Skip to content
Back to skills

Datasketch Resource Deduplication Starter

ASecurity

Use this skill to scan a tiny resource registry sample for near-duplicate text records with MinHash LSH.

  • 38 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 8, 2026
ai-agents

Security analysis

A100/100

Pro scans all 10 files and shows the line behind each finding

Scanned September 8, 2026

npx -y skills add ma-compbio-lab/SkillFoundry --skill datasketch-resource-deduplication-starter --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Datasketch Resource Deduplication Starter?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Datasketch Resource Deduplication Starter
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ma-compbio-lab-datasketch-resource-deduplication-starter/badge)](https://www.skillsdirectory.com/skills/ma-compbio-lab-datasketch-resource-deduplication-starter)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# datasketch Resource Deduplication Starter

Use this skill to scan a tiny resource registry sample for near-duplicate text records with MinHash LSH.

## What This Skill Does

- reads a toy JSONL resource list
- tokenizes title and summary text
- builds MinHash sketches with `datasketch`
- returns candidate duplicate pairs above a configurable threshold

Files in this skill

  • SKILL.md356 B
  • assets/README.md105 B
  • assets/datasketch_dedup_summary.json381 B
  • examples/README.md363 B
  • examples/toy_resources.jsonl506 B
  • metadata.yaml1.3 KB
  • refs.md190 B
  • scripts/run_datasketch_resource_deduplication.py2.5 KB
  • tests/README.md138 B
  • tests/test_run_datasketch_resource_deduplication.py1.3 KB

Attribution

ma-compbio-labView sourceSee grades on GitHubMore from ma-compbio-lab

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…