Data Quality Claw
data-quality-claw
v0.2.0May 28, 2026Find the NULLs, duplicates, and silent corruption dashboards hide — then wire quality gates into CI
Finds the NULLs, duplicates, and silent corruption that dashboards hide. Builds quality scorecards with completeness, uniqueness, and freshness metrics — then wires them into CI so bad data never reaches production.
PRIMARY ACTION
Unlock with ProWhen to Use
- Design clean data workflows
- Plan reliable ETL and quality checks
- Track metrics and pipeline health
- Deliver maintainable data outputs
Compatible Frameworks
8 TOOLs
Quality Gates
- Completeness score above 95%
- Uniqueness check on keys
- Outlier detection thresholds configured
- Schema validation passes
4 GATEs DEFINED
Expected Outputs
Native exports per tool
openclaw/AGENTS.mdopenclaw/SOUL.mdopenclaw/TOOLS.md+7 morehermes/skills/flickclaw/data-quality-claw/SKILL.mdhermes/skills/flickclaw/data-quality-claw/references/workflow.mdhermes/skills/flickclaw/data-quality-claw/references/quality-gates.md+2 moreclaude-code/CLAUDE.mdclaude-code/.claude/skills/data-quality-claw/SKILL.mdclaude-code/.claude/skills/data-quality-claw/references/workflow.md+3 morecodex/AGENTS.mdcodex/.flickclaw/agents/data-quality-claw/codex.mdcodex/.flickclaw/agents/data-quality-claw/workflow.md+2 morecursor/.cursor/rules/flickclaw-data-quality-claw.mdccursor/.cursor/rules/flickclaw-data-quality-claw-workflow.mdccursor/.cursor/rules/flickclaw-data-quality-claw-quality-gates.mdcwindsurf/.windsurf/rules/flickclaw-data-quality-claw.mdwindsurf/.windsurf/rules/flickclaw-data-quality-claw-workflow.mdwindsurf/.windsurf/rules/flickclaw-data-quality-claw-quality-gates.mdaider/CONVENTIONS.mdaider/aider.mdaider/.aider.conf.ymlollama/Modelfileollama/system-prompt.mdollama/template.md+1 moreInstall Commands
Install the FlickClaw CLI, then select your AI agent framework below to get the correct install command.
Step 1: Install CLI (one-time)
npm install -g @flickclaw/cli@latestStep 2: Select Framework
npm exec --yes @flickclaw/cli@latest -- install data-quality-claw --target openclawDownload as ZIP
Example Prompt
Try this prompt with Data Quality Claw to see what it can do:
Analyze the data pipeline for quality issues. Review schema design, ETL processes, and monitoring. Produce Data Quality Scorecard, Anomaly Detection Report, Cleansing Pipeline Config.Example Output
IllustrativeWhat a typical Data Quality Claw report looks like:
# Data Quality Claw — Assessment Report **Project**: analytics-warehouse **Context**: a Snowflake data warehouse with 15 source integrations and daily ETL **Example type**: Illustrative output ## Executive Summary The Data Quality Claw completed its review of analytics-warehouse (a Snowflake data warehouse with 15 source integrations and daily ETL). 3 findings were identified with concrete remediation steps. All quality gates were verified before delivery. ## Findings | # | Severity | Area | Finding | Recommended Action | |---|----------|------|---------|-------------------| | 1 | **P1** | Schema | Slowly changing dimensions not tracked for customer table | Add SCD Type 2 with effective_date and is_current | | 2 | **P2** | Quality | 5% null rate in revenue column across 3 sources | Add NOT NULL constraint and source-level validation | | 3 | **P2** | Performance | Materialized view refresh blocks reads for 12min | Switch to incremental refresh with partition pruning | ## Quality Gates - [✓] Completeness score > 99% on critical columns - [✓] Uniqueness enforced on natural keys - [✓] Anomaly thresholds calibrated on 30-day baseline ## Outputs Generated - **Data Quality Scorecard**: Included in the report above. - **Anomaly Detection Report**: Included in the report above. - **Cleansing Pipeline Config**: Included in the report above. - **Column Profiling Summary**: Included in the report above. - **Quality Gate Integration (CI)**: Included in the report above. ## Validation - [x] All quality gates passed (3/3) - [x] 3 findings documented with severity and remediation - [x] 5 output sections generated - [x] Evidence collected and referenced --- *This is an illustrative example output from FlickClaw. Results vary based on project context.*