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 Writing Style

ASecurity

Use when drafting or polishing an American Journal of Political Science (AJPS) manuscript so it fits the word caps (Articles <= 10,000 words; Research Notes and Correspondence <= 4,000; abstract <= 150 words), follows the APSA Style Manual or Chicago 18th edition, and stays fully anonymized for double-blind review. Tightens prose and format; it does not invent 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-writing-style --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ajps Writing Style?

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

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

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

Download with Pro
Files
SKILL.md
---
name: ajps-writing-style
description: Use when drafting or polishing an American Journal of Political Science (AJPS) manuscript so it fits the word caps (Articles <= 10,000 words; Research Notes and Correspondence <= 4,000; abstract <= 150 words), follows the APSA Style Manual or Chicago 18th edition, and stays fully anonymized for double-blind review. Tightens prose and format; it does not invent content.
---

# Writing Style (ajps-writing-style)

An AJPS paper must be tightly argued, formatted to one accepted style, disciplined to the word cap, and
**fully anonymized** for double-blind review. This skill is about clarity, format, and the AJPS-specific
counting rules — not about generating claims.

## When to trigger

- Drafting the introduction, framing the contribution, or final polish
- Over the word cap and needing to cut without losing the argument
- Writing the **<= 150-word abstract**
- Aligning citations/format to APSA or Chicago style before submission

## Write tight and lead with the contribution

1. **Front-load the contribution.** By the end of the introduction the reader knows the question, the
   argument, the design, the finding, and why it matters. Do not bury the "so what."
2. **Argument-first prose.** Lead with claims; use evidence to support them. Avoid "the data show..."
   without saying what they show and why it matters.
3. **Reach a broad readership.** AJPS spans subfields; define niche jargon on first use and spell out
   acronyms.
4. **Signpost.** Clear section structure so a reader can navigate the argument.

## Format and the AJPS word-count rule

- **Style**: **APSA Style Manual for Political Science** (rev. 2018, updated 2023) **or** **Chicago
  Manual of Style (18th ed.)** — pick one and apply it consistently; references use authors' **full
  first and last names**. Double-spaced, 12-point, >= one-inch margins.
- **Abstract**: **<= 150 words**, covering background, hypotheses, methodological approach, findings,
  and conclusions.
- **Word count** (put it on the title page along with the abstract): **includes** the main body, notes,
  parenthetical references, print appendices, and **table/figure headers and notes**; **excludes** the
  title page, abstract, reference list, online Supporting Information, and mathematical notation.
  - Articles **<= 10,000**; Research Notes and Correspondence **<= 4,000**.

## Stay double-blind in the prose

- No author names, affiliations, **acknowledgments, funding statements, or conference mentions** in the
  manuscript.
- **Third-person self-citation** only — never "as we showed" / "in our prior work."
- Put the abstract and word count on the title page; the manuscript file itself stays anonymous.

## Fit the word cap

- Move balance tables, full specs, and extended robustness to the **Supporting Information** (<= 20 pp).
- Tighten footnotes and exhibit notes — they count toward the limit.
- Cut throat-clearing and the literature dump; engage the debate, not every paper (see
  `ajps-literature-positioning`).

## Anti-patterns

- An abstract over 150 words or one that hides the finding
- Burying the contribution in the middle of the paper
- Mixing APSA and Chicago styles, or last-name-plus-initial references
- Acknowledgments, funding lines, or first-person self-references that break anonymity
- Letting exhibit notes and footnotes silently push the paper over the cap

## Output format

```
【Contribution stated by end of intro?】[Y/N]
【Abstract】word count (<=150), states finding?
【Word count】Article <=10,000 / Note|Correspondence <=4,000 (incl. notes + table/figure captions)?
【Style】APSA or Chicago 18th, applied consistently? full names in refs?
【Anonymized】no names/affiliations/acknowledgments/funding; third-person self-cites? [Y/N]
【Next】ajps-replication-and-verification
```

## Supplementary resources

- [`../../resources/official-source-map.md`](../../resources/official-source-map.md) — word/abstract caps, APSA-or-Chicago style, anonymizing rules

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 →