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

Jde Writing Style

ASecurity

Use when polishing prose for a Journal of Development Economics (JDE) manuscript so the development question, answer, and policy stakes land for a field audience. A late-stage polish; do not rewrite the intro before identification and framing are settled.

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

Security Analysis

A100/100

Scanned 6/5/2026

Install to Claude Code

$npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill jde-writing-style --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Jde Writing Style?

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

Security grade badge for Jde Writing Style
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-jde-writing-style/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-jde-writing-style)

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

Download with Pro
Files
SKILL.md
---
name: jde-writing-style
description: Use when polishing prose for a Journal of Development Economics (JDE) manuscript so the development question, answer, and policy stakes land for a field audience. A late-stage polish; do not rewrite the intro before identification and framing are settled.
---

# Writing Style (jde-writing-style)

## When to trigger

- The abstract states a setting but not a finding with a magnitude
- The introduction buries the development question under methods or data description
- The prose mixes American and British English, or reads inconsistently
- Identification and contribution are settled and the paper needs its final polish

## The JDE prose bar

JDE readers are development economists; the writing has to make a **first-order development question and its answer** land quickly, with policy stakes explicit. Principles:

- **Abstract states the finding with a number.** Lead with the development question, the design in a phrase, and the headline effect in welfare-relevant units — not just "we study X in country Y." (Pre-results review Stage 1 proposals cap the abstract at **150 words**; a regular-submission abstract cap was not confirmed officially — keep it tight, see 待核实 in the source map.)
- **Introduction as an argument.** Question → why it matters for development → setting and design in a few sentences → headline result with magnitude → contribution relative to the frontier → roadmap. Avoid a literature-survey opening.
- **Policy and welfare made visible.** Translate effects into terms a development economist and a policymaker can weigh (poverty gap, cost-effectiveness, test-score SDs).
- **Honest scope.** State external-validity limits plainly; development referees reward calibrated claims and punish overreach.
- **Language consistency.** Write in **either American or British English, not a combination** — JDE requires one consistent variant. Use author-date citations consistently (single author: name + year; two: both names + year; three or more: first author + "et al." + year). JDE accepts any consistent reference style at submission and applies its own at the proof stage, so prioritize consistency over house formatting.

## Tactics

- Cut throat-clearing; the first paragraph should already pose the development question.
- Prefer concrete institutional detail over abstract generality — context is part of the contribution in development work.
- Define constructed variables and indices in words before the reader meets them in a table.
- Keep the conclusion to what the design supports plus honest open questions.

## Anti-patterns

- An abstract that names a topic but states no effect size
- A survey-style introduction that delays the question and result
- Mixing US and UK spelling/usage in the same manuscript
- Inflated external-validity language unsupported by the design

## Output format

```
【Abstract】states finding + magnitude in welfare units? [Y/N]
【Intro arc】question → stakes → design → result → contribution? [Y/N]
【Policy framing】effects in comparable units? [Y/N]
【Language】consistent US or UK English? [Y/N]
【Citations】consistent author-date? [Y/N]
【Next step】jde-replication-and-data-policy
```

Attribution

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

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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', ...

693161 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 →