scdenney/open-science-skills · codex/text-classification/SKILL.md

text-classification skillA

Designs and validates LLM-based text classification for research data — codebook construction, choice of learning regime, model selection and reproducibility, prompt construction, pilot validation against human coding with agreement statistics (kappa, F1), hybrid human-LLM workflows, and reporting model-coded data. Also carries a resumable batch pipeline with a rule-based baseline for coding large sets of repeated free-text values against a closed codebook — occupation, institution, and registry

Latest version
mdr add scdenney/open-science-skills/text-classification@git:20260905.39e8276
Exact content
mdr add scdenney/open-science-skills/text-classification@sha256:d0a3acf3560a6fea
Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_2erk4ewue3fcpibx.svg)](https://markdownregistry.com/a/art_2erk4ewue3fcpibx)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260905.39e8276 latest2026-09-05 39e8276 22,975 BA view · diff
git:20260902.8289c422026-09-02 8289c42 22,517 BA view · diff
git:20260808.ee9c9642026-08-08 ee9c964 19,675 BA view · diff
git:20260808.0b54e422026-08-08 0b54e42 19,293 BA view · diff
git:20260702.0d142fe2026-07-02 0d142fe 19,292 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.

Source

GitHub

scdenney/open-science-skills · 54 stars · license NOASSERTION · pushed 2026-09-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_2erk4ewue3fcpibx
GET https://markdownregistry.com/api/v1/resolve?ref=scdenney/open-science-skills/text-classification
GET https://markdownregistry.com/api/v1/blob/d0a3acf3560a6feab0d25d06e924eb983919958ae5932d251147a79e3a7cc814