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.

Quality

77%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/profiling-tables/SKILL.md

Quality

Content

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 well-structured SQL examples covering metadata, statistics, cardinality, and quality assessment. Its main weaknesses are the lack of validation/error-handling checkpoints in the workflow and some verbosity in the quality assessment section where rhetorical questions replace concrete instructions. The output format specification is a strength, giving Claude a clear template to follow.

Suggestions

Add validation checkpoints: e.g., verify the table exists and is accessible before proceeding, check row count before running expensive column-level statistics on very large tables, and handle cases where SQL functions like PERCENTILE_CONT may not be available.

Replace the rhetorical questions in Step 6 (Data Quality Assessment) with concrete SQL checks or thresholds — e.g., 'Flag columns with >20% NULLs' instead of 'Are NULLs expected or problematic?'

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 what cardinality analysis shows, and the detailed Data Quality Assessment dimensions that Claude would naturally understand). The Step 6 quality dimensions are somewhat verbose with rhetorical questions rather than actionable instructions.	2 / 3
Actionability	The skill provides fully executable SQL queries for each step, with specific column selections, functions, and patterns. The queries are copy-paste ready with clear placeholder conventions (<table>, <schema>, column_name), and the output format is explicitly defined with a markdown table template and scoring rubric.	3 / 3
Workflow Clarity	The 7-step sequence is clearly ordered and logical, progressing from metadata to statistics to quality assessment to output. However, there are no validation checkpoints — no guidance on what to do if queries fail (e.g., permission errors, unsupported functions), no feedback loops for error recovery, and no verification that the profiling results are reasonable before presenting them.	2 / 3
Progressive Disclosure	The content is well-structured with clear headers and logical sections, but it's a fairly long monolithic document (~120 lines). The detailed SQL templates for each data type and the extensive Data Quality Assessment section could potentially be split into referenced files. However, with no bundle files provided, the inline approach is acceptable for a single-file skill, though it's on the edge of being too much inline content.	2 / 3
	Total	9 / 12 Passed

Description

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 solid skill description with excellent completeness and trigger term coverage. Its main weakness is that the 'what' portion could be more specific about the concrete outputs or analyses performed (e.g., null analysis, value distributions, type inference). The explicit 'Use when' clause and prerequisite make it highly functional for skill selection.

Suggestions

Add specific concrete actions to improve specificity, e.g., 'Computes column statistics, null counts, value distributions, cardinality, and data type analysis for a specific table.'

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 includes a prerequisite ('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	The description is clearly scoped to profiling a specific table with terms like 'data profiling,' 'data quality,' and 'table's structure.' The requirement of a table name further narrows the scope, making it unlikely to conflict with general data analysis or querying skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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: 789b454

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

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.