1.2.0

Data quality validation patterns for daily checks and anomaly follow-up.

Security Scan

The skill's files and instructions match its stated purpose of providing data-quality run patterns and templates; nothing requests extra credentials or installs arbitrary code, though there are small naming/copy-paste inconsistencies to check.

Purpose & Capability

The SKILL.md, templates, and tiny helper scripts are coherent with a data-quality operations checklist/reporting skill. However, the top-level name shown as "1.2.0" and the healthcheck script echoing a different skill name ("pipiwu-benchmark-delta-skill") look like copy-paste or packaging lapses—these are sloppy but not inherently dangerous.

Instruction Scope

Runtime instructions are limited to running external commands (dq profile/validate/anomaly and workflow checklist/report) and using included templates; the SKILL.md does not instruct reading unrelated system files or exporting data to unknown endpoints. Note: the actual behavior depends on what the external 'dq' and 'workflow' binaries/tools do—those tools could contact services or require credentials, but that is outside this skill's files.

Install Mechanism

There is no install spec and only two tiny shell scripts plus templates are included. No downloads or archive extraction are present.

Credentials

The skill declares no required environment variables, no credentials, and the SKILL.md does not reference any secrets or unexpected env vars. This is proportionate for a checklist/reporting template skill.

Persistence & Privilege

The skill is not always-enabled and does not request elevated persistence. Model invocation is allowed (default), which is normal for user-invocable skills and not a red flag here.

Assessment

This skill appears to be a set of runbooks/templates for data-quality checks and is internally consistent. Before installing, verify what the 'dq' and 'workflow' commands are on your system (which binaries or services they map to), and confirm you trust those tools — they will perform the actual work and might require credentials or network access. Also note the small naming inconsistencies (package name/version/healthcheck text) which look like copy-paste errors; they are not dangerous but you may want to ask the publisher to correct them for clarity.

Data Quality Operations

Use when dataset freshness/completeness checks must be run consistently.

Inputs to Gather

• Primary target (service, team, or dataset)
• Current impact and urgency
• Assigned owner and deadline

Core Commands

• dq profile --dataset <name>
• dq validate --rule-set <id>
• dq anomaly --open --metric <name>
• workflow checklist --from templates/checklist.md
• workflow report --from templates/report.md

Operating Notes

• Prefer explicit owner assignment before action.
• Keep timeline notes concise and timestamped.
• Save output artifacts for audit and handoff.
• This version adds a structured report template for post-task summaries.

Version marker: data-quality-operations 1.2.0