analyzing-data
Queries data warehouse and answers business questions about data. Handles questions requiring database/warehouse queries including "who uses X", "how many Y", "show me Z", "find customers", "what is the count", data lookups, metrics, trends, or SQL analysis.
93
91%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
82%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 solid description with strong trigger term coverage and good completeness, explicitly addressing both what the skill does and when to use it. The main weaknesses are that the capability description could be more specific about concrete actions (e.g., writing SQL, joining tables, aggregating data) and some terms like 'metrics' and 'trends' could cause overlap with analytics-focused skills.
Suggestions
Add more specific concrete actions like 'generates SQL queries, aggregates metrics, joins tables across schemas' to improve specificity.
Narrow potentially overlapping terms by qualifying them, e.g., 'SQL-based metrics and trends from warehouse tables' to reduce conflict risk with analytics or dashboard skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (data warehouse querying) and a general action (queries data warehouse, answers business questions), but doesn't list multiple specific concrete actions like 'generate SQL queries, join tables, aggregate metrics, export results'. The actions remain somewhat high-level. | 2 / 3 |
Completeness | Clearly answers both 'what' (queries data warehouse and answers business questions about data) and 'when' (handles questions requiring database/warehouse queries including specific trigger phrases). The trigger guidance is explicit and well-enumerated. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'who uses X', 'how many Y', 'show me Z', 'find customers', 'what is the count', 'data lookups', 'metrics', 'trends', 'SQL analysis'. These closely match real user phrasing patterns. | 3 / 3 |
Distinctiveness Conflict Risk | While 'data warehouse' and 'SQL' are fairly specific, terms like 'data lookups', 'metrics', 'trends' could overlap with analytics, reporting, or dashboard skills. The broad phrase 'answers business questions about data' could conflict with BI or analytics skills. | 2 / 3 |
Total | 10 / 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 is lean, actionable, and well-structured. The workflow is clearly sequenced with caching and feedback mechanisms, the CLI reference is comprehensive yet scannable, and advanced content is appropriately delegated to reference files. It respects Claude's intelligence throughout, never explaining basic concepts.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place — no explanations of what a data warehouse is or how SQL works. The CLI reference tables are dense and scannable. No unnecessary padding or conceptual explanations. | 3 / 3 |
Actionability | Provides fully executable CLI commands and code snippets at every step. The workflow includes exact bash commands with realistic arguments, and the kernel functions table gives precise signatures and return types. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with explicit validation via pattern recording (success/failure), a clear fallback path (cache miss → discovery → query), and a mandatory caching step before presenting results. The feedback loop of pattern record --success/--failure provides error tracking. | 3 / 3 |
Progressive Disclosure | The main file provides a complete overview and working workflow, with advanced topics (large table handling, SQL templates) clearly linked to one-level-deep reference files. The CLI reference is appropriately inline as it's essential for every interaction. | 3 / 3 |
Total | 12 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- astronomer/agents
- Commit
166c98a
- 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.