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

Geb Topic Selection

ASecurity

Use when judging whether a game-theory result is the right fit and scale for Games and Economic Behavior (GEB) — does it advance the frontiers of game theory and its applications? Tests the idea against GEB's specialist-but-general-interest bar before the paper is built out.

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 geb-topic-selection --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Geb Topic Selection?

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

Security grade badge for Geb Topic Selection
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-geb-topic-selection/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-geb-topic-selection)

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

Download with Pro
Files
SKILL.md
---
name: geb-topic-selection
description: Use when judging whether a game-theory result is the right fit and scale for Games and Economic Behavior (GEB) — does it advance the frontiers of game theory and its applications? Tests the idea against GEB's specialist-but-general-interest bar before the paper is built out.
---

# Topic Selection (geb-topic-selection)

## When to trigger

- You have a model or experiment but are unsure it is "GEB-sized"
- The result is correct but feels incremental over a known theorem
- You are deciding between GEB and a field outlet (theory, behavioral, CS/EC venue)
- A referee or colleague said "true, but so what?"

## The GEB fit bar

GEB is the **leading specialist game-theory journal** and an official journal of the **Game Theory Society** (Elsevier; founded 1989 by Ehud Kalai; chief editor Hervé Moulin since 2021). The defining test is not general-economics policy interest — it is whether the work **significantly advances the frontiers of game theory and its applications**. The scope is deliberately broad across **methods**: equilibrium theory, mechanism and market design, behavioral game theory, learning and dynamics, and experimental/empirical work — and broad across **fields** that use game theory: economics, political science, biology, computer science, mathematics, and psychology. The audience is a general game-theory readership, so the contribution must be legible and interesting beyond one narrow sub-literature.

Selectivity is explicit and high: about **one-third of submissions are desk-rejected**, and only **~15%** are eventually published. The Editor in Charge will desk-reject papers judged to have no chance of meeting the publication criterion. That makes "what does this teach game theory that we did not know?" the first-page question.

## Fit tests (a GEB paper usually clears several)

- **Conceptual advance:** a new solution concept, a sharper characterization, a new class of games, an existence/uniqueness result, or a unifying framework.
- **Mechanism / design advance:** a new mechanism, an impossibility/possibility result, an optimal or constructive design.
- **Behavioral advance:** a model or experiment that changes how strategic behavior is understood, well-identified against alternatives.
- **Generality / surprise:** the result holds more broadly than expected, or overturns an intuition.
- **Cross-field reach:** game-theoretic content that speaks to CS/EC, biology, or political science — common at GEB, but it must still be a *game-theory* contribution.

## Anti-patterns

- A correct but routine extension ("Theorem 1 with one more player") with no new insight
- An applied paper that *uses* a game but contributes nothing to game theory itself (better at a field journal)
- A pure CS/EC conference result reframed with no added generality or economic interpretation
- Over-claiming a narrow special case as a general theory

## Output format

```
【Result type】theory / mechanism design / behavioral / experiment / cross-field
【Advance to game theory】one sentence — what we did not know before
【Fit tests cleared】[conceptual / design / behavioral / generality / cross-field]
【Desk-reject risk】low / medium / high — why
【Verdict】GEB-fit / borderline / better elsewhere
【Next step】geb-literature-positioning
```

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.

691 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 →