CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/soda-checks

Use when warehouse data quality (Snowflake, BigQuery, Postgres, Redshift and others) should be checked with YAML-based SodaCL: writing checks, configuration.yml data sources, soda scan runs and CI gating on the exit code, with Soda Core or Soda Cloud.

Quality

90%

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

82%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.

A highly actionable, executable body that covers the full SodaCL lifecycle with real commands and complete examples. It is efficient but has minor trims available, lacks an explicit step ordering and failure-recovery loop, and keeps all content inline where a reference file split would help.

Suggestions

Add a short numbered workflow at the top (author checks.yml -> write configuration.yml -> run soda scan locally -> wire into CI) so the cross-section sequence and a 'if the scan fails, fix the check or the data and re-run' recovery loop are explicit.

Trim editorial asides ('in contrast to Great Expectations, which is Python-first', 'when you most need it for triage') and consolidate the repeated inline citation parentheticals into the References section.

Move the full GitHub Actions workflow and the check-type reference table into a references/ file, keeping SKILL.md as a lean overview with well-signaled one-level-deep pointers.

DimensionReasoningScore

Conciseness

Efficient and dense with executable YAML/bash and no concept primers, but a few sentences could be trimmed: 'in contrast to Great Expectations, which is Python-first', 'when you most need it for triage', and repeated citation parentheticals like '(the canonical Soda filenames per [sodacl-quickstart][2])'.

4 / 5

Actionability

Fully copy-paste ready throughout: complete checks.yml and configuration.yml examples with env-var substitution, the exact 'soda scan -d warehouse -c configuration.yml checks.yml' invocation, a grep snippet for parsing results, and a full GitHub Actions workflow covering the common CI case.

5 / 5

Workflow Clarity

The author-configure-run-parse-CI sequence is clear with checkpoints (exit-code gating, 'grep -E FAIL' surfacing, the if: always() artifact-upload note), but steps are never explicitly ordered across sections and there is no recovery loop for iterating when a scan fails.

4 / 5

Progressive Disclosure

No bundle files exist and the single body is well-sectioned with one-level-deep external doc links and a closing References map. However, at ~230 lines the check-type table and full CI workflow could live in reference files, keeping it below the clear-split ideal of the 5 anchor.

4 / 5

Total

17

/

20

Passed

Description

92%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.

A strong description that explicitly states both capability and trigger conditions with concrete, tool-specific actions spanning the full skill scope. Only weakness is slightly thin synonym coverage for natural user phrasings.

DimensionReasoningScore

Specificity

Lists multiple concrete actions covering the skill's full scope: 'writing checks, configuration.yml data sources, soda scan runs and CI gating on the exit code'. Coverage is comprehensive (author, configure, run, CI) rather than having the minor gaps of the 4 anchor.

5 / 5

Completeness

Explicitly answers both: what ('checked with YAML-based SodaCL: writing checks, configuration.yml data sources, soda scan runs and CI gating on the exit code') and when ('Use when warehouse data quality (Snowflake, BigQuery, Postgres, Redshift and others) should be checked') with concrete triggers.

5 / 5

Trigger Term Quality

Good natural keyword coverage ('warehouse data quality', 'Snowflake, BigQuery, Postgres, Redshift', 'checks', 'soda scan'), but misses common user variations such as 'data quality checks', 'data tests', 'data validation', or 'Soda Library'.

4 / 5

Distinctiveness Conflict Risk

Names a clear niche (SodaCL, Soda Core, Soda Cloud) with tool-specific triggers; virtually no overlap risk with adjacent data-quality or transformation tools.

5 / 5

Total

19

/

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.

Reviewed

On this page