Causal Inference Engine
Developmentcausal-inference-engineCausal Inference Engine is an Agent Skill for development published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Causal reasoning implementing DAG construction, do-calculus, and intervention effect estimation
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/a5c-ai/babysitter/blob/HEAD/library/specializations/domains/science/scientific-discovery/skills/causal-inference-engine/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/causal-inference-engine, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Causal Inference Engine
Purpose
Provides causal reasoning capabilities implementing DAG construction, do-calculus, and intervention effect estimation.
Capabilities
- Causal DAG construction and validation
- Backdoor/frontdoor criterion checking
- Average treatment effect estimation
- Instrumental variable analysis
- Mediation analysis
- Sensitivity analysis for unmeasured confounding
Usage Guidelines
- DAG Construction: Build causal graphs from domain knowledge
- Identification: Check if effects are identifiable
- Estimation: Apply appropriate estimation methods
- Sensitivity: Assess robustness to unmeasured confounding
Tools/Libraries
- DoWhy
- CausalNex
- pgmpy
- EconML