CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

working-with-dbt-mesh

Use when changing a dbt model in a way that could break its consumers — renaming, removing, or retyping a column, or changing a model that downstream models, exposures, dashboards, or BI tools depend on — to judge whether the change is breaking and who it affects. Also use when versioning a model (model versions, latest_version, latest_version_pointer, deprecation_date, migration windows), enforcing contracts, setting access or groups, or doing multi-project dbt Mesh work (cross-project refs via dependencies.yml, disambiguating similarly-named models, splitting a monolith). Covers single- and multi-project, and planning or advising as well as implementing.

Quality

96%

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

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.

A strong, highly actionable skill body: executable examples, explicit validation checkpoints in the migration workflow, and a clean one-level-deep split across four real reference files. The only real cost is token weight — the Common Mistakes table and When to Use section restate content that already appears elsewhere in the skill or frontmatter.

Suggestions

Trim the Common Mistakes table to rows that add new information beyond the body (e.g., the alias-fallback, latest-version-bump, contract-on-staging, and Enterprise rows already covered in Decision Framework and earlier sections), or move it to a reference file.

Compress the "When to Use" section, which duplicates the frontmatter description's triggers; keep only the "Do NOT use for" pointers to sibling skills, which are new information.

Consider condensing the correct/wrong YAML pair in "YAML placement rule" to the rule plus the correct example, since the inverted wrong example largely repeats the same keys.

DimensionReasoningScore

Conciseness

The body is dense with genuinely non-obvious dbt Mesh specifics (pointer mechanisms, access resolution, Fusion YAML parsing), but the 17-row Common Mistakes table restates several earlier points (alias fallback, latest-version bump, contract-on-staging, Enterprise gating) and "When to Use" largely duplicates the frontmatter description. Efficient overall with trimmable redundancy — not a 3, since almost nothing explains concepts Claude already knows.

4 / 5

Actionability

Guidance is copy-paste ready throughout: correct/wrong two-argument ref() pairs, a dependencies.yml snippet, correct/wrong YAML config-nesting examples, a runnable verification command (dbt show --inline "select <old_col> from {{ target.schema }}.<unsuffixed_relation>"), and concrete decision trees covering the common cases.

5 / 5

Workflow Clarity

The orientation steps are clearly sequenced (read dependencies.yml → understand ref flow → disambiguate → check patterns → check access), and the migration workflow is a two-deploy sequence with an explicit post-deploy validation step and error-recovery interpretation ("A column does not exist error means latest_version was promoted too early"). Validation is present for these breaking-change operations, so no cap applies.

5 / 5

Progressive Disclosure

SKILL.md serves as a genuine overview (core principle, decision frameworks, common mistakes) while all four referenced files exist, are substantive, clearly signaled via the governance table's Reference column and inline links with anchors, and are one level deep (reference files link only to siblings/own anchors).

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.

An exemplary description: it defines a precise niche, lists concrete capabilities, and provides explicit, multi-surface "Use when" triggers covering both single- and multi-project contexts. Every clause carries trigger or capability information with no padding.

DimensionReasoningScore

Specificity

The description enumerates concrete actions across the whole domain — "renaming, removing, or retyping a column", "versioning a model", "enforcing contracts, setting access or groups", "cross-project refs via dependencies.yml", "splitting a monolith" — comprehensive coverage matching the anchor-5 example's breadth.

5 / 5

Completeness

Explicit "Use when..." clauses state the triggers, and the what is stated concretely ("to judge whether the change is breaking and who it affects... planning or advising as well as implementing"), so both what and when are explicitly answered with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user phrasings ("renaming a column", "break its consumers", "dashboards, or BI tools", "migration windows", "splitting a monolith") are combined with exact technical tokens users would echo back (dependencies.yml, latest_version, deprecation_date), giving comprehensive keyword coverage.

5 / 5

Distinctiveness Conflict Risk

It carves out a clear niche — dbt Mesh governance and breaking-change management — with triggers (cross-project refs, contracts, access/groups, model versions) that no generic dbt or analytics skill would claim, so conflict risk is minimal.

5 / 5

Total

20

/

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/skills/working-with-dbt-mesh/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.