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
configuring-dbt-mcp-server
skills/dbt/skills/configuring-dbt-mcp-server/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 provides specific concrete actions, includes natural trigger terms users would actually say, explicitly states both what the skill does and when to use it, and targets a clear niche that won't conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generates MCP server configuration JSON', 'resolves authentication setup', and 'validates server connectivity'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (generates config JSON, resolves auth, validates connectivity) AND when ('Use when setting up, configuring, or troubleshooting the dbt MCP server for AI tools...'). Explicit trigger guidance is present. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'MCP server', 'dbt', 'configuration', 'Claude Desktop', 'Claude Code', 'Cursor', 'VS Code', 'setting up', 'configuring', 'troubleshooting'. Good coverage of tool names and action terms. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche: dbt MCP server configuration for specific AI tools. The combination of 'dbt', 'MCP server', and the named tools (Claude Desktop, Cursor, VS Code) creates a distinct trigger profile unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong skill with excellent actionability and workflow clarity. The configuration templates are copy-paste ready, client-specific instructions are clear, and verification steps are explicit. Minor verbosity in the comparison tables and some redundant descriptions prevent a perfect conciseness score, but overall this skill effectively guides users through dbt MCP server setup.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some redundant information in the comparison tables (e.g., 'Local Server' description repeats platform connection capabilities twice). The decision flow diagram and tables add value but could be tighter. | 2 / 3 |
Actionability | Provides fully executable JSON configurations, specific commands (uvx, claude mcp add), exact file paths, and copy-paste ready templates for each client. The verification steps include concrete test commands. | 3 / 3 |
Workflow Clarity | Clear decision flow with mermaid diagram, numbered setup steps for each client, explicit verification steps ('No errors = successful configuration'), and a logical question-based flow to determine the right configuration. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections, appropriate use of tables for comparisons, and one-level-deep references to external docs (finding-credentials.md, troubleshooting.md, environment-variables.md). Core content is inline while detailed references are linked. | 3 / 3 |
Total | 11 / 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 | |