CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

migrating-dbt-project-across-platforms

Use when migrating a dbt project from one data platform or data warehouse to another (e.g., Snowflake to Databricks, Databricks to Snowflake) using dbt Fusion's real-time compilation to identify and fix SQL dialect differences.

Quality

88%

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

The canonical home for this skill is dbt-labs/dbt-agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

Excellent actionable content: the 7-step workflow is fully executable with explicit validation gates, feedback loops, and real one-level-deep references. The only weakness is repetition — the 'trust Fusion's errors, don't pre-fix' principle is stated many times over, which could be consolidated.

Suggestions

Consolidate the 'trust Fusion's error output / don't pre-fix what Fusion hasn't flagged' guidance, which currently appears in the intro, Step 5, its own 'Trust Fusion's errors' paragraph, Don'ts #1-#2, and the Limitations section, into one authoritative statement (e.g., a single callout in Step 5).

Remove the Contents section or merge it with the Additional Resources list, since they duplicate each other's entries and anchors.

Trim restated validation criteria (0 errors/0 warnings) by referencing the single 'Success criteria' definition from the checklist and Step 7 rather than repeating the threshold inline in Step 5 and elsewhere.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious specifics (warning codes like dbt1065/dbt1005, cache clearing, versioned-model caveats) but the 'trust Fusion's errors / don't pre-fix' principle is restated roughly six times across the intro, Step 5, the 'Trust Fusion's errors' paragraph, the Don'ts, and Limitations, and the Contents section duplicates the Additional Resources list. This is noticeable tightening opportunity beyond the 'minor instances' of anchor 4, fitting anchor 3.

3 / 5

Actionability

Fully executable guidance throughout: concrete commands ('dbtf compile', 'dbt ls --select "+tag:core" --resource-type model', 'dbt show --select model_name --limit 5', 'rm -rf target/', 'dbt test --select test_type:unit'), coded warnings with specific fixes (dbt1065 → 'cast(sum(col) as decimal(18,2))'), and a copy-paste migration_changes.md template, matching anchor 5.

5 / 5

Workflow Clarity

A 7-step workflow with a copyable progress checklist, explicit validation gates at each phase (0 errors on source, unit tests pass before switching targets, 0 errors AND 0 warnings on target), and iterative fix-recompile-retest feedback loops including error-recovery guidance for failed unit tests — matching anchor 5.

5 / 5

Progressive Disclosure

A clear overview with three well-signaled, one-level-deep reference files (references/installing-dbt-fusion.md, references/generating-unit-tests.md, references/switching-targets.md), all of which exist on disk. Content is appropriately split — installation, test-generation detail, and target-switching detail live in references while the workflow stays in SKILL.md, matching anchor 5.

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: it explicitly states both what the skill does and when to use it, with concrete platform examples and natural trigger phrasing. Minor gaps in scope coverage (unit testing, target switching) and synonyms keep specificity and trigger-term quality just below maximum.

DimensionReasoningScore

Specificity

The description names the domain ('migrating a dbt project from one data platform or data warehouse to another') and concrete actions ('using dbt Fusion's real-time compilation to identify and fix SQL dialect differences') with named example platforms. It lists several specific actions but omits parts of the skill's actual scope (unit-test generation, target switching), matching anchor 4 rather than the comprehensive coverage of anchor 5 or the 1-2 actions of anchor 3.

4 / 5

Completeness

It explicitly answers 'when' with a concrete 'Use when migrating a dbt project from one data platform or data warehouse to another (e.g., Snowflake to Databricks, Databricks to Snowflake)' and 'what' with 'using dbt Fusion's real-time compilation to identify and fix SQL dialect differences', matching the anchor-5 example structure with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases users would say are well covered: 'migrating', 'dbt project', 'data platform', 'data warehouse', 'Snowflake', 'Databricks'. A few natural terms/synonyms are missing (e.g., 'port', BigQuery, Redshift), fitting anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (cross-platform dbt project migration) with distinct triggers including specific platform names and the Fusion tool. Conflict risk is minimal — only slight adjacency to a dbt version-migration skill — matching anchor 5.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

dbt-labs/dbt-agent-skills

Path

skills/dbt-migration/skills/migrating-dbt-project-across-platforms/SKILL.md

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.