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

Mksc Writing Style

ASecurity

Use when polishing the prose of a Marketing Science manuscript — front-loading model intuition before notation, managing the formal apparatus for readability, and following INFORMS author-year style and formatting. Late-stage polish; do not invoke while the model or identification is still unsettled.

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 mksc-writing-style --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mksc Writing Style?

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

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

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

Download with Pro
Files
SKILL.md
---
name: mksc-writing-style
description: Use when polishing the prose of a Marketing Science manuscript — front-loading model intuition before notation, managing the formal apparatus for readability, and following INFORMS author-year style and formatting. Late-stage polish; do not invoke while the model or identification is still unsettled.
---

# Writing Style (mksc-writing-style)

## When to trigger

- The paper buries its intuition under notation; an editor cannot grasp the contribution from the first pages
- Notation is dense, inconsistent, or introduced before motivation
- Citations/formatting are not in INFORMS style
- You are doing a final pass before submission (and the model is settled)

## Lead with intuition, then formalize

Marketing Science readers are technical, but the **intuition must come first**. State the marketing question, the mechanism, and the headline counterfactual in words before the model appears. Each major result should be previewed in plain language ("intuitively, because firms re-optimize prices, …") and only then proven. Notation is a tool for precision, not a substitute for an argument.

- Introduce notation **just-in-time**, near where it is used; keep a consistent, minimal symbol set; consider a notation table for heavy models.
- For analytical results, state the proposition in words, give the economic intuition, then the formal claim; push long proofs to an appendix.
- For structural work, motivate each modeling assumption by the marketing institution it captures.

## INFORMS house style

- **Citations**: author-year, e.g., (Norman 1977) or Norman (1977); reference list alphabetical by author in INFORMS reference style.
- **Format**: double-spaced, single column, 11- or 12-point font, one-inch margins; prepared in MS Word or LaTeX (INFORMS LaTeX style files and Style-Instructions.pdf on the Author Portal); uploaded as Word or PDF.
- **Abstract**: not more than 200 words, on the first page; 3–6 keywords describing the theoretical and methodological orientation.
- **Length discipline**: regular articles have no fixed cap but are expected to be written succinctly; **Frontiers** is a strict 6,000-word total cap (including references, tables, graphs, appendices), so for Frontiers, ruthlessly cut and push detail online.
- Keep the manuscript **blinded** for double-anonymous review — no self-identifying phrasing.

## Checklist

- [ ] Question, mechanism, and counterfactual stated in words up front
- [ ] Each result previewed intuitively before being formalized
- [ ] Notation minimal, consistent, introduced just-in-time
- [ ] INFORMS author-year citations; alphabetical reference list
- [ ] Format: double-spaced, 11–12 pt, one-inch margins; Word/LaTeX→Word/PDF
- [ ] Abstract ≤ 200 words; 3–6 keywords
- [ ] Frontiers manuscripts within the 6,000-word total cap
- [ ] Manuscript blinded

## Anti-patterns

- Opening with a wall of notation and no intuition.
- Re-defining symbols or carrying unused notation.
- Numbered/footnote-style citations instead of INFORMS author-year.
- Over-length Frontiers submissions that will be returned.

## Output format

```
【Intuition-first】question/mechanism/counterfactual stated up front?
【Notation】minimal, consistent, just-in-time?
【Citations/format】INFORMS author-year; double-spaced 11–12pt; Word/LaTeX
【Abstract/keywords】≤200 words; 3–6 keywords
【Length】regular succinct / Frontiers ≤6,000 words total
【Blinding】intact?
【Next step】mksc-submission
```

Attribution

brycewang-stanfordbrycewang-stanford
View sourceMore from brycewang-stanford →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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', ...

686011 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 →