CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/soda-checks

Authors and runs SodaCL (Soda Checks Language) checks against SQL warehouses (Snowflake, BigQuery, Postgres, Redshift, etc.) via `soda scan`, configures scan profiles in configuration.yml, and gates CI on scan exit code. Use when the user works with Soda Core / Soda Cloud or needs YAML-driven warehouse data quality.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

85%

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

The body is actionable and well-sequenced with executable examples and real validation checkpoints. The main weakness is mild redundancy of introductory context that Claude already knows.

Suggestions

Trim the 'Overview' definition of SodaCL and the Great Expectations/dbt contrast; assume Claude knows what a YAML DSL and competing DQ tools are.

Move the longer configuration.yml and GitHub Actions examples to a referenced file if the skill grows, keeping SKILL.md a lean overview.

Consider consolidating the repeated 'soda scan -d warehouse -c configuration.yml checks.yml' invocations into one canonical example plus a note on variations.

DimensionReasoningScore

Conciseness

Mostly efficient with executable examples, but includes some Claude-knows context such as 'SodaCL is a YAML-based domain-specific language for data reliability' and the Great Expectations/dbt contrast that could be trimmed.

2 / 3

Actionability

Provides copy-paste-ready checks.yml, configuration.yml, bash 'soda scan' invocations, and a complete GitHub Actions workflow with env-var wiring.

3 / 3

Workflow Clarity

Clear sequenced sections (Authoring -> Configuration -> Running -> Parsing -> CI) with explicit validation checkpoints: non-zero exit gating, 'if: always()' artifact capture, and a grep filter for surfacing failures.

3 / 3

Progressive Disclosure

A single well-organized SKILL.md with clearly signaled one-level-deep external doc references and no nested bundle indirection; appropriate for a no-bundle skill.

3 / 3

Total

11

/

12

Passed

Description

100%

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 specific, trigger-rich, and clearly distinguishes the skill's niche, with explicit what-and-when guidance. It is concise without padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions - 'Authors and runs SodaCL checks', 'configures scan profiles in configuration.yml', and 'gates CI on scan exit code' - beyond merely naming the domain.

3 / 3

Completeness

Clearly answers 'what' (authors/runs/configures/gates) and 'when' with an explicit 'Use when the user works with Soda Core / Soda Cloud or needs YAML-driven warehouse data quality' trigger clause.

3 / 3

Trigger Term Quality

Natural user-facing terms like 'Soda Core / Soda Cloud', 'soda scan', 'YAML-driven warehouse data quality', and warehouse names provide good coverage of what users would actually say.

3 / 3

Distinctiveness Conflict Risk

Targets a distinct SodaCL niche with specific triggers and an explicit contrast against Great Expectations and dbt, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents