules), but the AWS-limits table is partially restated in Error Scenarios and the 'Key capabilities' bullets duplicate the description, so it is not fully lean.	4 / 5
Actionability	Concrete executable guidance is strong (exact transact/readonly_query/dsql_lint calls, a psql IAM-token heredoc), but Workflow 4's central gate references safe_query.build() via mcp/tools/safe_query.py, which does not exist in the bundle, leaving a key actionable detail unavailable.	3 / 5
Workflow Clarity	Workflows are well-sequenced with explicit validation before destructive/batch DDL (dsql_lint(fix=true)), feedback loops (Workflow 2 resume-by-unset-state, Workflow 8 conditional Phase 3 and reassessment addendum), and a required-elements checklist, satisfying the validation-cap requirement.	5 / 5
Progressive Disclosure	Structure is otherwise excellent (one-level-deep references with When/Contains navigation, modular subdirectories), but five paths under a referenced mcp/ directory are dead links and several bundled examples/ and auth/ files are never surfaced, a navigation defect beyond a minor gap.	3 / 5
	Total	15 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: it states concrete capabilities, enumerates comprehensive natural trigger phrases, answers both what and when, and is tightly scoped to a named product with low conflict risk. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('manage schemas, execute queries, handle migrations, diagnose query plans, load data') plus a comprehensive 'Covers' list (IAM auth, multi-tenant patterns, FK replacement code generation, OCC retry patterns, ORM migration), matching the comprehensive-coverage anchor.	5 / 5
Completeness	It clearly answers 'what' in the first two sentences and 'when' via explicit concrete trigger phrases, matching the score-5 anchor that requires both with concrete triggers.	5 / 5
Trigger Term Quality	An explicit 'Triggers on phrases like:' clause lists ~18 natural user phrases including synonyms ('DSQL', 'Aurora DSQL'), user-language forms ('why is my DSQL query slow', 'load CSV into DSQL'), and the tool name 'aurora-dsql-loader', giving comprehensive natural-term coverage.	5 / 5
Distinctiveness Conflict Risk	The named product 'Aurora DSQL' plus heavily DSQL-qualified trigger phrases establish a clear niche with minimal overlap risk against other database skills; voice is third person throughout.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 8 missing, 30 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 27 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: awslabs/mcp
Path: src/aurora-dsql-mcp-server/skills/dsql-skill/SKILL.md
Commit: 5609db9

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.