CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/dbt-testing

Use for any question or task about testing dbt models, including adding tests to a model's YAML and bad data such as duplicate IDs that a passing dbt build missed: generic, singular and custom-macro tests, model assertions, reading failures from run_results.json and gating dbt build on the results in CI.

Quality

89%

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

Overview
Quality
Evals
Security
Files

Quality

Content

86%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.

High-quality content: dense with non-obvious dbt-specific gotchas, fully executable examples, and a well-executed two-file progressive-disclosure structure. The only trimming opportunities are the over-complete run_results.json field table and inline version annotations.

DimensionReasoningScore

Conciseness

Mostly lean: the body concentrates on non-obvious, version-specific knowledge Claude cannot be assumed to know (the data_tests/tests rename, the 'arguments:' key, NULL semantics of accepted_values/relationships, the trailing-semicolon trap, incremental unit-test 'expect' semantics). Minor over-explanation could be trimmed — e.g. the run_results.json field table includes entries (execution_time, timing, adapter_response, relation_name) beyond what failure parsing needs, and version notes ('v1.9', 'v1.10') sit inline rather than in a compat section — so it sits at 'efficient; minor instances' rather than anchor 5.

4 / 5

Actionability

Fully executable throughout: copy-paste YAML for generic and unit tests, a working singular-test SQL file, a complete {% test %} macro, runnable dbt CLI selectors, jq one-liners for failure triage, and a freshness config block. The gap table pairs each silent-failure mode with a concrete fix, covering the common cases.

5 / 5

Workflow Clarity

The lifecycle is clearly sequenced (when to use → authoring → silent-failure checklist → running → parsing failures → CI gating) with an explicit checkpoint ('Check these before calling a model "tested"') and error-path handling (fail vs error statuses, severity downgrade to warn). It falls short of anchor 5 only in lacking an explicit fix-and-rerun feedback loop; the CI steps themselves are delegated to the reference file.

4 / 5

Progressive Disclosure

Clear overview with bulk detail correctly split into two real, one-level-deep references, each signaled inline at the point of need ('See references/macros.md for the canonical macro shapes') and again in a References section. Verified both files exist, contain the promised content, and nest no further references (only external dbt doc URLs).

5 / 5

Total

18

/

20

Passed

Description

87%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 with explicit use-when guidance, concrete trigger phrases, and multiple specific capabilities anchored to dbt-specific terminology. Its only weakness is coverage: unit tests and source freshness — both substantive parts of the body — are not surfaced in the description.

DimensionReasoningScore

Specificity

Names the domain ('testing dbt models') and multiple concrete actions ('adding tests to a model's YAML', 'generic, singular and custom-macro tests', 'reading failures from run_results.json', 'gating dbt build on the results in CI'). Minor gaps in coverage — unit tests and source freshness, both covered by the body, are absent from the description — so it fits 'several specific actions; minor gaps' rather than the comprehensive anchor 5.

4 / 5

Completeness

Explicitly answers both questions: the 'when' is 'Use for any question or task about testing dbt models, including... bad data such as duplicate IDs that a passing dbt build missed', and the 'what' is the enumerated capability list. The when-clause includes concrete trigger phrases, matching the anchor-5 example pattern rather than anchor 4's generic 'Use when working with PDF files'.

5 / 5

Trigger Term Quality

Good natural keyword coverage: 'testing dbt models', 'dbt build', 'duplicate IDs that a passing dbt build missed', 'CI', 'run_results.json', 'model assertions'. A few natural terms a user might say are missing (e.g. 'unique', 'not_null', 'data quality'), placing it just below the anchor-5 synonym-and-extension level.

4 / 5

Distinctiveness Conflict Risk

Clear niche (dbt data testing) with dbt-specific triggers ('dbt build', 'run_results.json', 'generic/singular/custom-macro tests') that no non-dbt skill would fire on; minimal conflict risk even against a hypothetical general dbt skill.

5 / 5

Total

18

/

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