Agent skill · Data & Analytics

sigir-writing-style

Use when drafting or revising prose for a SIGIR paper — the IR register that leads with task, collection, and metric; claim sentences calibrated to significance results; first-page architecture for retrieval contributions; table-centric argumentation; and compressing into the 9-page budget without cutting soundness.

brycew6m4,252★ · +31/wk · 3 repos on radarProfile →
claude-codeMIT
Install
npx skills add brycewang-stanford/Awesome-Journal-Skills --skill sigir-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: 6 KB
Bundled scripts: none
Path: SIGIR-Skills/skills/sigir-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

# SIGIR Writing Style SIGIR prose has a recognizable register: it names the retrieval task before the model, quantifies on named collections with named metrics, and calibrates every adjective to a statistical test. Papers written in general-ML register ("we achieve state-of-the-art performance across diverse benchmarks") read as tourists. This skill converts drafts into the native register. ## The first-page arc for a retrieval paper Reviewers form the accept/reject prior on page one. The arc that works: 1. **Task + regime**: which retrieval problem, under which constraints (first-stage vs re-ranking, latency budget, corpus scale, low-resource language, ...). 2. **The specific failure of current practice**: not "existing methods have limitations" but "late-interaction models pay a storage cost that grows with document length" — a mechanism, not a mood. 3. **The move**: your method/finding in one sentence, mechanism visible. 4. **Calibrated evidence preview**: collections, headline metric deltas, and the significance qualifier, all in one breath. 5. **Contribution bullets** that are checkable promises ("a re-ranking model that ...; an analysis showing ...; run files and code at ..."

What's inside
Steps it walks through
  1. The first-page arc for a retrieval paper
  2. Vocabulary calibration
  3. Tables carry the argument
  4. Sectioning that survives the 9-page budget
  5. Sentence-level habits of accepted IR papers
  6. Abstract length and shape
  7. Revision protocol
  8. Output format
More from Awesome-Journal-Skills
All skills →
About this skill
What does the sigir-writing-style skill do?

Use when drafting or revising prose for a SIGIR paper — the IR register that leads with task, collection, and metric; claim sentences calibrated to significance results; first-page architecture for retrieval contributions; table-centric argumentation; and compressing into the 9-page budget without cutting soundness.

How do I install it?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill sigir-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