scdenney/open-science-skills · codex/model-council-voting/SKILL.md

model-council-voting skillA

Runs several language models as independent coders on the same labeling or discovery task and reads their disagreement as data — panel assembly for model diversity, keeping votes independent, consensus rules, agreement statistics (Cohen's and Fleiss kappa, Krippendorff's alpha), the correlated-errors caveat that stops agreement being mistaken for validity, human validation beyond the panel, and reporting. Use when the user asks about a council, panel, ensemble, or jury of models, asks how to com

Latest version
mdr add scdenney/open-science-skills/model-council-voting@git:20260905.39e8276
Exact content
mdr add scdenney/open-science-skills/model-council-voting@sha256:1dced0e45ae4b4cd
Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_f53u2ls5nifd4lpe.svg)](https://markdownregistry.com/a/art_f53u2ls5nifd4lpe)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260905.39e8276 latest2026-09-05 39e8276 17,406 BA view · diff
git:20260902.da5a2632026-09-02 da5a263 17,406 BA view · diff
git:20260808.c81b3502026-08-08 c81b350 16,842 BA view · diff
git:20260726.ec471db2026-07-26 ec471db 17,074 BA view · diff
git:20260725.6f8b5932026-07-25 6f8b593 19,623 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_f53u2ls5nifd4lpe
GET https://markdownregistry.com/api/v1/resolve?ref=scdenney/open-science-skills/model-council-voting
GET https://markdownregistry.com/api/v1/blob/1dced0e45ae4b4cd8607eac369e821ad2e7c550ff08b720f2df6f93015041e1a