configuring-dbt-mcp-server
Use when setting up, configuring, or troubleshooting the dbt MCP server for AI tools like Claude Desktop, Claude Code, Cursor, or VS Code.
Install with Tessl CLI
npx tessl i github:dbt-labs/dbt-agent-skills --skill configuring-dbt-mcp-server84
Quality
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Discovery
89%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-structured description with excellent trigger terms and clear 'Use when' guidance. The main weakness is that the capabilities could be more specific about what concrete actions the skill enables beyond the general verbs 'setting up, configuring, troubleshooting'. The description effectively carves out a distinct niche.
Suggestions
Add specific concrete actions like 'edit configuration files', 'validate server connections', 'resolve authentication errors', or 'update environment variables' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (dbt MCP server) and general actions (setting up, configuring, troubleshooting), but doesn't list specific concrete actions like 'edit config files', 'validate connections', or 'resolve authentication errors'. | 2 / 3 |
Completeness | Explicitly answers both what (setting up, configuring, troubleshooting dbt MCP server) and when (starts with 'Use when...') with clear trigger conditions for AI tools. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'dbt', 'MCP server', 'Claude Desktop', 'Claude Code', 'Cursor', 'VS Code', plus action terms like 'setting up', 'configuring', 'troubleshooting'. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche combining 'dbt MCP server' with specific AI tool names creates a distinct trigger profile unlikely to conflict with general coding or database skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill for configuring dbt MCP servers across multiple clients. The decision flow diagram and comprehensive configuration templates are excellent. However, the skill is quite long and could benefit from splitting detailed reference material (credentials, troubleshooting, env vars) into separate files, and some redundant explanations could be trimmed.
Suggestions
Move 'How to Find Your Credentials', 'Troubleshooting', and 'Environment Variable Reference' sections to separate linked files to improve progressive disclosure
Remove redundant mentions of OAuth requirements and token type explanations that appear in multiple places
Consider consolidating the 'Common Mistakes' and 'Troubleshooting' sections as they have overlapping content
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundant explanations (e.g., repeated information about token types, OAuth requirements mentioned multiple times). Tables are efficient but some sections could be tightened. | 2 / 3 |
Actionability | Provides fully executable JSON configurations, specific commands for each client, and copy-paste ready code blocks. Clear step-by-step instructions with exact paths and commands for verification. | 3 / 3 |
Workflow Clarity | Excellent decision flow diagram, clear sequential steps for each client setup, explicit verification steps, and a troubleshooting section with specific fixes. The 'Questions to Ask' section provides a clear guided workflow. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and tables, but everything is in one large file. The credential finding instructions, troubleshooting, and environment variable reference could be split into separate files with links from the main skill. | 2 / 3 |
Total | 10 / 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 — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 16 Passed | |
- 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.