causal

If the skill install path cannot be resolved (some sandboxed environments): read the script file(s) from this skill, write a copy into a scripts/ folder inside the working folder, and run from there. The scripts are self-contained.

Skill: /causal — OpenCausalInf Causal Inference Toolkit

Purpose

Multi-mode skill for causal inference when experiments aren't possible. Helps users estimate treatment effects from observational data with explicit assumption checking, sensitivity analysis, and mandatory caveats. Uses the coded estimator library bundled in this skill at scripts/causal_stats/.

Using the bundled library: add this skill's scripts/ directory to sys.path, then import, e.g.

import sys
sys.path.insert(0, "<path to this skill>/scripts")  # the scripts/ dir next to this SKILL.md
from causal_stats import did_basic

Requires pandas, numpy, scipy, statsmodels, and scikit-learn (for propensity matching); install the last two in the sandbox if missing.

When to Use

Invoke as /causal [mode] or trigger on causal inference intents:

• "Did this feature actually cause the improvement?"
• "We can't run an experiment, but..."
• "Was this change responsible for the metric movement?"
• "Can we measure the impact retroactively?"

Modes

/causal select

Purpose: Walk the method selection decision tree and recommend a causal method. Agent: the causal-method-selector plugin agent Flow:

1. Ask 4-6 diagnostic questions:
   • Can you randomize? → Route to /experiment design
   • Do you have a comparison group?
   • Do you have pre-treatment data?
   • Are there observable confounders you can measure?
   • How many time periods do you have?
2. Recommend: Pre-Post, DiD, PSM, Regression Adjustment, or "not feasible"
3. Output: recommended method + confidence level + rationale Checkpoint: Method confirmation (Type C — user must confirm before analysis)

/causal analyze

Purpose: Run the selected causal method on data. Agent: the causal-analyzer plugin agent Flow:

1. Read selected method from previous step or user input
2. Dispatch to the appropriate bundled estimator:

   from causal_stats import (
       pre_post_analysis, did_basic, propensity_match,
       regression_adjust,
   )
   # Method routing:
   # "pre_post" → pre_post_analysis(pre, post, covariates)
   # "did"      → did_basic(df, outcome, treat, post)
   # "psm"      → propensity_match(df, treat, covariates, outcome)
   # "regression" → regression_adjust(df, outcome, treatment, covariates)
   

3. Generate charts (treatment effect, balance plots for PSM, event study for DiD)
4. Output: working/causal_analysis_results.json