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

Ajps Workflow

ASecurity

Use as the entry point for any American Journal of Political Science (AJPS) manuscript. Routes to the right AJPS sub-skill based on lifecycle stage and which submission type (Article, Research Note, Correspondence) fits, and reminds you that AJPS re-runs your code via a third-party verifier before publishing. It dispatches; it does not draft content.

1,052 stars
0 votes
0 copies
0 views
Added 6/4/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 6/4/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Ajps Workflow?

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

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

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

Download with Pro
Files
SKILL.md
---
name: ajps-workflow
description: Use as the entry point for any American Journal of Political Science (AJPS) manuscript. Routes to the right AJPS sub-skill based on lifecycle stage and which submission type (Article, Research Note, Correspondence) fits, and reminds you that AJPS re-runs your code via a third-party verifier before publishing. It dispatches; it does not draft content.
---

# AJPS Workflow Router (ajps-workflow)

The orchestrator for an AJPS submission. Figure out the stage and the **submission type**, then send
the user to the matching skill. AJPS is the MPSA's flagship, **Wiley**-published, **double-blind**
journal whose defining feature is **mandatory third-party verification of replication materials before
publication** — so this router also makes sure reproducibility is engineered from the start, not bolted
on at acceptance.

## When to trigger

- Starting a new AJPS paper and unsure where to begin
- Mid-project and unsure which skill applies next
- Deciding whether the paper is an **Article**, **Research Note**, or **Correspondence**
- Returning with a decision letter (route to `ajps-rebuttal`)

## First question: which submission type?

| Situation | Type | Route to |
|-----------|------|----------|
| Full original study | **Article** (<= 10,000 words) | normal pipeline below |
| A **methodology** advance or a **meta-analysis** | **Research Note** (<= 4,000 words) | normal pipeline, tighter scope |
| Critique / correction of a paper already published in AJPS | **Correspondence** (<= 4,000 words) | `ajps-literature-positioning` + `ajps-data-analysis` |

> The Research Note is **not** a short empirical paper — at AJPS it is reserved for methodology
> (including methodology in normative theory) and meta-analyses. Do not mis-route a small empirical
> study into it.

## Routing map (stage -> skill)

```text
Idea / fit?                       -> ajps-topic-selection
Where does it sit in the field?   -> ajps-literature-positioning
What's the argument?              -> ajps-theory-building
Is the design identified?         -> ajps-research-design
Are the analyses sound?           -> ajps-data-analysis
Are the exhibits clear?           -> ajps-tables-figures
Does it read well + fit caps?     -> ajps-writing-style
Will the code re-run for a verifier? -> ajps-replication-and-verification
How will it be judged?            -> ajps-review-process
Ready to submit?                  -> ajps-submission
Got an R&R / decision?            -> ajps-rebuttal
```

## Default order

`topic-selection -> literature-positioning -> theory-building -> research-design -> data-analysis ->
tables-figures -> writing-style -> replication-and-verification -> review-process -> submission ->
rebuttal`

Iterate: theory <-> design <-> analysis usually loops several times. Critically, start the
**replication-and-verification** package while you analyze — at acceptance an independent verifier
re-runs your code, and an unscripted analysis cannot be fixed quickly under deadline.

## Anti-patterns

- Treating reproducibility as a post-acceptance chore — AJPS verifies before publishing
- Mis-routing a short empirical study into the methodology-only Research Note type
- Sending a critique of a non-AJPS paper as Correspondence (it is for published AJPS work)
- Forgetting that table/figure captions and footnotes count toward the word limit

## Output format

```
【Stage】idea / positioning / theory / design / analysis / exhibits / writing / replication / review / submit / rebut
【Type】Article / Research Note (methodology|meta-analysis) / Correspondence
【Route to】ajps-<skill>
【Why】one line
【Then】the next skill after that
```

## Supplementary resources

- [`../../resources/external_tools.md`](../../resources/external_tools.md) — political-science data + software by method
- [`../../resources/official-source-map.md`](../../resources/official-source-map.md) — official AJPS URLs behind every fact in this pack

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".

1074701 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 →