Claude MarketplacesSubmit

Novelty Assessment

lingzhi227/agent-research-skills

This runs a systematic literature search loop to figure out if your research idea already exists. It does up to 10 rounds of searches across Semantic Scholar and arXiv, checking each batch of papers for overlap. The harsh critic persona is useful here: it won't let you ship a trivial extension as novel work. You get a binary novel or not novel decision with confidence level and specific papers that come close. Minimum three search rounds before it'll declare something novel. Best used before you commit weeks to a direction, and the structured JSON output feeds nicely into related work sections if you proceed.

skills.sh installs: 1.9K
GitHub stars: 459
last updated: Aug 21, 2026

Install

$ npx -y skills add lingzhi227/agent-research-skills --skill novelty-assessment --agent claude-code

Installs into .claude/skills of the current project.

Files

Novelty Assessment

Rigorously assess whether a research idea is novel through systematic literature search.

Input

$0 — Research idea description, title, or JSON file

Scripts

Automated novelty check

python ~/.claude/skills/idea-generation/scripts/novelty_check.py \
  --idea "Your research idea description" \
  --max-rounds 10 --output novelty_report.json

Literature search

python ~/.claude/skills/deep-research/scripts/search_semantic_scholar.py \
  --query "relevant search query" --max-results 10

References

Assessment prompts and criteria: ~/.claude/skills/novelty-assessment/references/assessment-prompts.md

Workflow

Step 1: Understand the Idea

Identify the core contribution
List the key technical components
Determine the research area and subfield

Step 2: Multi-Round Literature Search (up to 10 rounds)

For each round:

Generate a targeted search query
Search Semantic Scholar / arXiv / OpenAlex
Review top-10 results with abstracts
Assess overlap with the idea
Decide: need more searching, or ready to decide

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly

Agent CaffeineSponsoredClose your lid, come back to finished work

SnugSponsoredThe clipboard manager for the AI era Promote your product hereReach 125k+ visitors monthly

WaxSponsoredBlock anything with supervision, without erasing your iPhone Promote your product hereReach 125k+ visitors monthly

knobsSponsoredSee your site on any phone, any day, in any language

Details

Repository: github.com/lingzhi227/agent-research-skills
Categories: AI & Agent Building, Data Science & ML, Productivity & Planning
First seen: Jun 3, 2026

Recommended

More AI & Agent Building

1

paper-writing-sectionlingzhi227/agent-research-skillsWrite a specific section of an academic paper (Abstract, Introduction, Background, Related Work, Methods, Experiments, Results, Discussion/Conclusion) with sect1.8Kskills.sh installs

2

pdfk-dense-ai/scientific-agent-skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple P1.8Kskills.sh installs

3

paper-revisionlingzhi227/agent-research-skillsRevise papers based on reviewer feedback. Map reviewer concerns to specific sections, apply targeted edits, run additional experiments if needed, and verify imp1.8Kskills.sh installs

4

shopify-admin-executionshopify/shopify-ai-toolkitRun a validated Admin GraphQL operation against a specific store using Shopify CLI. Use this when the user wants an executable store workflow, not just the quer1.8Kskills.sh installs

5

github-researchlingzhi227/agent-research-skillsExplore and analyze GitHub repositories related to a research topic. Reads deep-research output, discovers repos from multiple sources, deeply analyzes code, an1.8Kskills.sh installs

6

docxk-dense-ai/scientific-agent-skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any 1.8Kskills.sh installs