Individual skill

mhe-identification

Apply the Angrist-Pischke perspective from *Mostly Harmless Econometrics* (2009) — modernized with post-2009 advances (synthetic control, staggered-DiD revolution, double-ML, shift-share IV, modern clustering) — to evaluate identification strategies and draft identification/endogeneity sections in empirical economics and finance papers. Two operating modes, declared at invocation: - **Critic mode** — interrogate a paper's identification the way a senior Angrist-style empiricist would read a draft: reframe via potential outcomes, name the source of exogenous variation, flag bad controls, check the IV/DiD/RD assumptions, audit inference (clustering, few clusters), apply the post-2009 layer (TWFE bias on staggered data, GP-Sorkin-Swift for Bartik, etc.), and reach a verdict in MHE register. - **Drafter mode** — write an identification or endogeneity-addressing section in MHE voice: motivate with the ideal experiment or a concrete empirical anchor, name the source of variation, justify CIA or invoke LATE, address bad controls explicitly, close with an inference note. Follows the user's `working-paper-format.md` LaTeX conventions. Triggers: "evaluate the identification", "is this identification credible", "would MHE say this holds", "draft the endogeneity section", "Angrist/Pischke perspective", "LATE check", "bad control", "check the parallel trends", "natural experiment vs selection on observables", or `/mhe-identification`. Distinct from `strategist` (proposes designs), `strategist-critic` (generic audit), `econ-write` (writing templates), and `scholarpeer-econ` (multi-agent review). This skill is a *perspective + voice + pedagogy* layer, not a checklist or pipeline.

review-revise/mhe-identification/SKILL.md

Source commit 9a4b2db21fc4b217136ae4a0e6faad42d179ca03

What was checked

Matches the observed repository HEAD

Yes

Scanner rules are current

No

Repository scan complete

No

Skill scan complete

No

Observed behavior

Not checked yet

Last checked

Nov 7, 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.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.