Agent skill · Code Review & Quality

wsdm-writing-style

Use when drafting or revising prose for a WSDM paper - the practical-yet-principled register, user-and-platform-grounded framing, self-containment writing for a no-rebuttal review, ethical-considerations craft, limitation sentences that protect borderline papers, and compression into the appendix-inclusive page cap.

brycew6m878★ · +32/wk · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add brycewang-stanford/Awesome-Journal-Skills --skill wsdm-writing-style --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 7 KB
Bundled scripts: none
Path: WSDM-Skills/skills/wsdm-writing-style/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 909 · +31 this week
Language: Stata
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# WSDM Writing Style Revise a manuscript into the register WSDM's series page announces for itself: "practical yet principled approaches" to search and mining on the Web and the Social Web. That phrase is an editorial instruction. A WSDM paper earns its slot by being simultaneously deployable-sounding and analytically honest - pure benchmark exercises read as under-motivated, pure war stories read as unscientific. The stylistic moves below operationalize that balance. ## Open with the behavioral problem, not the model family WSDM work starts from something users, platforms, or web data actually do: clicks are position-biased, sessions are short, graphs are power-law sparse, feedback loops entrench popularity, adversaries game ranking. The strongest openings name that behavioral fact and make the technical contribution the response to it. ```text Weak (model-first): "Transformer-based architectures have shown promise in recommendation. We propose a novel attention mechanism..." WSDM-shaped (behavior-first): "Users abandon a search session after roughly one unsatisfying page, so a ranker trained on clicks observes almost nothing below rank ten. We show this truncated feedback systema

What's inside
Steps it walks through
  1. Open with the behavioral problem, not the model family
  2. The self-containment voice
  3. Sentence-level tells, WSDM edition
  4. The ethics section as prose, not boilerplate
  5. Compression without loss
  6. Abstract anatomy for this venue
  7. Revision pass order
  8. Output format
More from Awesome-Journal-Skills
All skills →
About this skill
What does the wsdm-writing-style skill do?

Use when drafting or revising prose for a WSDM paper - the practical-yet-principled register, user-and-platform-grounded framing, self-containment writing for a no-rebuttal review, ethical-considerations craft, limitation sentences that protect borderline papers, and compression into the appendix-inclusive page cap.

How do I install it?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill wsdm-writing-style --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From brycewang-stanford/Awesome-Journal-Skills, a repository with 909 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going