# Model Metadata Updates

Records model knowledge cutoffs, families and generations during onboarding and backfills.

- Repository: https://github.com/lobehub/lobehub (83676 stars)
- Category: Data and ML
- License: see repository
- Last updated: 2026-11-01
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add lobehub/lobehub --skill model-bank-metadata -g -a claude-code -y`
Codex: `npx skills add lobehub/lobehub --skill model-bank-metadata -g -a codex -y`
Cursor: `npx skills add lobehub/lobehub --skill model-bank-metadata -g -a cursor -y`
Gemini CLI: `npx skills add lobehub/lobehub --skill model-bank-metadata -g -a gemini-cli -y`

## Description

Use for model knowledgeCutoff, family and generation metadata: onboarding, corrections, research and bulk backfills.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Model-Bank Metadata (knowledgeCutoff / family / generation)

How to populate and maintain the three structured metadata fields on `packages/model-bank/src/aiModels/*.ts` model cards, at single-model scale (new model PR) or repo-wide scale (sweep across \~80 provider files / \~1900 entries).

## Field semantics

| Field             | Format                                                                              | Meaning                                                                                                                                                                                 |
| ----------------- | ----------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `knowledgeCutoff` | `'YYYY-MM'` (or `'YYYY'` if only the year is published)                             | World-knowledge cutoff. When a vendor distinguishes a **"reliable knowledge cutoff"** from the broader training-data cutoff (Anthropic does), always use the **reliable** one.          |
| `family`          | lowercase slug (`claude`, `gpt`, `o-series`, `qwen`, `deepseek`, `llama`, `glm`, …) | Model lineage, finer than `organization`. Lets the UI group models and match the same model across aggregator providers.                                                                |
| `generation`      | family slug + version (`claude-4.6`, `gpt-5.2`, `qwen3.5`, `llama-3.1`)             | Generation within the family. Only set when confidently derivable from the model line's naming. Rolling aliases (`qwen-max`, `deepseek-chat`, `gemini-flash-latest`) get `family` only. |

All three are optional. **The cardinal rule: only fill what an authoritative source states or naming rules derive, never guess.** An empty field is correct for vendors that publish nothing.

The rest: https://github.com/lobehub/lobehub/blob/HEAD/.agents/skills/model-bank-metadata/SKILL.md