Agent skill · Data & Analytics

icdm-writing-style

Use when drafting or revising prose for an ICDM (IEEE International Conference on Data Mining) paper - the data-regime-first register, the named-mechanism discipline, measured-scale language instead of scalability adjectives, discovery-validity sentences, triple-blind-safe self-reference, and compression into the single 10-page IEEE all-inclusive cap.

brycew6m878★ · +32/wk · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add brycewang-stanford/Awesome-Journal-Skills --skill icdm-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: 5 KB
Bundled scripts: none
Path: ICDM-Skills/skills/icdm-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

# ICDM Writing Style Revise a manuscript into the register ICDM reviewers reward: a **data-mining mechanism** made legible to a data-centric IEEE audience, with claims a reviewer can check and a scale story that is measured rather than asserted. Two hard constraints shape every choice — the Research Track is **triple-blind**, so the prose cannot lean on author identity, and the whole paper (references and appendix included) must fit **10 IEEE two-column pages**. ## Open with the data regime, not the model family ICDM work starts from the shape of the data: streams seen once, power-law-sparse graphs, implicit rather than explicit feedback, evolving edges, high-dimensional transactions. The strongest openings name that regime and make the mechanism its consequence. ```text Weak (model-first): "We propose a novel graph neural network with a new attention module for anomaly detection, achieving state-of-the-art results." ICDM-shaped (regime-first): "Interaction graphs arrive as an unbounded edge stream seen once and cannot be stored. We give a one-pass detector whose memory is sub-linear in the number of edges, with a stated error bound." ``` The second version names the regime, implie

What's inside
Steps it walks through
  1. Open with the data regime, not the model family
  2. Name the mechanism, and give it a reason
  3. Measure scale; do not adjective it
  4. Write discovery-validity sentences
  5. Keep self-reference triple-blind-safe
  6. Compress into 10 all-inclusive pages
  7. Vignette: rescuing a buried contribution
  8. Output format
More from Awesome-Journal-Skills
All skills →
About this skill
What does the icdm-writing-style skill do?

Use when drafting or revising prose for an ICDM (IEEE International Conference on Data Mining) paper - the data-regime-first register, the named-mechanism discipline, measured-scale language instead of scalability adjectives, discovery-validity sentences, triple-blind-safe self-reference, and compression into the single 10-page IEEE all-inclusive cap.

How do I install it?

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