CtrlK
BlogDocsLog inGet started
Tessl Logo

dbt-model-index

Provide a lookup index of dbt models (BigQuery tables) to guide query writing against a data warehouse. Use when you need to query, analyze, or look up data in a dbt-powered data warehouse, or when resolving a vague data question into the right BigQuery tables to query.

64

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/dbt-model-index/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 clean, well-structured template for curating a dbt model index with concrete setup guidance and useful production caveats. Its weaknesses are the lack of an explicit query workflow with validation checkpoints and the placeholder index entries that leave the core content as scaffolding.

Suggestions

Add a short 'How to query' workflow that sequences: pick the model matching the question -> check its grain and standard filters -> apply the partition/date-range filter for cost control -> run, with a checkpoint to confirm the partition filter is present before executing.

Fill at least one domain/model entry with a real example so the template demonstrates the intended level of detail (grain, key fields, useful-for patterns) rather than leaving only placeholders.

Move the standard filters, production path, and tier-value notes into a brief reference block or keep them but ensure each model entry links to its applicable standard filter so guidance is actionable per-table.

DimensionReasoningScore

Conciseness

The body is a lean template that avoids explaining concepts Claude already knows (no dbt/BigQuery primers) and keeps each section brief; minor placeholder scaffolding text could be trimmed but overall every token earns its place.

4 / 5

Actionability

'How to Set Up This Skill' gives concrete, specific guidance (table name, 1-2 sentence description, 'Useful for:' bullets, join keys, partition fields) and 'Important Notes' supplies executable examples like `where not is_internal_user` and `your-gcp-project.prod.<model_name>`; gaps remain only because the core index entries are placeholders rather than filled models.

4 / 5

Workflow Clarity

As a single-purpose lookup skill it has a clear trigger via 'When to Use', but there is no explicit query/selection workflow and the cost-control and grain guidance are stated as cautions without a validation checkpoint (e.g. confirm partition filter before running), so it sits at the 'steps present but checkpoints missing' anchor.

3 / 5

Progressive Disclosure

Content is organized into well-labeled sections (When to Use, How to Set Up, per-domain blocks, Important Notes) in a single file with no bundle files present and none needed; it is a touch over 50 lines so it does not reach the simple-skill 5, but structure is clean and navigable.

4 / 5

Total

15

/

20

Passed

Description

82%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 well-constructed description that clearly states what the skill does and when to use it, with strong trigger terms and a distinct niche. The only soft spot is specificity, since the capability is a single lookup/index action rather than a broad set of concrete operations.

DimensionReasoningScore

Specificity

Names the domain (dbt models / BigQuery tables) and a concrete action ('provide a lookup index ... to guide query writing'), but the capability is essentially a single lookup function rather than a comprehensive set of concrete actions, so it stops at the '1-2 concrete actions' anchor.

3 / 5

Completeness

Explicitly answers both 'what' (provide a lookup index of dbt models to guide query writing) and 'when' ('Use when you need to query, analyze, or look up data ... or when resolving a vague data question into the right BigQuery tables'), with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user-facing terms — 'query, analyze, or look up data', 'data warehouse', 'BigQuery tables', 'dbt' — giving good keyword coverage with common variations; a few natural synonyms (e.g. 'reporting', 'metrics') are absent, keeping it just below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

Anchored to a clear niche (dbt models / BigQuery tables / data warehouse querying) with distinct triggers and minimal overlap risk against generic SQL or analytics skills.

5 / 5

Total

17

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
warpdotdev/oz-skills
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.