CtrlK
BlogDocsLog inGet started
Tessl Logo

sql-reporting

Conventions and review steps for writing analytics SQL against the warehouse. Use whenever the task involves querying tables, building a report, or aggregating metrics.

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, well-structured instruction skill that delivers concrete SQL conventions and a pre-return validation checklist without any wasted tokens. The main gap is the absence of a worked example query tying the conventions together.

Suggestions

Add one short worked SQL example showing all conventions applied (explicit columns, partition predicate, aliased aggregate, LIMIT) to lift actionability toward copy-paste ready.

Add a brief validate->fix->retry note in the Review Checklist for cases where a query errors or returns unexpected row counts, strengthening the feedback loop for database operations.

Optionally note read-only safety explicitly (e.g., never run DDL/DML) to sharpen distinctiveness and reduce overlap with general SQL skills.

DimensionReasoningScore

Conciseness

Lean and efficient with no padding; it assumes Claude already knows what SQL and warehouses are, and every line is a concrete rule or checklist item.

5 / 5

Actionability

Concrete, specific conventions (explicit SELECT, partition predicates, snake_case aliases, LIMIT caps) and a usable checklist, but it lacks a worked executable SQL example that would make it copy-paste ready.

4 / 5

Workflow Clarity

A clear pre-return 'Review Checklist' provides an explicit validation checkpoint for these database operations, though no error-recovery feedback loop (validate -> fix -> retry) is specified.

4 / 5

Progressive Disclosure

A simple, well-organized single-file skill under 50 lines with no external references and clean sectioning (When to Use / Conventions / Review Checklist / Output Format).

5 / 5

Total

18

/

20

Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concise description that pairs a clear capability statement with an explicit trigger clause. It is somewhat generic on the 'what' side but the enumerated 'when' triggers make it highly usable.

DimensionReasoningScore

Specificity

Names the analytics-SQL domain and a few concrete actions (querying tables, building a report, aggregating metrics), but the stated capability is the abstract 'Conventions and review steps' rather than a comprehensive action list.

3 / 5

Completeness

Clearly states the 'what' ('Conventions and review steps for writing analytics SQL against the warehouse') and an explicit 'Use whenever...' clause with concrete enumerated triggers.

5 / 5

Trigger Term Quality

Natural user-facing phrases like 'querying tables', 'building a report', and 'aggregating metrics' give good keyword coverage, though common synonyms (dashboard, BI) are missing.

4 / 5

Distinctiveness Conflict Risk

'analytics SQL against the warehouse' carves a clear niche with specific triggers, leaving only minor overlap risk with generic SQL/BI or dashboard skills.

4 / 5

Total

16

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
apache/airflow
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.