kdd-writing-style
Use when revising a KDD paper into the venue's register, where the first page names a data regime, a mechanism, and scale evidence, efficiency adjectives trace to design decisions, and two-column sigconf pages punish sprawl. Covers Research vs ADS voice, dataset-size discipline, assertive contribution bullets, and 8-page compression.
Profile →npx skills add brycewang-stanford/Awesome-Journal-Skills --skill kdd-writing-style --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# KDD Writing Style Use this during revision passes. KDD prose has a recognizable register: it talks about **data regimes** (scale, drift, sparsity, heterogeneity, label scarcity) rather than model families, it attaches every performance adjective to a mechanism, and it treats dataset cardinalities as part of grammar — a dataset without a size reads as unfinished. The `resources/worked-examples/01-introduction.md` file shows a full before/after; this skill is the rule set behind it. ## First-page contract Within page one, a KDD reviewer expects to find, in some order: 1. The **data regime** that makes the problem hard (not "X is important"). 2. Why existing method families fail **in that regime**, each for a mechanism-level reason. 3. The **named mechanism** this paper adds (a primitive someone could re-implement). 4. Evidence scoped with numbers: dataset scale, throughput or memory if claimed, headline quality delta. 5. For ADS: where this is deployed and the post-launch headline number. If the introduction could open an ICML or a database paper unchanged, the framing is not yet KDD's. ## Register rules | Draft habit | KDD-register rewrite | Why it matters here | |---|---|---| | "
- First-page contract
- Register rules
- Contribution bullets that survive review
- ADS voice
- Two-column compression tactics
- Anonymity phrasing
- Title and abstract mechanics
- Revision pass order
- Output format
grep -n -iE "novel|significant|efficient|large-scale|real-world|extensive" \
What does the kdd-writing-style skill do?
Use when revising a KDD paper into the venue's register, where the first page names a data regime, a mechanism, and scale evidence, efficiency adjectives trace to design decisions, and two-column sigconf pages punish sprawl. Covers Research vs ADS voice, dataset-size discipline, assertive contribution bullets, and 8-page compression.
How do I install it?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill kdd-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.