←Leaderboard/Research/paperjury
Last commit on August 9, 2026·Created on June 2, 2026

Spark-To-Paper-Skills/paperjury

“Stress-tests a CS paper before the reviewers see it.”
Combined rank
#281
across all skills
In Research
#13
category rank
Stars
1.2k
+0.3% in last 7d
Forks
44
+2.3% in last 7d
Watchers
26
0.0% in last 7d
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
TL;DR

PaperJury runs a CS-conference manuscript through an adversarial courtroom review engine that assigns domain reviewers, routes issues to a trial jury, and gates every edit behind author sign-off. It helps authors, lab teams, and graduate students harden papers for vision, NLP, and ML venues without leaving the agent workflow.

WHO IT'S FOR
CS conference authors
harden papers via adversarial review
AI research lab teams
streamline review rehearsal with auto mode
Graduate students in AI/ML
polish LaTeX and translate ideas
Non-native English speaking researchers
convert Chinese ideas to fluent LaTeX
Repository contents

1 skill file

Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.

Use this skill

Follow the documented setup, then try a first task.

Claude Code marketplace plugin

Installs: Complete PaperJury plugin from the Spark-To-Paper-Skills marketplace · Claude Code

Before you start
  • Claude Code
  • node installed; it is required for deterministic checks
  1. Enter these commands inside a Claude Code session, not in a terminal. Add the author’s marketplace and then install its PaperJury plugin.

    /plugin marketplace add Spark-To-Paper-Skills/paperjury
    /plugin install paperjury@Spark-To-Paper-Skills
  2. After installation, run this terminal command from the installed skill folder to verify repository integrity, required tools, and manuscript detection.

    npm run doctor
README.en.md ↗ · Checked Sep 29, 2026.claude-plugin/plugin.json ↗ · Checked Sep 29, 2026.claude-plugin/marketplace.json ↗ · Checked Sep 29, 2026

Give it something to do.

Suggested first task

Review experiments and claims

Uses paperjury

  • Paper project path to substitute for <paper-project>
  • A manuscript in the project
  • The target CS-conference venue or venue family if it is not otherwise available
Use the paperjury skill to review the manuscript in <paper-project>, especially its experiments and claims. Treat <paper-project> as the path to my paper project. Report the issues and proposed revisions, and require my confirmation before applying any patch.
README.en.md ↗ · Checked Sep 29, 2026SKILL.md ↗ · Checked Sep 29, 2026
Suggested first task

Tighten an introduction paragraph

Uses paperjury

  • The manuscript or paper project
  • A file location, line range, or pasted paragraph to substitute for <target-passage>
  • Any wording or length constraint that must be preserved
Use the paperjury skill in direct-edit mode to tighten the introduction paragraph at <target-passage> without changing its claim. Treat <target-passage> as a placeholder for the file and paragraph, line range, or pasted passage I provide. Draft the bounded change and wait for my sign-off before applying it.
README.en.md ↗ · Checked Sep 29, 2026SKILL.md ↗ · Checked Sep 29, 2026
Suggested first task

Check submission readiness

Uses paperjury

  • Paper project path to substitute for <paper-project>
  • Main manuscript path to substitute for <main-manuscript>
  • node installed
  • Optional LaTeX toolchain for real compilation and layout checks
Use the paperjury skill’s submission-readiness checker on <main-manuscript> in <paper-project>. Treat both values as path placeholders. Give me the deterministic desk-reject screening and compile findings; if no LaTeX toolchain is available, clearly report the supported structural-lint fallback instead.
README.en.md ↗ · Checked Sep 29, 2026SKILL.md ↗ · Checked Sep 29, 2026