CtrlK
BlogDocsLog inGet started
Tessl Logo

connecting-to-data-source

Create and troubleshoot AWS Glue connections to JDBC databases (Oracle, SQL Server, PostgreSQL, MySQL, RDS), Redshift, Snowflake, and BigQuery. Gathers connection hints from user, discovers existing connections and RDS/Redshift candidates, registers credentials in Secrets Manager or IAM DB auth, configures VPC, and tests. Triggers on: connect to database, set up Glue connection, register data source, connect to Snowflake/BigQuery/RDS, connection timeout, test connection, troubleshoot connection. Do NOT use for moving data (use ingesting-into-data-lake), creating tables (use creating-data-lake-table), queries (use querying-data-lake), catalog exploration (use exploring-data-catalog), or SaaS (Salesforce, ServiceNow, SAP, MongoDB, Kafka).

77

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 a strong example of skill structure: a lean, command-driven workflow with genuine two-phase validation, an explicit error-recovery path, and clean one-level-deep progressive disclosure into seven real reference files. The only notable weakness is that the central create-connection step is not self-contained, requiring a hop to a reference to construct the required JSON.

DimensionReasoningScore

Conciseness

The body is lean and operational: commands, tables, and gotchas with almost no conceptual padding — e.g. "A connection is a named pipe, not a pipeline" is a two-line scoping statement, not a tutorial. It assumes Claude's competence (no explanation of what Glue or VPCs are), and the one explanatory passage (why Phase B test-connection is insufficient) conveys non-obvious, failure-relevant information. Matches anchor 5's 'every token earns its place' rather than anchor 4's 'minor instances of over-explanation'.

5 / 5

Actionability

Mostly executable guidance: concrete commands like `aws sts get-caller-identity`, `aws glue get-connections --filter ConnectionType=<TYPE>`, `aws glue test-connection --connection-name <NAME>`, plus per-source hint checklists. However, the core creation step `aws glue create-connection --connection-input '<JSON>'` uses an unresolved placeholder with no inline example of the JSON shape, deferring entirely to the references — a minor gap that fits anchor 4 ('concrete code or commands with minor gaps') rather than anchor 5's copy-paste-ready coverage of common cases.

4 / 5

Workflow Clarity

Eight clearly sequenced steps with explicit validation: "You MUST test before handing off" with a two-phase check (Phase A `aws glue test-connection`, Phase B engine-level verification), a defined failure route ("On failure in either phase, Step 8"), and an ordered diagnostic procedure with constraints. This matches anchor 5's explicit validation steps and feedback loops for error recovery, not anchor 4's 'minor validation gaps'.

5 / 5

Progressive Disclosure

The body is a well-organized overview that routes to seven one-level-deep references, each contextually signaled (source-classification table, per-step links, and a References section with one-line descriptions), and all seven referenced files exist in ./references/. Content is appropriately split (per-source setup details live in the references; routing and orchestration stay inline), matching anchor 5 rather than anchor 4's 'minor organization gaps'.

5 / 5

Total

19

/

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 in third person, provides comprehensive natural-language triggers, and disambiguates against sibling skills with an explicit exclusion list. It clearly matches the top anchor on every dimension with no vague or padded language.

DimensionReasoningScore

Specificity

Names the domain ("AWS Glue connections to JDBC databases (Oracle, SQL Server, PostgreSQL, MySQL, RDS), Redshift, Snowflake, and BigQuery") and lists multiple concrete actions: "Gathers connection hints", "discovers existing connections and RDS/Redshift candidates", "registers credentials in Secrets Manager or IAM DB auth", "configures VPC, and tests". This is comprehensive coverage across the whole workflow, matching the anchor-5 example rather than anchor 4's 'minor gaps in coverage'.

5 / 5

Completeness

Explicitly answers both 'what' (first two sentences of concrete capabilities) and 'when' ("Triggers on: ..." plus a "Do NOT use for ..." exclusion list). Concrete trigger phrases are present, matching anchor 5; anchor 4 would require the 'when' to be less explicit or specific.

5 / 5

Trigger Term Quality

"Triggers on: connect to database, set up Glue connection, register data source, connect to Snowflake/BigQuery/RDS, connection timeout, test connection, troubleshoot connection" covers the natural phrases a user would say, including product-name synonyms and failure-mode triggers ("connection timeout"). Coverage is comprehensive with synonyms, matching anchor 5 rather than anchor 4's 'a few natural terms missing'.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Glue connection registration) with explicit negative routing to named sibling skills ("use ingesting-into-data-lake", "creating-data-lake-table", "querying-data-lake", "exploring-data-catalog") and excluded product categories (Salesforce, ServiceNow, SAP, MongoDB, Kafka). Conflict risk is minimal, matching anchor 5's 'clear niche with distinct triggers'.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
aws/agent-toolkit-for-aws
Reviewed

Table of Contents

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.