Data Data Quality
Use when the user asks to add data quality checks to the pipeline, data validation, Great Expectations (GX Core), dbt tests, Soda checks, data profiling or quality dimensions and SLAs. Produces check suites, thresholds and where they run in the pipeline. Not for test strategy and regression diffs (use data-testing) or monitoring (use data-data-observability).
Install
npx skills add j4flmao/agent-skills --skill data-data-qualitygit clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/data/data-quality ~/.claude/skills/data-data-qualityPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Data Data Quality ## Purpose Build a data quality framework covering quality dimensions (completeness, accuracy, timeliness, consistency, uniqueness, integrity), automated validation tests (Great Expectations expectations suites, data docs, checkpoints; dbt singular, generic, freshness tests), data observability (Soda, Monte Carlo, Elementary), data SLAs with escalation paths, and data contracts. ## Agent Protocol ### Trigger Exact user phrases: "data quality", "data validation", "data profiling", "Great Expectations", "dbt tests", "data observability", "data contract", "schema validation", "data quality check", "data testing", "data monitoring", "quality dimensions", "data freshness", "data completeness", "Soda", "Monte Carlo", "data SLA", "data integrity". ### Input Context Before activating, verify: - Data stack (warehouse, lake, streaming platform) - Transformation tool (dbt, Spark, custom SQL) - Data sources and producers (internal, external, partner) - Existing monitoring and alerting infrastructure - Critical data assets for business operations - Data consumers and their quality SLAs ### Output Artifact Data quality framework with dimension definitions, test configurations, monitoring setup, and contract templates. ### Response Format ```yaml # Quality dimension definitions # Great Expectations suite # dbt test config # Data contract template # Alert rules # SLA definitions ``` No preamble. No postamble. No explanations. No filler/hedging/transitions.
Details
- Skill name
data-data-quality- Repository
- j4flmao/agent-skills
- Path
skills/data/data-quality/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Data Data Quality skill do?
Use when the user asks to add data quality checks to the pipeline, data validation, Great Expectations (GX Core), dbt tests, Soda checks, data profiling or quality dimensions and SLAs. Produces check suites, thresholds and where they run in the pipeline. Not for test strategy and regression diffs (use data-testing) or monitoring (use data-data-observability).
How do I install the Data Data Quality skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill data-data-quality. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Data Data Quality popular?
It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.
Related skills
Agent Observability
45j4flmao/agent-skills
Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).
AI Agent Architectures
45j4flmao/agent-skills
Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).
AI Agent Core Loop
45j4flmao/agent-skills
Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).
Data Testing
45j4flmao/agent-skills
Use when the user asks about dbt unit tests, data regression testing, data-diff / Datafold, Soda or GX tests in CI, or testing data pipelines before deploy. Produces a layered data test strategy with unit, contract and diff tests. Not for runtime quality monitors (use data-data-observability) or CI wiring (use data-pipeline-cicd).
Cloud Native Distributed Tracing
45j4flmao/agent-skills
Use when the user asks about traceparent and W3C trace context, baggage, tail vs head sampling, tracing Kafka messages, span links, or Jaeger/Tempo trace correlation across services. Produces an end-to-end tracing design: propagation, sampling and collector topology. Not for OTel SDK and Collector rollout (use devops-opentelemetry) or metrics alerting (use prometheus-grafana).
Dev Loop Performance Profiler
45j4flmao/agent-skills
Use when the user asks to profile slow code, find a CPU or memory bottleneck, read a flame graph, use pprof, py-spy, perf or Chrome DevTools profiler, or chase a memory leak or high latency. Produces a measure-first profiling plan and targeted optimizations. Not for functional bugs (use dev-loop-debugging-strategy) or load tests (use quality-load-testing).
Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.