Skip to content
Get packs

Analyze Data Quality

Checks whether a dataset or metric is trustworthy enough to analyze, model, or cite.

Source Download skill
Repository
XiaomiMiMo/MiMo-Code
Stars
13,743
Licence
MIT
Files
2 files

What it does

When installed, the agent treats a request to judge data as a structured audit. It clarifies what the data represents and its intended grain, profiles it (row counts, keys, duplicates, null rates, date ranges), runs completeness, uniqueness, validity, consistency, integrity, timeliness and volume checks, and looks for changes over time. It then reports concrete evidence, the analytical risk, likely causes, and the smallest fix or automated test, and prefers putting the SQL or Python behind its findings in a companion notebook so a person can inspect it.

Great for

  • Analysts who need to decide whether a dashboard or query result can be cited
  • Data engineers investigating sudden drops, duplicates or missing partitions after a release or migration
  • Teams validating experiment or ML feature tables before use

Skip it if

  • Designing KPIs or metric targets, which is a different skill (design-kpis) and not about checking existing data
  • Reviewing a finished report or chart for errors in its conclusions, which is better handled by a QA skill (validate-data)
  • Sensitive production data without review: the workflow may run queries against live tables through connectors, so check permissions first

Try asking

  • “Check whether our orders table is trustworthy enough to use for the Q3 revenue analysis”
  • “Two dashboards disagree on active users; reconcile the sources and tell me which to cite”
  • “Signups dropped suddenly after March 4th; investigate whether this is a data issue”
  • “Profile this events table for duplicate event IDs and future timestamps”
Step-by-step guide: how to use Analyze Data QualityInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    analyze-data-quality.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip analyze-data-quality.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip analyze-data-quality.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • State the grain, primary key and time zone up front so the agent does not have to guess.
  • Give a trusted reference table or prior period as a baseline for reconciliation.
  • Ask for the notebook path to rerun the checks later or turn stable rules into automated tests.

What's inside

  • agents/openai.yaml
  • SKILL.md

Redistributed unmodified from XiaomiMiMo/MiMo-Code under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.