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.
74
91%
Does it follow best practices?
Impact
—
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. Its main weaknesses are moderate specificity in describing concrete actions and some potential overlap risk with other data-related skills. The natural language trigger examples ('who uses X', 'how many Y') are particularly effective for skill selection.
Suggestions
Add more specific concrete actions like 'generates SQL queries, aggregates metrics, joins tables across schemas, produces summary reports' to improve specificity.
Differentiate more clearly from potential analytics or BI skills by specifying the type of data warehouse (e.g., Snowflake, BigQuery) or emphasizing that this is for ad-hoc querying rather than dashboard creation or data visualization.
| 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 'when' guidance is explicit with concrete examples of triggering phrases. | 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 how users naturally phrase data questions. | 3 / 3 |
Distinctiveness Conflict Risk | While it specifies data warehouse querying, terms like 'data lookups', 'metrics', 'trends' could overlap with analytics/BI skills or general data analysis skills. The SQL and warehouse focus helps but 'business questions about data' is broad enough to potentially conflict with other data-oriented 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 efficiently teaches Claude a complex multi-step data analysis workflow. It combines a clear sequential workflow with comprehensive CLI reference documentation, all while remaining concise and actionable. The caching strategy (concepts, patterns, table schemas) adds a sophisticated learning loop that makes the skill more effective over repeated use.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It assumes Claude knows SQL, Python, and data analysis concepts. Every section serves a purpose—no explanations of what a data warehouse is or how SQL works. The CLI reference tables are compact and scannable. | 3 / 3 |
Actionability | Every step includes exact, copy-paste-ready CLI commands. The workflow provides concrete bash commands for each phase (pattern lookup, concept lookup, table discovery, query execution, caching). The kernel functions table gives precise signatures and return types. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with a logical progression from cache lookup → discovery → execution → caching → presentation. It includes feedback loops (pattern record success/failure) and conditional branching (if cache misses, search codebase). Validation is implicit but appropriate—the pattern record step serves as an outcome verification mechanism. | 3 / 3 |
Progressive Disclosure | The SKILL.md provides a clear overview with the workflow and CLI reference inline (appropriately, as they're essential), while pointing to one-level-deep references for advanced topics: discovery-warehouse.md for large table handling and common-patterns.md for SQL templates. Navigation is well-signaled with descriptive labels. | 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
535a040
- 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.