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

Ci Writing Style

ASecurity

Use when drafting or polishing the prose of a Critical Inquiry (CI) essay so it meets the journal's bar for ambitious, lucid critical writing and fits the word limit (articles ≤ 9,500 words including discursive notes and all bibliographical information; Critical Responses ≤ 3,000; Reviews ≤ 500). Tightens style and discipline; it does not invent argument or evidence.

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

Works with

cli

Security Analysis

A100/100

Scanned 6/5/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Ci Writing Style?

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

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

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

Download with Pro
Files
SKILL.md
---
name: ci-writing-style
description: Use when drafting or polishing the prose of a Critical Inquiry (CI) essay so it meets the journal's bar for ambitious, lucid critical writing and fits the word limit (articles ≤ 9,500 words including discursive notes and all bibliographical information; Critical Responses ≤ 3,000; Reviews ≤ 500). Tightens style and discipline; it does not invent argument or evidence.
---

# Writing Style (ci-writing-style)

A *Critical Inquiry* essay must read as **ambitious, precise, and alive** — prose worthy of the claim,
legible to a reader from another field, and disciplined to the word limit. This skill is about how the
essay sounds and how tightly it is cut, not about generating the argument.

## When to trigger

- Drafting the opening or doing a final stylistic polish
- Over the **9,500-word** cap (which counts notes) and needing to cut
- The argument is strong but the prose is flat, baggy, or opaque
- Tuning the register so it is rigorous without being airless

## Write to CI's bar

1. **Clarity is the highest ambition.** Difficulty should come from the ideas, never from the
   sentences. Say the hard thing plainly.
2. **Voice with control.** CI prose can be vivid and essayistic, but every flourish must carry
   argument. Style serves the claim, not the author's persona.
3. **Show the reading.** Move close to the text or image; let the analysis breathe rather than
   asserting conclusions (see `ci-evidence-and-objects`).
4. **Address the discipline-crossing reader.** Define terms on first use; an art historian should
   follow a literary essay and vice versa (see `ci-structure-and-exposition`).

## Fit the word cap (notes are counted)

- The limit **includes discursive notes and all bibliographical information** — prune footnote essays
  and bloated citations as hard as body text (see `ci-citation-and-style`).
- Cut throat-clearing, redundant examples, and the second sentence that restates the first.
- Replace summary of others with a single precise sentence and a citation.
- Prefer one deep reading to three shallow ones.

## Sentences and paragraphs

- Vary sentence length; let a short sentence land the claim.
- One idea per paragraph; topic the paragraph to the argument, not the example.
- Quote sparingly and exactly; integrate quotation into your syntax.
- Kill the cliché ("always already," "interrogate," "troubling") unless it does real work.

## Anti-patterns

- Opacity mistaken for depth; jargon standing in for thought
- A glittering style that outruns the argument
- An abstractly theoretical voice that never touches the object
- Footnotes that quietly blow the word budget
- Padding a Critical Response or Review past its cap

## Output format

```
【Clarity】hard ideas, plain sentences? [Y/N]
【Voice】flourishes carry argument? [Y/N]
【Cross-field legibility】terms glossed? [Y/N]
【Word count】≤ 9,500 incl. notes + all bibliographical info (or ≤ 3,000 / ≤ 500)?
【Cuts identified】throat-clearing / redundant examples / fat notes
【Next】ci-citation-and-style
```

## Supplementary resources

- [`../../resources/external_tools.md`](../../resources/external_tools.md) — the word-count rule and note discipline
- [`../../resources/official-source-map.md`](../../resources/official-source-map.md) — word caps for each CI format

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 →