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.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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 description with excellent trigger terms and completeness, clearly answering both what and when. Its main weakness is the lack of specificity in concrete actions—'Quick data freshness check' is somewhat vague about what the skill actually does mechanically. Adding 1-2 specific actions would elevate it further.
Suggestions
Add specific concrete actions to the 'what' portion, e.g., 'Checks table metadata timestamps, compares last refresh dates, and reports data age' instead of just 'Quick data freshness check'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (data freshness) and implies actions like checking if data is up to date or stale, but doesn't list specific concrete actions (e.g., 'queries metadata timestamps', 'compares last update against threshold', 'checks table modification dates'). | 2 / 3 |
Completeness | Clearly answers both what ('Quick data freshness check') and when ('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') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'up to date', 'last updated', 'stale', 'data freshness', 'data currency'. These cover common variations of how users would phrase this need. | 3 / 3 |
Distinctiveness Conflict Risk | The focus on data freshness/staleness/currency is a clear niche that is unlikely to conflict with other skills. The trigger terms are specific to temporal data validation rather than general data processing. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, actionable skill that provides clear SQL queries, a defined freshness scale, and a logical escalation workflow for stale data. Its main weakness is moderate verbosity—the Astro/OSS sections and some explanatory text could be trimmed. The workflow is well-sequenced with natural validation checkpoints through the freshness status classification.
Suggestions
Trim the Astro and OSS Airflow subsections into a more concise format—Claude can infer UI-based checks from the platform context without detailed bullet points.
Consider condensing the timestamp column discovery list; a shorter representative set with a note to check INFORMATION_SCHEMA would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary detail. The list of common timestamp column names is helpful but slightly verbose, and the Astro/OSS Airflow sections add moderate bulk. The freshness status table and output format are well-structured but the overall content could be tightened. | 2 / 3 |
Actionability | Provides fully executable SQL queries with clear placeholders, concrete CLI commands for Airflow investigation (af dags list, af dags get, af dags stats), a specific freshness threshold table, and a concrete output format template. Guidance is copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear three-step sequence (find timestamp → query last update → check row counts) with a well-defined escalation path when data is stale (check Airflow → find DAG → diagnose). The workflow naturally includes validation through the freshness status table and branches to the debugging-dags skill when issues are found. | 3 / 3 |
Progressive Disclosure | The skill references the debugging-dags skill appropriately for escalation, but the Astro vs OSS Airflow sections and the detailed output format template could potentially be split out. For a standalone skill with no bundle files, the inline content is somewhat long but reasonably organized with clear headers. | 2 / 3 |
Total | 10 / 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.