agentsclimarketplace

Data quality audit

Skill motao123/dev-workflow-kit/data-quality-audit

21 markdown-first software delivery workflow skills for Claude Code, Codex, and compatible agents. Standalone skill kit covering planning, debugging, CI, review, security, rollout, performance, data quality, and post-incident workflows.

Install
npx -y skills add motao123/dev-workflow-kit --skill data-quality-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when existing data correctness, freshness, completeness, or constraint integrity is in question at runtime, distinct from migration-time safety.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.9 KB, as published. Nobody here has run it

Data Quality Audit

Use this skill when the runtime data itself may be wrong, stale, incomplete, or inconsistent.

Trigger Conditions

Use this skill when:

  • a dataset, table, or event stream has suspect values
  • nullability, uniqueness, foreign-key, or enum integrity may be violated
  • freshness or completeness is in question
  • duplicate, drifted, or orphaned records are suspected
  • the team wants a data-trust pass before a release or downstream use

Do not use this skill for migration planning, code-path debugging, or schema design.

Workflow

  1. Identify the dataset under review and its purpose.
  2. List the relevant quality dimensions: correctness, completeness, freshness, uniqueness, referential integrity, schema conformance.
  3. Surface anomalies and likely failure modes.
  4. Separate critical issues from low-priority cleanup.
  5. Recommend remediation and verification.
  6. Note follow-up monitoring or contracts to add.

Output

For non-trivial work, provide:

  • dataset under review
  • quality dimensions checked
  • key anomalies and severity
  • recommended remediation
  • verification or monitoring suggestions

Coordination

After data audit:

  • use data-migration-safety-review if remediation needs schema or backfill changes
  • use systematic-debugging if anomalies look code-driven
  • use docs-writer if data contracts or runbooks need to be published

Invocation Examples

  • "Use data-quality-audit from dev-workflow-kit to assess freshness, completeness, and correctness of this dataset."
  • "Use data-quality-audit to check whether this table has duplicate or orphaned rows before we expose it."
  • "Use data-quality-audit because downstream reports look wrong but the code path seems fine."

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.