answering-natural-language-questions-with-dbt
Use when a user asks a business question that requires querying data (e.g., "What were total sales last quarter?"). NOT for validating, testing, or building dbt models during development.
Install with Tessl CLI
npx tessl i github:dbt-labs/dbt-agent-skills --skill answering-natural-language-questions-with-dbt75
Quality
66%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/answering-natural-language-questions-with-dbt/SKILL.mdDiscovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has a well-structured 'Use when' clause with a helpful example and explicit exclusion, but critically fails to describe what the skill actually does. It tells Claude when to use it but not what capabilities it provides, making it difficult to understand the skill's concrete functionality.
Suggestions
Add specific actions the skill performs (e.g., 'Writes and executes SQL queries against the data warehouse to answer business questions' or 'Generates analytical queries and summarizes results').
Expand trigger terms to include common variations like 'analytics', 'metrics', 'report', 'SQL query', 'data analysis', 'KPIs'.
Clarify the data sources or systems this skill works with to improve distinctiveness (e.g., 'queries Snowflake/BigQuery' or 'accesses the production analytics database').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lacks concrete actions - it only says 'querying data' without specifying what actions the skill performs (e.g., write SQL queries, generate reports, connect to databases). The example question helps but doesn't describe capabilities. | 1 / 3 |
Completeness | Has a clear 'when' clause with explicit triggers and a helpful exclusion clause. However, the 'what' is very weak - it doesn't explain what the skill actually does beyond vaguely 'querying data'. | 2 / 3 |
Trigger Term Quality | Includes some natural terms like 'business question', 'sales', 'last quarter', and the exclusion of 'dbt models' helps. However, missing common variations like 'analytics', 'metrics', 'dashboard', 'SQL', 'database query'. | 2 / 3 |
Distinctiveness Conflict Risk | The exclusion of dbt development tasks helps distinguish it, and 'business question' provides some niche. However, 'querying data' is broad and could overlap with general SQL skills, reporting tools, or analytics skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill with excellent actionability and workflow clarity. The decision flow diagram, quick reference table, and concrete examples make it immediately usable. The 'Rationalizations to Resist' and 'Red Flags' sections are particularly valuable for preventing common errors. Minor improvement could come from splitting detailed approach documentation into separate files if the skill grows.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, assuming Claude's competence with dbt and SQL. No unnecessary explanations of basic concepts; every section serves a clear purpose with minimal padding. | 3 / 3 |
Actionability | Provides concrete, executable guidance including specific tool names, SQL examples, jq commands, and clear decision criteria. The quick reference table and code examples are copy-paste ready. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear decision flow (mermaid diagram), explicit priority ordering, and validation through the 'Red Flags - STOP' and 'Common Mistakes' sections that serve as checkpoints. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but it's a monolithic document. The four approaches could potentially be split into separate files for complex details, though the current length is manageable. | 2 / 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 — 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.