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

Io Writing Style

ASecurity

Use when drafting or polishing an International Organization (IO) manuscript so it reads for international-relations scholars across paradigms, fits the word caps (Research Article <= 14,000; Research Note <= 8,000; Essay <= 10,000, including tables, figures, and notes but excluding the bibliography), and meets IO format conventions (double-blind, third-person self-citation, short author-date footnotes, separate abstract/word-count/acknowledgments). Tightens prose and format; it does not inve...

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

Security Analysis

A100/100

Scanned 6/5/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Io Writing Style?

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

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

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

Download with Pro
Files
SKILL.md
---
name: io-writing-style
description: Use when drafting or polishing an International Organization (IO) manuscript so it reads for international-relations scholars across paradigms, fits the word caps (Research Article <= 14,000; Research Note <= 8,000; Essay <= 10,000, including tables, figures, and notes but excluding the bibliography), and meets IO format conventions (double-blind, third-person self-citation, short author-date footnotes, separate abstract/word-count/acknowledgments). Tightens prose and format; it does not invent content.
---

# Writing Style (io-writing-style)

An IO paper must be readable by an international-relations scholar from a different tradition, framed
around a **generalizable IR theory**, and disciplined to the word cap. This skill is about reaching the
IR field and respecting IO's format — not about generating claims.

## When to trigger

- Drafting the introduction, framing the IR contribution, or final polish
- Over the word cap and needing to cut without losing the argument
- Preparing the **abstract, word count, and acknowledgments** (submitted **separately** from the manuscript)
- Aligning citations/footnotes/format to IO conventions before submission

## Reach the IR field (across paradigms)

1. **Front-load the IR contribution.** By the end of the introduction the reader knows the
   international question, the theory, the evidence, and why it matters for international politics. Don't
   make a reader from another tradition dig for the "so what."
2. **Speak across rationalist / constructivist / IPE / security divides.** Define paradigm-specific
   jargon on first use; a security scholar should follow an IPE paper and vice versa. Spell out IGO and
   dataset acronyms.
3. **Argument-first prose.** Lead with the IR claim; use evidence to support it. Avoid "the data
   show…" without saying what they show about international politics and why it matters.
4. **Signpost.** Clear section structure so a reader can follow theory → design → evidence.

## Format to IO conventions

- **Self-citation / anonymity**: IO is **double-blind** — after the title page, **omit self-references
  that reveal identity** and refer to your own work in the **third person** (e.g., "Matthews 2022," not
  "as we showed"). Strip identifying file metadata.
- **Citations**: accepted manuscripts use **short author-date footnotes** rather than parenthetical
  references; keep one consistent style (manage with Zotero/BibTeX) and convert at acceptance. The
  **bibliography is excluded** from the word count.
- **Abstract / word count / acknowledgments**: submitted **separately** from the manuscript; include a
  **Data Availability Statement** before the reference list (see `io-transparency-and-data-policy`).
- **ORCID**: corresponding author registers an ORCID iD.

## Fit the word cap (counts include tables/figures/notes; exclude the bibliography)

- Research Article **≤ 14,000**, Research Note **≤ 8,000**, Essay **≤ 10,000** words.
- Move balance tables, full specs, robustness grids, and formal-proof details to **supplementary
  material** (which should rarely exceed ~20 pages).
- Cut throat-clearing and literature dumps; engage the IR debate, not every paper (see
  `io-literature-positioning`).
- Tighten footnotes — they count toward the limit. Prefer one decisive figure to three redundant tables.

## Anti-patterns

- A single-tradition intro that never states the general IR contribution
- Burying the contribution in the middle of the paper
- First-person self-references that break double-blind anonymity
- Mixed citation styles; acknowledgments left inside the manuscript instead of submitted separately
- Padding a Research Note toward Article length

## Output format

```
【IR contribution stated by end of intro?】[Y/N]
【Reads across traditions?】paradigm jargon defined / acronyms spelled? [Y/N]
【Word count】Article ≤14,000 / Note ≤8,000 / Essay ≤10,000 (incl. tables/figures/notes; excl. bibliography)?
【Double-blind】third-person self-citation + metadata clean? [Y/N]
【Abstract/word-count/acknowledgments separate + DAS + ORCID】[Y/N]
【Next】io-transparency-and-data-policy
```

## Supplementary resources

- [`../../resources/official-source-map.md`](../../resources/official-source-map.md) — word caps, third-person self-citation, short author-date footnotes, separate abstract/word-count/acknowledgments, ORCID

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 →