profiling-tables
Deep-dive data profiling for a specific table. Use when the user asks to profile a table, wants statistics about a dataset, asks about data quality, or needs to understand a table's structure and content. Requires a table name.
62
73%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/profiling-tables/SKILL.mdQuality
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 a clear 'Use when...' clause and good trigger terms that users would naturally employ. Its main weakness is that the capabilities described are somewhat general—'deep-dive data profiling' could be more specific about what concrete outputs or analyses are performed. There is also moderate overlap risk with other data analysis or exploration skills.
Suggestions
Add specific concrete actions to improve specificity, e.g., 'Computes column-level statistics (nulls, uniqueness, distributions), detects data quality issues, and summarizes table structure.'
Differentiate from related skills by clarifying what makes this a 'deep-dive' profile versus a quick summary or general data analysis, e.g., mention specific outputs like histograms, pattern detection, or anomaly flagging.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain ('data profiling') and mentions some actions like 'statistics about a dataset' and 'understand a table's structure and content,' but it doesn't list multiple specific concrete actions (e.g., null counts, distribution analysis, cardinality checks, outlier detection). | 2 / 3 |
Completeness | Clearly answers both 'what' (deep-dive data profiling for a specific table) and 'when' (explicit 'Use when...' clause listing multiple trigger scenarios). Also notes a requirement ('Requires a table name'), which adds useful context. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'profile a table,' 'statistics about a dataset,' 'data quality,' 'table's structure and content,' and 'table name.' These are terms users would naturally use when requesting this kind of analysis. | 3 / 3 |
Distinctiveness Conflict Risk | While 'data profiling' and 'table' provide some specificity, this could overlap with general data analysis, data exploration, or schema inspection skills. The description doesn't strongly differentiate itself from broader data analysis tools. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable data profiling skill with concrete SQL examples and a well-defined output format. Its main weaknesses are the lack of validation/error-handling checkpoints in the workflow and some verbosity in explanatory sections that Claude doesn't need. The step-by-step structure is clear but could benefit from explicit guidance on handling edge cases (very large tables, permission errors, missing columns).
Suggestions
Add validation checkpoints: verify the table exists and is accessible before running statistics, and include guidance for handling query failures or timeouts on large tables.
Trim the explanatory text in Steps 4 and 6 — remove rhetorical questions and 'This reveals:' bullets that Claude can infer from the query results.
Add a note about batching column statistics into a single query where possible to avoid excessive round-trips on wide tables.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with concrete SQL examples, but includes some unnecessary explanatory text (e.g., 'This reveals:' bullet points explaining cardinality, the 'If the table is large and you want variety' suggestion). The Data Quality Assessment section (Step 6) is somewhat verbose with rhetorical questions that Claude could infer. However, it's not egregiously padded. | 2 / 3 |
Actionability | The skill provides fully executable SQL queries for each step, with specific column selections and functions. The queries are copy-paste ready with clear placeholder conventions (<table>, <schema>). The output format is also concretely specified with a markdown table template and scoring rubric. | 3 / 3 |
Workflow Clarity | The 7-step sequence is clearly ordered and logical, but there are no validation checkpoints or feedback loops. For instance, there's no guidance on what to do if a query fails, if the table is too large for certain statistics, or how to handle errors in column-level statistics. The skill also doesn't mention verifying that the table exists before proceeding through all steps. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear section headers and a logical progression, but it's a fairly long monolithic document (~120 lines). The column-level statistics section with three sub-types and the data quality assessment could potentially be split into referenced files. However, with no bundle files provided, the inline approach is acceptable for a single skill file, though it borders on too much detail in one place. | 2 / 3 |
Total | 9 / 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.