Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Jpe Workflow

ASecurity

Use when deciding which jpe-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for a Journal of Political Economy (JPE) manuscript. Routes — it does not replace — the specialized skills.

1,052 stars
0 votes
0 copies
0 views
Added 6/5/2026
ai-agentsgoexpress

Security Analysis

A100/100

Scanned 6/5/2026

Install to Claude Code

$npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill jpe-workflow --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Jpe Workflow?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Jpe Workflow
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-jpe-workflow/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-jpe-workflow)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: jpe-workflow
description: Use when deciding which jpe-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for a Journal of Political Economy (JPE) manuscript. Routes — it does not replace — the specialized skills.
---

# JPE Workflow Router (jpe-workflow)

## Overview

This is the router. It does not replace any specialized skill. It tells you **which jpe-* skill to use given where you are right now** in a Journal of Political Economy (JPE) submission.

Default assumption: unless the user says otherwise, treat the target as **JPE proper** (University of Chicago Press; lead editor Esteban Rossi-Hansberg). The same routing applies to the **2023-launched companion journals** — JPE Microeconomics (lead editor John List) and JPE Macroeconomics (lead editor Greg Kaplan) — but those are narrower in scope; flag that routing choice in `jpe-topic-selection`. Note two JPE-specific gates that shape the whole pipeline: a **non-refundable $250 / $125 submission fee** with a 3-referee-reports waiver, and a conditional accept that triggers the **JPE Data Editor** verifying a DCAS package deposited to the **JPE Dataverse**.

The single organizing question behind every JPE skill: **"What does economic theory predict here, and does the evidence bear it out?"** A Chicago referee will read the paper as an economic argument, not a regression table. Internal consistency of that argument is scrutinized harder than at most journals.

## When to trigger

- The user asks "what should I do next?" on a JPE-targeted paper
- A draft is handed over and the current bottleneck is unclear
- Work is bouncing between modeling, empirics, and writing with no clear order
- A JPE decision letter (reject / R&R) has arrived and the user needs to switch into response mode

## Routing table

| Current symptom                                                        | Next skill                  |
|------------------------------------------------------------------------|-----------------------------|
| Idea is a correlation in search of a question; no economic mechanism   | `jpe-topic-selection`       |
| Unsure whether the paper is "JPE-shaped" vs. a field journal           | `jpe-topic-selection`       |
| Lit review reads as a list; contribution not framed in Chicago author-date | `jpe-literature-positioning`|
| Empirics are OLS + controls; causal claim not defended                 | `jpe-identification`        |
| Reduced-form result has no model / mechanism behind it                 | `jpe-theory-model`          |
| Structural model present but identification of parameters is unclear   | `jpe-theory-model`          |
| Main result exists but rests on a single specification                 | `jpe-robustness`            |
| Tables overloaded; figures not carrying the economic story             | `jpe-tables-figures`        |
| Prose is verbose / hedged / not in JPE's spare analytical voice        | `jpe-writing-style`         |
| Conditionally accepted; need a DCAS package for the JPE Data Editor / JPE Dataverse | `jpe-replication-package` |
| Want to anticipate the price-theory / GE objections a referee will raise | `jpe-referee-strategy`    |
| Ready to submit; need Editorial Express preflight + $250/$125 fee/format check | `jpe-submission`     |
| Received an R&R; need to draft the response letter                     | `jpe-rebuttal`              |

## Default order

1. `jpe-topic-selection` — lock the economic question and the mechanism it tests
2. `jpe-literature-positioning` — situate the contribution in the economics literature (Chicago author-date)
3. `jpe-identification` — make the causal/empirical claim credible
4. `jpe-theory-model` — the model or mechanism that gives the result its economic meaning
5. `jpe-robustness` — kill the alternative explanations a referee will float
6. `jpe-tables-figures` — finalize main exhibits so each carries economic content
7. `jpe-writing-style` — tighten prose into JPE's analytical register (polish)
8. `jpe-referee-strategy` — pre-mortem the report you expect, patch holes
9. `jpe-replication-package` — assemble data/code to DCAS standard for the JPE Data Editor / JPE Dataverse
10. `jpe-submission` — Editorial Express preflight ($250/$125 fee, Chicago author-date format, single-blind)
11. `jpe-rebuttal` — after the R&R lands

> `jpe-writing-style` is a **late polish** stage. Do not chase prose before the identification and the model are sound. `jpe-theory-model` and `jpe-identification` often iterate together — for JPE the model frequently disciplines the empirical specification, not the reverse.

## Decision heuristics

- "I have a clean causal effect but no story for *why*" → `jpe-theory-model` (a bare effect is not a JPE paper)
- "I have a model but the empirics are an afterthought" → `jpe-identification`
- "My intro cites everyone but never says what economics learns" → `jpe-literature-positioning`
- "DID uses TWFE with staggered timing and I haven't addressed heterogeneity bias" → `jpe-identification`
- "All my evidence is one regression" → `jpe-robustness`
- "A referee will say this ignores general equilibrium / selection / incentives" → `jpe-referee-strategy`
- "Submitting tomorrow" → `jpe-submission`
- "Got three referee reports" → `jpe-rebuttal`

## Differences vs. QJE / Econometrica / REStud stacks

JPE sits among the top-five but has a distinct house taste:

- **JPE**: premium on a tight economic *mechanism* and price-theoretic reasoning; reduced-form and structural both welcome, but the result must mean something for economic theory.
- **QJE**: prizes a striking, important question and a clean natural experiment; mechanism valued but identification often leads.
- **Econometrica**: methodological / theoretical novelty and formal rigor lead; pure applied work needs a method or theory contribution.
- **REStud**: technical depth with a younger-frontier slant; theory and structural empirics both core.

If the paper is methodological with no economic application, Econometrica may fit better. If it is an atheoretical policy evaluation, reconsider the framing in `jpe-topic-selection` before targeting JPE. And unlike its peers, JPE offers an in-house routing choice between the flagship and the JPE Micro / JPE Macro companions — use it deliberately.

## Anti-patterns

- **Do not** skip `jpe-theory-model` and present a reduced-form correlation as a finished JPE paper — referees ask "what is the economics?"
- **Do not** let `jpe-tables-figures` polish exhibits while the identification is still contested
- **Do not** let `jpe-rebuttal` draft a response letter before the manuscript itself has been revised
- **Do not** treat `jpe-submission` as the first stop; preflight is worthless if the economic argument is not yet sound
- **Do not** defer reproducible code to post-accept; the JPE Data Editor verifies the package before publication

Attribution

brycewang-stanfordbrycewang-stanford
View sourceMore from brycewang-stanford →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →