Pre-submission CS-conference LaTeX paper editing and adversarial review.

MITAuto-check passedDocuments & Office

Install Paperjury

skills CLI
$ npx skills add Spark-To-Paper-Skills/paperjury-codex --skill paperjury -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Spark-To-Paper-Skills/paperjury-codex paperjury --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Spark-To-Paper-Skills/paperjury-codex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/paperjury-codex/skills/paperjury .claude/skills/paperjury && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
paperjury
GitHub stars
223
Token cost
~351 tokens
SKILL.md length
133 words
Files
2
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Pre-submission CS-conference LaTeX paper editing and adversarial review.

  • Direct edits such as polish
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Translating Chinese notes to LaTeX
  • Compressing passages

What it does

Paperjury is an agent skill from Spark-To-Paper-Skills/paperjury-codex. Pre-submission CS-conference LaTeX paper editing and adversarial review. Use for direct edits such as polish, de-AI, translating Chinese notes to LaTeX, compressing passages, captions, and experiment prose; for review or critique requests such as review, mock-review, 审稿, 评审; and for explicit auto or goal-driven review-revise loops.

Its SKILL.md is about 350 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Documents & Office, covering LaTeX and Translation. It works with LaTeX. The repository describes itself as: Codex-first port of PaperJury, a pre-submission CS paper review and editing skill. The licence is MIT.

When your agent uses it

  • Direct edits such as polish
  • Translating Chinese notes to LaTeX
  • Compressing passages
  • Experiment prose

Example prompts

  • “/paperjury”

What it can do on your machine

Read from SKILL.md and the folder at commit 6383d0c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Paperjury loads about 351 tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 133 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~351

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Spark-To-Paper-Skills/paperjury-codex at commit 6383d0c, republished under its MIT licence (© Spark-To-Paper-Skills). 133 words, ~351 tokens.

Download SKILL.mdSave it as .claude/skills/paperjury/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
paperjury
description
Pre-submission CS-conference LaTeX paper editing and adversarial review. Use for direct edits such as polish, de-AI, translating Chinese notes to LaTeX, compressing passages, captions, and experiment prose; for review or critique requests such as review, mock-review, 审稿, 评审; and for explicit auto or goal-driven review-revise loops.

PaperJury Plugin Entry

This skill is packaged by the paperjury-codex Codex plugin. The canonical PaperJury workflow lives at the plugin root in ../../SKILL.md; read that file first and follow it as the source of truth.

Resolve the plugin-owned support files from the plugin root, not from this wrapper directory:

  • deterministic scripts: ../../scripts/
  • review and writing references: ../../references/
  • Codex runtime notes and phase contracts: ../../codex/
  • config template: ../../configs/config-template.md
  • fallback agent metadata/personas: ../../agents/

At the start of each PaperJury invocation, run the plugin root's scripts/check-update.js unless PAPERJURY_DISABLE_UPDATE_CHECK=1 is set. Show an update notice only when the script reports an available update; otherwise continue silently and never block the workflow on update checking.

Project-specific paper files, ledgers, journals, and generated patches belong in the user's active paper project. Do not write them into the plugin directory.

© Spark-To-Paper-Skills, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in plugins/paperjury-codex/skills/paperjury of Spark-To-Paper-Skills/paperjury-codex.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 6383d0c

Compare with similar skills

Paperjury next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Paperjury compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Paperjury this skillSpark-To-Paper-Skills/paperjury-codex223—~351Automated safety check: PassMIT
Typst Paperbahayonghang/academic-writing-skills500—~3.6kAutomated safety check: PassNone
Sci PptShZhao27208/Aut_Sci_Write209—~757Automated safety check: PassMIT
Latex Translation Guidewentorai/research-plugins2981 repos~1.2kAutomated safety check: PassMIT
Translate To Quartobrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~542Automated safety check: NotesCustom licence
Nature-Style Academic PolishingYuan1z0825/nature-skills47k—~1.5kAutomated safety check: PassApache-2.0

Similar skills

  • Typst Paper

    bahayonghang/academic-writing-skills

    Typst paper assistant for existing .typ manuscripts in English or Chinese.

    500 GitHub stars~3.6k tokensUpdated 13 days ago
    Documents & OfficeAuto-check passed
  • Sci Ppt

    ShZhao27208/Aut_Sci_Write

    Generate professional academic PowerPoint (PPTX) presentations from paper PDFs, structured outlines, or plain text.

    209 GitHub stars~757 tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • Latex Translation Guide

    wentorai/research-plugins

    Translate LaTeX documents preserving math formulas and structure

    298 GitHub starsUsed in 1 repo~1.2k tokens
    Documents & OfficeAuto-check passed
  • Translate To Quarto

    brycewang-stanford/Auto-Empirical-Research-Skills

    Translate Beamer LaTeX to Quarto RevealJS. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.

    4.6k GitHub stars~542 tokensUpdated 5 days ago
    Documents & OfficeAuto-check: notes
  • Nature-Style Academic Polishing

    Yuan1z0825/nature-skills

    Polishes, translates or tightens existing academic prose and fixes manuscript LaTeX layout while keeping facts, terminology and evidence boundaries intact.

    47k GitHub stars~1.5k tokensUpdated today
    Writing & ContentAuto-check passed
  • Academic Paper

    brycewang-stanford/Auto-Empirical-Research-Skills

    Academic paper writing skill with 12-agent pipeline. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.

    4.6k GitHub stars~7.3k tokensUpdated 5 days ago
    Documents & OfficeAuto-check passed

More from Spark-To-Paper-Skills/paperjury-codex

  • Paperjury

    Spark-To-Paper-Skills/paperjury-codex

    Pre-submission CS-conference LaTeX paper editing and adversarial review.

    223 GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Works with

Questions about Paperjury

What does Paperjury do?

Pre-submission CS-conference LaTeX paper editing and adversarial review. Paperjury is an agent skill from Spark-To-Paper-Skills/paperjury-codex. Pre-submission CS-conference LaTeX paper editing and adversarial review.

When should I use Paperjury?

Paperjury fits situations like: direct edits such as polish; translating Chinese notes to LaTeX; compressing passages; experiment prose.

How do I install Paperjury in Claude Code?

Run `npx skills add Spark-To-Paper-Skills/paperjury-codex --skill paperjury -a claude-code`. Or copy the skill folder (plugins/paperjury-codex/skills/paperjury in Spark-To-Paper-Skills/paperjury-codex) into .claude/skills/paperjury in your project. Claude Code loads it when a task matches its description.

How do I install Paperjury in Codex?

Run `npx skills add Spark-To-Paper-Skills/paperjury-codex --skill paperjury -a codex`. Or copy the skill folder (plugins/paperjury-codex/skills/paperjury in Spark-To-Paper-Skills/paperjury-codex) into .agents/skills/paperjury in your project. Codex loads it when a task matches its description.

Can I use Paperjury in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Spark-To-Paper-Skills/paperjury-codex --skill paperjury -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/paperjury, .gemini/skills/paperjury, .github/skills/paperjury and .opencode/skills/paperjury in your project.

What does Paperjury need to run?

SKILL.md names no scripts, command-line tools or credentials: Paperjury is instructions for the agent only.

Does Paperjury access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Paperjury safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Paperjury use?

Paperjury is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Paperjury use?

About 351 tokens (SKILL.md is roughly 1.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Paperjury?

Skills that share tags, products or a category with Paperjury: Typst Paper (bahayonghang/academic-writing-skills, 500 stars), Sci Ppt (ShZhao27208/Aut_Sci_Write, 209 stars), Latex Translation Guide (wentorai/research-plugins, 298 stars) and Translate To Quarto (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Paperjury?

Spark-To-Paper-Skills (a GitHub organization) maintains it in Spark-To-Paper-Skills/paperjury-codex, which has 223 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on August 9, 2026.

Source: Spark-To-Paper-Skills/paperjury-codex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.