agentsclimarketplace
Sign in

Evoke

Skill bkowshik/evoke

Turn any EEG dataset reference — a citation, DOI, repository accession, URL, or local file — into a reproducible, ready-to-run loader script that harmonizes the data to MNE and reports how much to trust the result. Use whenever the user wants to fetch, load, or reproduce an EEG dataset from a paper or reference, especially when no maintained loader (MOABB, eegdash) covers it.From its SKILL.md

Install
npx -y skills add bkowshik/evoke

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

  • 0 stars0 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.

SKILL.md

1.1 KB, 188 tokens by cl100k_base, as published. Nobody here has run it

evoke

⚠️ Not written yet. This is a placeholder. The project vision and scope are finalized in VISION.md; the skill body will be authored against it.

TODO

  • Reference resolution (bibkey · DOI · accession · URL · local path · name)
  • Source location across UCI / OpenNeuro / PhysioNet / Zenodo / UPF / Kaggle / lab pages
  • Loader-script generation → minimal fetch → harmonize to MNE → return a Bunch
  • Oracle-ladder verification (functional reproduction · library diff · stated spec · checksums · cross-source · sanity)
  • Confidence + datasheet report (verified / assumed / not-done)
  • Seed recipes: Bonn (andrzejak2001), BEED (obaido2026eeg)

What ships with it: 4 files

12.6 KB alongside SKILL.md

Keep looking

Skills are one crate of 326,144. 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.