Identify causal relationships in data.
Causal Graph Modeling Expert
DoWhy, CausalNex, causal-learn
Best for
- ▸Identifying causal relationships between marketing campaigns and revenue using DAG analysis
- ▸Implementing backdoor criterion adjustment for unbiased treatment effect estimation
- ▸Building causal discovery pipelines with NOTEARS and PC algorithms in causal-learn
- ▸Designing difference-in-differences studies for policy impact evaluation
What you'll get
- ▸Hand-drawn DAG with d-separation analysis, Python code implementing backdoor adjustment in DoWhy, and sensitivity bounds for unmeasured confounding
- ▸Causal discovery pipeline using PC algorithm with conditional independence tests, followed by structural equation modeling validation
- ▸Complete difference-in-differences design with parallel trends testing, event study plots, and robustness checks across multiple specifications
A clear causal question, domain knowledge about variable relationships, and observational or quasi-experimental data with potential confounders.
Causal DAGs, identification strategies, implementation code in DoWhy/CausalNex, and sensitivity analysis results with explicit assumptions.
What's inside
“You are a Causal Graph Modeling Expert. You help move from correlational analysis to credible causal claims by constructing, validating, and analyzing causal graphs using Pearl's framework and modern causal inference libraries. - Insist on drawing the DAG before selecting an estimation method; make ...”
Covers
Not designed for ↓
- ×Pure predictive modeling without causal claims
- ×Correlation analysis or statistical association studies
- ×Time series forecasting without causal interpretation
- ×A/B testing with perfect randomization (no confounding)
SupaScore
87.13▼
Evidence Policy
Standard: no explicit evidence policy.
Research Foundation: 8 sources (3 books, 2 official docs, 3 academic)
This skill was developed through independent research and synthesis. SupaSkills is not affiliated with or endorsed by any cited author or organisation.
Version History
v5.5 final distill
Pipeline v4: rebuilt with 3 helper skills
Initial release
Prerequisites
Use these skills first for best results.
Works well with
Need more depth?
Specialist skills that go deeper in areas this skill touches.
Common Workflows
Marketing Attribution Analysis
Build causal DAG for marketing channels, implement attribution modeling with proper confounding control, then design experiments to validate causal claims
© 2026 Kill The Dragon GmbH. This skill and its system prompt are protected by copyright. Unauthorised redistribution is prohibited. Terms of Service · Legal Notice