mlsys-writing-style
Use when revising an MLSys paper's prose and structure, building the measured-bottleneck opening, naming the mechanism instead of listing optimizations, writing evaluation sections as answers to research questions, quantifying every performance claim with workload context, and fitting the argument into the venue's 10-page two-column body.
Profile →npx skills add brycewang-stanford/Awesome-Journal-Skills --skill mlsys-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.
# MLSys Writing Style Use this during drafting and revision. MLSys prose sits between two failure modes: the ML-paper voice (contribution bullets, related-work-first, benchmarks as decoration) and the tech-report voice (system tour, feature list, "extensive experiments"). The venue's own genre is different: a paper here is an *argument about where time, memory, or money goes* in an ML workload, and how a named idea changes that. ## The first-page arc 1. **Bottleneck, measured.** Open with the profiling fact that justifies the paper — a percentage, a stall, a cost line — on a workload the reader recognizes. If the introduction's first numbers appear in the evaluation section, the order is wrong. 2. **Why existing designs cannot remove it.** Mechanistic reasons per named system or design family, not "prior work is limited." 3. **Insight.** The one observation that unlocks the design, stated in a sentence a reader could repeat tomorrow. 4. **Mechanism, named.** Give the technique a noun. Anonymous "several optimizations" is how research contributions disappear into engineering. 5. **Payoff with scope.** Ranged improvement, named baseline, stated cost or non-win. ## Sentence-level rewr
- The first-page arc
- Sentence-level rewrites
- Evaluation sections answer questions
- Numbers discipline
- Compression into 10 two-column pages
- Figures and tables carry the paper
- Title and abstract mechanics
- Anonymization without lobotomy (research track)
- Output format
What does the mlsys-writing-style skill do?
Use when revising an MLSys paper's prose and structure, building the measured-bottleneck opening, naming the mechanism instead of listing optimizations, writing evaluation sections as answers to research questions, quantifying every performance claim with workload context, and fitting the argument into the venue's 10-page two-column body.
How do I install it?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill mlsys-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.