inacior

Writing For Computer Science — AI skill for Claude Code

AI community

An AI agent skill that reviews and revises scientific and technical writing to the standards of Justin Zobel's 'Writing for Computer Science'.

How to install Writing For Computer Science

This entry records only its repository, not the path inside it, so there is no exact command to give. Open inacior/writing-for-computer-science and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Writing For Computer Science does

An AI agent skill that reviews and revises scientific and technical writing to the standards of Justin Zobel's 'Writing for Computer Science'.

Alternatives in AI

Skill Architecture — System architecture and API design with multi-AI consensus — use for design reviews and new subsystems 2.8k ★
Open Science — Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux 1.5k ★
LongHorizon Harness — The long-horizon computer-use harness 1.3k ★

README

writing-for-computer-science

A skill that reviews, revises, and drafts scientific and technical writing to the standards of Justin Zobel's *Writing for Computer Science*. It distills the book into actionable rules for papers, theses, reports, and talks in computing and mathematics.

Installation

Install with the skills CLI:

npx skills add inacior/writing-for-computer-science

Or copy the folder into your agent's skills directory, for example:

mkdir -p ~/.codex/skills
cp -R writing-for-computer-science ~/.codex/skills/

For Claude Code or other agents, use their skills directory (e.g. `~/.claude/skills/writing-for-computer-science`) or register the path via the agent's skill config.

Usage

Invoke the skill, then paste the text:

/writing-for-computer-science

[your text]

Or ask directly: "Review this abstract using the Writing for Computer Science skill" / "Rewrite this introduction to match Writing for Computer Science."

What it covers

Reference	Contents
`references/01-article-structure.md`	Title, abstract, introduction, survey, results, conclusions, composing the paper
`references/02-editing-checklist.md`	Full revision and consistency checklist
`references/03-style.md`	Economy, tone, sentence and paragraph structure, ambiguity, word choice, tense, usage, sexist language
`references/04-punctuation-math.md`	Punctuation conventions and mathematical notation, numbers, units
`references/05-figures-algorithms.md`	Graphs, diagrams, tables, captions; algorithm presentation and complexity
`references/06-experiments-refereeing-talks.md`	Hypotheses and experiments, refereeing, and short talks

Design

SKILL.md holds the workflow, core principles, and the most common fixes, and points to the detailed reference files (progressive disclosure).
Reference files are structured notes extracted from the book, with watchlists and before/after examples drawn from the