Novelty Check

Novelty Check is an AI Engineering skill for Claude Code, published by OpenLAIR in dr-claw.

1K stars116 forkson OpenLAIR/dr-clawAdded 2026/08/21Repository updated 2026/08/09

ai-agentsai-scientistauto-researchclaude-codeclaude-science-desktop-alternativeclaude-science-freeliterature-reviewpaper-writingresearch-assistant

Install in seconds

Install Novelty Check

Copy Novelty Check into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/OpenLAIR/dr-claw/tree/main/skills/aris-novelty-check ~/.claude/skills/aris-novelty-check

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/OpenLAIR/dr-claw.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/aris-novelty-check/SKILL.md in OpenLAIR/dr-claw
Installs to: ~/.claude/skills/aris-novelty-check
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Novelty Check does

Novelty Check verifies whether a proposed research method or idea has already appeared in recent literature. Use it before implementation when you need a blunt assessment of overlap and likely prior work.

Novelty Check is cataloged under AI Engineering on DirSkills. Novelty Check comes from a repository tagged ai-agents, ai-scientist, auto-research, claude-code and claude-science-desktop-alternative.

Documentation

README

Excerpt

Novelty Check Skill

Check whether a proposed method/idea has already been done in the literature: $ARGUMENTS

Constants

REVIEWER_MODEL = gpt-5.4 — Model used via Codex MCP. Must be an OpenAI model (e.g., gpt-5.4, o3, gpt-4o)

Instructions

Given a method description, systematically verify its novelty:

Phase A: Extract Key Claims

Read the user's method description
Identify 3-5 core technical claims that would need to be novel:
- What is the method?
- What problem does it solve?
- What is the mechanism?
- What makes it different from obvious baselines?

Phase B: Multi-Source Literature Search

For EACH core claim, search using ALL available sources:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Novelty Check

What else does OpenLAIR publish alongside Novelty Check?
Novelty Check is one of 25 skills that DirSkills catalogs from OpenLAIR/dr-claw, the repository it ships in. Its siblings there include ARIS Infra, Ablation Planner and Academic Researcher. Each one is a separate skill with its own page in this directory, installs the same way Novelty Check does, and is maintained by OpenLAIR in that same repository. The rest of the collection is listed on the OpenLAIR/dr-claw page.
How does Novelty Check compare to other AI Engineering skills?
Novelty Check ranks #1343 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Novelty Check against them. Open each page to compare what they document and how they install.