Individual skill

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.

MLSys-Skills/skills/mlsys-writing-style/SKILL.md

Read pinned source

Source commit 932eb23331721b16e967c59f093781be1928b498

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Network or broad shell
Last checked: Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 1,405
Repository last updated: Sep 27, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

academic-writing Repository topic
agent-skills Repository topic
journal Repository topic
academic-research Repository topic
ai-agents Repository topic
anthropic Repository topic
awesome-list Repository topic
claude Repository topic
claude-code Repository topic
economics Repository topic
research Derived category
writing Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 7,083 bytes

Read excerpt


# 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