Individual skill

StatsPAI_skill

Agent-native one-stop toolkit for the full empirical data-analysis pipeline in Python (v1.6+). 900+ functions, one import (`import statspai as sp`), unified API. Covers the complete loop after data cleaning — descriptive stats & EDA (sp.sumstats, sp.balance_table, sp.balance_panel), estimand-first research-question DSL (sp.causal_question), LLM-assisted DAG discovery (sp.llm_dag_propose/validate/constrained), one-call orchestration (sp.causal), classical estimators (OLS, IV, DID, staggered DID, RDD, PSM, SCM), ML causal (DML, Causal Forest, Meta-Learners, TMLE), neural causal, text causal (sp.causal_text), and diagnostics + robustness (sp.diagnose, sp.spec_curve, sp.honest_did). Use when the user asks to run a full empirical analysis, decide which estimator to use ("DID vs RD vs IV?"), explore models via DAG, estimate treatment effects, evaluate policy, run observational studies, or apply any of the listed econometric methods in Python. Every function returns structured result objects with self-describing schemas for LLM-driven workflows. Data cleaning (missing values, type coercion, merges) is *not* covered — handle that with pandas first, then enter StatsPAI.

data-analysis/StatsPAI_skill/SKILL.md

Source commit 9a4b2db21fc4b217136ae4a0e6faad42d179ca03

What was checked

Matches the observed repository HEAD

Yes

Scanner rules are current

Yes

Repository scan complete

No

Skill scan complete

No

Observed behavior

Network or broad shell

Last checked

Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

Standard SKILL.md format has not been attested at this commit. No installation command is available; inspect the source.