agentsclimarketplace

Massbank record validation

Skill HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/massbank-record-validation

Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

Install
npx -y skills add HolobiomicsLab/asb-skill-collections --skill massbank-record-validation

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 14 stars14 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when you have a collection of MassBank records (in plain-text or structured format) that need to be systematically validated for conformance to MassBank format specification—particularly in a continuous integration context where validation must run on every commit or pull request to maintain.

The file declares its own license as CC-BY-4.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

6.3 KB, as published. Nobody here has run it

massbank-record-validation

License: restricted — no clear open-source license detected for the underlying tool; verify licensing before commercial use or redistribution. <!-- asb-license-banner -->

Summary

Automated validation of MassBank spectral records against standardized format and content rules using GitHub Actions and the MassBank-web Validator. This skill ensures all records in the MassBank-data repository conform to defined metadata and spectral data standards before publication.

When to use

Apply this skill when you have a collection of MassBank records (in plain-text or structured format) that need to be systematically validated for conformance to MassBank format specification—particularly in a continuous integration context where validation must run on every commit or pull request to maintain data quality across a shared repository.

When NOT to use

  • Records are already known to conform to MassBank specification and do not require re-validation
  • You need to validate records against a custom or non-standard schema different from MassBank's defined format
  • Input records are in a non-MassBank format (e.g., mzML, mzXML) that the MassBank Validator does not parse

Inputs

  • MassBank records in plain-text or structured format
  • MassBank-data repository commit or pull request
  • Individual or batch MassBank record files

Outputs

  • Validation status report (pass/fail per record set)
  • Machine-readable validation output (JSON or CSV)
  • Validation error/warning messages for failed checks
  • GitHub Actions workflow status badge

How to apply

Trigger the GitHub Actions workflow validate-records.yml in the MassBank-data repository, which invokes the Validator component from MassBank-web against all records. The Validator parses each record's metadata fields (accession, name, formula, mass, spectrum peaks, etc.) according to MassBank format specification, applies validation rules for field presence, data type, value range, and format constraints, and collects validation errors or warnings for each failed rule. The workflow generates a machine-readable validation report (JSON or CSV) with pass/fail outcomes per record set. Monitor validation status via GitHub Actions badges displayed for main and dev branches to verify that all records pass before merging changes.

Related tools

Evaluation signals

  • All validation status badges for main and dev branches show passing (green) status
  • Validation report lists zero failed checks for all records in the batch
  • Machine-readable output (JSON/CSV) contains no error entries or all error counts are zero
  • GitHub Actions workflow completes without timeout or fatal errors and produces machine-readable output
  • Specific error messages are absent from validation report (or present only for intentionally flagged records)

Limitations

  • The MassBank-web repository is deprecated; the Validator and command-line tools are now maintained in https://github.com/MassBank/MassBank-cli-tools, so validation logic may differ between legacy and current versions
  • Validation rules are fixed to MassBank specification and cannot be customized per-record-set without modifying the Validator source code
  • GitHub Actions workflow execution may have latency or quota limits depending on repository size and GitHub infrastructure availability

Evidence

  • [readme] uses GitHub Actions to validate the content of all records with the Validator from MassBank-web: "uses GitHub Actions to validate the content of all records with the [Validator](https://github.com/MassBank/MassBank-web/blob/main/MassBank-Project/MassBank-lib/src/main/java/massbank/cli/Validator.ja"
  • [other] Validator parses metadata fields and applies format rules: "Parse the record's metadata fields (accession, name, formula, mass, spectrum peaks, etc.) according to MassBank format specification. 3. Apply the validation rules implemented in MassBank-web"
  • [other] validation status badges displayed for main and dev branches: "validation status badges displayed for main and dev branches"
  • [other] Machine-readable validation output requirement: "Output the validation report in a machine-readable format (JSON or CSV)"
  • [readme] MassBank-web is deprecated; validator moved to cli-tools: "This repo is deprecated. Please do not use it! The new MassBank web app is maintained in repo https://github.com/MassBank/MassBank3. The validator and other command line tools are maintained in"

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.