aejpol-robustness

aejpol-robustness is a skill for Claude Code from brycewang-stanford/Awesome-Journal-Skills. It costs 63 tokens per session (1,464 once invoked), scanned A, original, MIT.

A plan for checking whether the main policy estimate in an economics paper remains credible under different assumptions and data choices. Robustness checks are tests of whether a conclusion survives reasonable changes to the analysis.

In plain words
What is it for?
Use it to organize specification comparisons, pre-trend checks, alternative samples, inference checks, and other tests before responding to reviewers. It is for defending an existing policy estimate, not choosing the original research design.
Why use it?
It replaces an unstructured list of extra regressions with checks tied to specific threats, such as model choices, samples, inference, and identification. This shows whether the policy conclusion—not just one numerical estimate—changes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the aej-economic-policy-skills plugin — 12 skills shipped together

Good fit Use it to organize specification comparisons, pre-trend checks, alternative samples, inference checks, and other tests before responding to reviewers. It is for defending an existing policy estimate, not choosing the original research design.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brycewang-stanford/awesome-journal-skills/aejpol-robustness
About the project

Awesome Journal Skills is a collection of agent skill packs tailored to hundreds of academic journals across fields including economics, social science, medicine, science, and engineering. Researchers use the packs for tasks such as choosing topics, designing empirical strategies, preparing tables and figures, submitting papers, and responding to reviewers. The catalogue entries are the project's journal-specific skills and related plugins.

brycewang-stanford/Awesome-Journal-Skills · 1,142 stars · on GitHub · copaper.ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add brycewang-stanford/Awesome-Journal-Skills --skill aejpol-robustness
Clone the repo
git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills

Made for: Claude Code.

Or install aej-economic-policy-skills, the plugin that ships this one along with the rest of its 12 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for aejpol-robustness

README.md
[![agentmods](https://agentmods.dev/badge/skills/brycewang-stanford/awesome-journal-skills/aejpol-robustness/github.svg)](https://agentmods.dev/skills/brycewang-stanford/awesome-journal-skills/aejpol-robustness)
Your own site
<a href="https://agentmods.dev/skills/brycewang-stanford/awesome-journal-skills/aejpol-robustness"><img src="https://agentmods.dev/badge/skills/brycewang-stanford/awesome-journal-skills/aejpol-robustness/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for aejpol-robustness

Your own site · 80×15
<a href="https://agentmods.dev/skills/brycewang-stanford/awesome-journal-skills/aejpol-robustness"><img src="https://agentmods.dev/badge/skills/brycewang-stanford/awesome-journal-skills/aejpol-robustness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,464 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.01464
Opus 5 $0.00032 $0.00732
Sonnet 5 $0.00013 $0.00293
Haiku 4.5 $0.00006 $0.00146

Measured 7d ago against content hash db2dab02cc86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-22, from the pricing page.

Security

Grade A, and why

aejpol-robustness scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AEJ-Economic-Policy-Skills/skills/aejpol-robustness/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Robustness — Defending the Policy Estimate (aejpol-robustness)

When to trigger

  • The headline causal estimate moves across specifications, or you do not yet know if it does
  • A referee will ask "is this robust?" and you have no organized answer
  • Inference (clustering, few clusters, multiple outcomes) is not yet airtight
  • You need to show the policy conclusion, not just a coefficient, survives stress

Principle: robustness defends the policy conclusion, not the coefficient

At AEJ: Policy, robustness is judged by whether the policy takeaway is stable — if the headline estimate is the cost-per-job or the MVPF, show that number is stable, with its uncertainty, not merely that a regression coefficient stays significant. Organize the robustness program around the threats that would change the policy conclusion, and report enough that a skeptical referee can see each threat addressed.

Robustness by threat (each maps to a concrete check)

Threat to the policy conclusion Check
Functional form / controls drive the result Specification ladder; show the estimate across a coherent set, not a single lucky spec
Pre-trends / parallel-trends violation Honest-DID (Rambachan–Roth) sensitivity bounds; placebo pre-period "effects"
Estimator bias under staggered timing Re-estimate with ≥1 heterogeneity-robust DID estimator (CS / SA / BJS / dCDH)
Bandwidth / kernel (RDD) Bandwidth sweep + bias-corrected CIs; donut-RDD if heaping at the cutoff
Weak / invalid instrument Effective F; AR-robust CI; over-ID test if available
Wrong inference / few clusters Wild-cluster bootstrap; report clustering level sensitivity
Multiple outcomes / specifications Romano–Wolf / sharpened q-values; a specification curve where many specs are run
Confounding by an omitted policy/shock Controls for co-timed policies; event-study around the focal reform only
Selection on unobservables Oster (2019) δ / bounds; argue the implied selection is implausible
Sample composition / outliers Drop influential jurisdictions; winsorize; alternative sample windows

Read the full file on GitHub · 95 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 95 lines · 0 tokens per session scan A db2dab02cc86

Subscribe to this mod's changes

aejpol-robustness is a skill published in the GitHub repository brycewang-stanford/Awesome-Journal-Skills (1,142 stars, last pushed 7d ago), licensed MIT. It adds 63 tokens to every session and 1,464 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-15.

Related

Other skills, from other repositories

alterlab-pyhealth

Develops, tests, and deploys clinical machine learning models with the PyHealth healthcare AI toolkit. Use when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare…

AlterLab-IEU/AlterLab-Academic-Skills · 117 tokens

alterlab-imaging-data-commons

Query and download public cancer imaging data from the NCI Imaging Data Commons (IDC) using the idc-index Python package, filtering by metadata, visualizing in-browser, and checking licenses, with no authentication required. Use when obtaining large-scale radiology (CT, MR, PET) or digital pathology DICOM datasets for…

AlterLab-IEU/AlterLab-Academic-Skills · 90 tokens

alterlab-eda

Exploratory data analysis (EDA) on a scientific data file — auto-detects the format, runs structure/quality/statistics checks, and writes a markdown EDA report with downstream recommendations. Use when asked to "explore", "analyze", "summarize", "profile", or "QC" a data file, or to understand its…

AlterLab-IEU/AlterLab-Academic-Skills · 258 tokens

alterlab-gnomad

Query gnomAD (Genome Aggregation Database) for population allele frequencies and gene constraint scores (pLI, LOEUF) reflecting loss-of-function intolerance. Use when checking how common a variant is across populations, filtering rare-disease candidate variants, assessing variant pathogenicity, or identifying…

AlterLab-IEU/AlterLab-Academic-Skills · 80 tokens

alterlab-monarch

Query the Monarch Initiative knowledge graph for disease-gene-phenotype associations across species, integrating OMIM, ORPHANET, HPO, ClinVar, and model organism databases. Use when discovering rare disease genes, mapping phenotypes to genes, modeling disease across species, or looking up HPO terms. Part of the…

AlterLab-IEU/AlterLab-Academic-Skills · 76 tokens

alterlab-zinc-db

Access the ZINC database of 230M+ commercially available (purchasable) compounds, searching by ZINC ID or SMILES, running similarity searches, and downloading 3D-ready structures. Use when assembling a compound library for virtual screening, finding purchasable analogs, or obtaining docking-ready 3D structures for…

AlterLab-IEU/AlterLab-Academic-Skills · 85 tokens