skills.rest
steinbeck
steinbeckCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

lucy-ng:sanitize

Sanitize Bruker NMR dataset metadata by redacting compound identifiers via manifest-driven text replacement.

3|2|Updated Jan 8, 2026
Search Tags:#workflow#sanitization#NMR#data-integrity#Bruker#CASE#metadata-redaction
One-click install
npx skills add https://github.com/steinbeck/lucy-ng --skill lucy-ng-sanitize
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: lucy-ng:sanitize
Source: https://github.com/steinbeck/lucy-ng/tree/main/skill/sanitize
Command: npx skills add https://github.com/steinbeck/lucy-ng --skill lucy-ng-sanitize

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill removes compound identity information from Bruker NMR datasets' metadata while preserving spectroscopic data for valid blind CASE evaluations.

Core Features & Use Cases

  • Automated metadata sanitization: Redacts compound names, CAS numbers, and other identifiers across titles, logs, peak lists, and dataset metadata without touching spectral data.
  • Manifest-driven redaction: Generates or consumes a redaction manifest to ensure reproducible, auditable sanitization steps.
  • Safety-first workflow: Enforces a fresh AI session after sanitization to prevent memory leakage of identities and supports verification via a post-sanitization extractor run.
  • Use Case: Prepare public Bruker NMR datasets for blind CASE studies by removing identity information before analysis.

Quick Start

Steps:

  1. Run the text extractor to review dataset content: python lucy_text_extractor.py <dataset_path>
  2. AI identifies identifiers and creates a manifest file (identifiers.txt)
  3. Run the bulk sanitizer: python lucy_bulk_sanitize.py <dataset_path> --manifest identifiers.txt
  4. Re-run the text extractor to verify sanitization: python lucy_text_extractor.py <dataset_path>

Frequently Asked Questions about lucy-ng:sanitize

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I sanitize Bruker NMR datasets for blind CASE analyses?▼

This skill removes compound names, CAS numbers, and other identifiers from titles, logs, and peak lists without altering spectral data, ensuring a valid blind CASE evaluation.

What is the process for redacting compound identity from NMR metadata?▼

The workflow involves running a text extractor to review content, creating an identifiers manifest, executing a bulk sanitizer, and re-running the extractor to verify that compound identity is fully removed.

Does the NMR sanitization process modify binary spectral data files?▼

No, the sanitization process skips binary data files entirely, targeting only text files like titles and logs to redact identifiers while preserving the raw spectroscopic data required for analysis.

How do I verify that NMR metadata sanitization removed all compound identifiers?▼

You verify sanitization by re-running the text extractor on the dataset after the bulk sanitizer completes, which produces a verification report confirming no compound identity remains in the metadata.

Can I delete structure files during the NMR dataset sanitization workflow?▼

Yes, the sanitization workflow optionally deletes structure files alongside redacting compound names and identifiers from text-based metadata to ensure complete identity removal for blind CASE studies.

Related Skills

Explore More Education & Research Skills→
xjtulycxjtulyc
33

nmr-analysis

Process NMR FID data into phase-corrected spectra with peak lists and J-couplings.

Community
Advanced
steinbecksteinbeck
3

lucy-ng:CASE

Guide de novo structure elucidation from NMR correlations without database matches.

Community
Advanced
wanyusheng63-altwanyusheng63-alt

batch-image-generator

Batch generate game assets from a structured JSON manifest.

Community
Advanced
InternScienceInternScience
52

chem-data-extractor

Extract chemical characterization data from PDFs and Markdown into strict JSON.

Official
Intermediate