checking-freshness

Quick data freshness check. Use when the user asks if data is up to date, when a table was last updated, if data is stale, or needs to verify data currency before using it.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

70%

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

The skill body is highly actionable with executable SQL, concrete commands, and a clear output format, and is well organized as a single self-contained file. Its main gaps are a lack of an explicit validation/feedback loop in the staleness diagnosis workflow and minor token padding in the explanatory sections.

Suggestions

Add an explicit validation checkpoint before escalating stale data, e.g. confirm the freshness result is not a transient query/cache issue and re-query to verify before diagnosing the Airflow DAG.

Tighten the timestamp-column and Airflow/Astro/OSS sections by trimming explanatory prose Claude can already infer, keeping only the column lists and command syntax.

Make the stale-data investigation a numbered workflow with a retry/feedback loop (find DAG -> check status -> if failed, debug -> re-run freshness check to confirm resolution) rather than a loose bullet list.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with copy-ready SQL and a tight status table, but the timestamp-column lists and Airflow/Astro/OSS sections include explanatory phrasing Claude could infer, so it is not fully lean.	2 / 3
Actionability	It supplies complete executable SQL queries with real functions (TIMESTAMPDIFF, DATE_TRUNC, DATEADD), concrete `af` commands, and a copy-paste output template, which is fully actionable.	3 / 3
Workflow Clarity	The freshness process is sequenced, but the staleness investigation is a batch/diagnostic operation with no explicit validation checkpoint confirming staleness is real before escalating, capping it at 2 per the destructive/batch guidance.	2 / 3
Progressive Disclosure	It is a self-contained, well-organized single file with clear section headers and no nested external references, which is appropriate for a skill with no bundle files.	3 / 3
	Total	10 / 12 Passed

Description

85%

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

The description is well-formed: concise, third person, with an explicit 'Use when' trigger clause and strong natural-language trigger terms. Its only mild weakness is specificity, since it summarizes the capability as a single action rather than listing multiple concrete operations.

Dimension	Reasoning	Score
Specificity	"Quick data freshness check" names the domain and a single concrete action (freshness check) but does not list multiple specific concrete actions, matching the 'names domain and some actions' anchor.	2 / 3
Completeness	It states what it does ("Quick data freshness check") and gives an explicit "Use when..." clause enumerating trigger conditions, satisfying both what and when.	3 / 3
Trigger Term Quality	Natural user phrases like "if data is up to date", "when a table was last updated", "if data is stale", and "verify data currency" give strong coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The data-freshness/currency niche is narrow and the triggers are distinct, making it unlikely to fire for unrelated 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: astronomer/agents
Commit: 8827e93

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.