Data · Global library
Design analytics flows that preserve useful product insight while reducing privacy and re-identification risk.
Best use case
Use Privacy-Preserving Analytics when you need to design analytics flows that preserve useful product insight while reducing privacy and re-identification risk, especially when the work is driven by differential privacy and k anonymity.
Trigger signals
Validation hooks
Install surface
Inspect
pip install "orchestrator-mcp[dashboard]"
orchestrator-mcp skills show privacy-preserving-analyticsUse
orchestrator-mcp skills export privacy-preserving-analytics --to ./skillforge-packs
# copy the exported pack into your preferred agent environmentExport
cp -R skills/privacy-preserving-analytics ./your-agent-skills/privacy-preserving-analytics
# or open skills/privacy-preserving-analytics/SKILL.md in a markdown-first clientFile patterns
Model preferences
Related skills
Implements privacy-preserving data techniques including differential privacy, k-anonymity, and data masking for GDPR/CCPA compliance
Build cohort retention logic and churn views that survive product evolution and messy subscription edge cases.
Implements enterprise data catalogs with DataHub or Amundsen for data discovery, governance, and collaboration