dbt-labs/dbt-agent-skills
A curated collection of Agent Skills for working with dbt, to help AI agents understand and execute dbt workflows more effectively.
91
Does it follow best practices?
Validation for skill structure
running-dbt-commands
skills/dbt/skills/running-dbt-commands/SKILL.md
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that excels across all dimensions. It uses third person voice, provides specific capabilities, includes natural trigger terms that dbt users would actually say, and clearly delineates both what the skill does and when to use it. The focus on dbt-specific operations makes it highly distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Formats and executes dbt CLI commands, selects the correct dbt executable, and structures command parameters.' These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (formats/executes dbt CLI commands, selects executable, structures parameters) AND when (running models/tests/builds/compiles/show queries, unsure about executable or parameter formatting) with explicit 'Use when' clauses. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'dbt CLI', 'running models', 'tests', 'builds', 'compiles', 'show queries', 'dbt executable', 'command parameters'. Good coverage of dbt-related terminology. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on dbt CLI operations with distinct triggers like 'dbt executable', 'dbt CLI', and specific dbt operations (models, tests, builds). Unlikely to conflict with general CLI or database skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that exemplifies best practices. It's highly actionable with executable commands, efficiently organized with tables and clear sections, and respects Claude's intelligence by avoiding unnecessary explanations. The Common Mistakes section adds significant value by preventing known failure modes.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Every section provides actionable information without explaining concepts Claude already knows. No padding about what dbt is or how CLI tools work - jumps straight to practical guidance. | 3 / 3 |
Actionability | Fully executable commands throughout with copy-paste ready examples. Concrete bash commands, specific flag combinations, and real jq queries for analyzing results. The quick reference and examples are immediately usable. | 3 / 3 |
Workflow Clarity | Clear preferences hierarchy (MCP tools > build > run/test), explicit validation pattern with `dbt list` before running, and the Common Mistakes table serves as a checklist. The workflow of preview-then-execute is well-established. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections progressing from quick reference to detailed topics. Tables provide scannable information. Content is appropriately contained in a single file given the scope - no need for external references for this focused skill. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |