pitcany

Review Causal — Development skill for Claude Code

Development community

Review an observational or quasi-experimental causal claim — estimand, identification assumptions, DAG, overlap, DiD/IV/RDD/propensity/doubly-robust diagnostics, and sensitivity analysis.

How to install Review Causal

Installs to ~/.claude/skills/pitcany-statistical-agent-skills-review-causal/SKILL.md

Terminal

mkdir -p ~/.claude/skills/pitcany-statistical-agent-skills-review-causal && curl -fsSL https://raw.githubusercontent.com/pitcany/statistical-agent-skills/HEAD/commands/review-causal.md -o ~/.claude/skills/pitcany-statistical-agent-skills-review-causal/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Review Causal does

description: Review an observational or quasi-experimental causal claim — estimand, identification assumptions, DAG, overlap, DiD/IV/RDD/propensity/doubly-robust diagnostics, and sensitivity analysis.

Causal review

Target: $ARGUMENTS

What to do

Invoke the causal-inference skill.
Write the estimand before examining the method: treatment, outcome, contrast (ATE / ATT / CATE / LATE), and the population it describes. A causal estimand without a named population is

Alternatives in Development

JWT Scan — JWT attack toolkit (offline) — alg:none forgery, RS256→HS256 algorithm confusion, weak-secret crack, static cl 4.5k ★
Doctor — Environment diagnostics with interactive fixes — providers, auth, RTK, hooks, token optimization 2.8k ★
MCP Language Server — mcp-language-server gives MCP enabled clients access semantic tools like get definition, references, rename, a 1.5k ★