AC cm-data-quality-validator
Validate data quality in pipelines by checking completeness, consistency, freshness, accuracy, and distribution anomalies. Define expectations, profile data distributions, detect schema drift, identify outliers, and generate quality reports. Use when asked to validate data quality, audit pipeline data, check data completeness, detect data anomalies, profile datasets, review data freshness, or set up data quality checks. Triggers on "data quality", "data validation", "data completeness", "data freshness", "data profiling", "data anomaly", "data consistency", "data expectations", "pipeline quality", "great expectations", "data audit", "schema drift".
As a process C 51/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, consistency
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5499 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 51/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (cm-data-quality-validator) differs from the folder (data-quality-validator)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5499 tokens
- 100Steps. 17 steps
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 12 example trigger phrases
- +3Description length 656: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 17 items
- +3Output format is stated explicitly
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.