New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Model Bank Metadata

by lobehub in lobehub/lobehub

Fills and maintains the knowledgeCutoff, family and generation fields on model cards in LobeHub's model bank, from a single new model up to repo-wide backfills.

Custom licenceAuto-check passedAI & LLM Engineering

Install Model Bank Metadata

skills CLI
$ npx skills add lobehub/lobehub --skill model-bank-metadata -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lobehub/lobehub model-bank-metadata --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/model-bank-metadata .claude/skills/model-bank-metadata && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
model-bank-metadata
GitHub stars
83k
Token cost
~2k tokens
SKILL.md length
882 words
Files
5 (incl. scripts)
Skills in repo
50
Repo updated
First seen
Licence
Custom licence

At a glance

Fills and maintains the knowledgeCutoff, family and generation fields on model cards in LobeHub's model bank, from a single new model up to repo-wide backfills.

  • Works in 5 steps: Extract ids: bun… → Research (multi-agent): chunk ids by… → Policy filter: before applying, drop… → …
  • Onboarding a new model card with its cutoff, family and generation
  • SKILL.md covers Field semantics, Sourcing rules for…, family/generation derivation and Repo-wide sweep workflow, plus 1 more section
  • Runs TypeScript scripts from its folder; calls bun, bunx and git

What it does

The skill explains how to populate three optional metadata fields on model cards in packages/model-bank. knowledgeCutoff is a year and month, or only a year, for the world-knowledge cutoff, using the reliable cutoff when a vendor distinguishes it from the training-data cutoff. family is a lowercase lineage slug finer than the organization, and generation is the family plus a version where it can be derived confidently, with rolling aliases getting a family only. The cardinal rule is to fill only what an authoritative source states or naming rules derive, and never to guess.

Accepted sources for cutoffs are vendor documentation and official model cards on Hugging Face. Scripts support sweeps across roughly 80 provider files and 1900 entries: extract-model-ids, apply-cutoffs, derive-family and apply-family. No database migration is needed, because built-in models are merged from the model bank at read time.

When your agent uses it

  • Onboarding a new model card with its cutoff, family and generation
  • Correcting a wrong knowledge cutoff using an official source
  • Running a bulk backfill of family or cutoff fields across providers

Example prompts

  • “Add the knowledge cutoff, family and generation for the new model card from the vendor docs.”
  • “Backfill family fields across all provider files and leave anything uncertain empty.”
  • “This model's cutoff looks wrong. Check the vendor's documentation and correct it.”

Requirements

  • A checkout of the LobeHub repository

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Extract ids: bun .agents/skills/model-bank-metadata/scripts/extract-model-ids.ts → unique normalized chat-model ids (normalization = last…
  2. Research (multi-agent): chunk ids by family (≤50 per chunk) and fan out one research agent per chunk (Workflow tool), each returning {id…
  3. Policy filter: before applying, drop entries whose only source is a rejected category (check the returned sources map — e.g. drop…
  4. Apply: bun .agents/skills/model-bank-metadata/scripts/apply-cutoffs.ts and bun .agents/skills/model-bank-metadata/scripts/apply-family.ts…
  5. Verify: cd packages/model-bank && bunx vitest run src/aiModels/tests/index.test.ts && bunx tsc --noEmit.

What it can do on your machine

Read from SKILL.md and the folder at commit 31b02b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 4 files in scripts/ (TypeScript), which the agent can run.

    Shell commands in SKILL.md call:

    • bun
    • bunx
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use bunx and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Model Bank Metadata loads about 2k tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 882 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 882 words (~1,962 tokens).

“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).”

— opening of SKILL.md by lobehub, Custom licence
name
model-bank-metadata
user-invocable
false

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files (scripts) in .agents/skills/model-bank-metadata of lobehub/lobehub.

  • SKILL.md
  • scripts/apply-cutoffs.ts
  • scripts/apply-family.ts
  • scripts/derive-family.ts
  • scripts/extract-model-ids.ts

Open the folder on GitHubat commit 31b02b5

Compare with similar skills

Model Bank Metadata next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Model Bank Metadata compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Model Bank Metadata this skilllobehub/lobehub83k—~2kAutomated safety check: PassCustom licence
SageMaker Serving Image Selectionhuggingface/skills11k1 repos~4.6kAutomated safety check: PassApache-2.0
Hugging Face Local Model Evalshuggingface/skills11k2 repos~1.6kAutomated safety check: PassApache-2.0
Esmfold2JimLiu/science-skills2284 repos~2.5kAutomated safety check: PassApache-2.0
Qwen Mtp GgufR6410418/Jackrong-llm-finetuning-guide1.7k—~1.7kAutomated safety check: PassMIT
Dataset Transformationawslabs/agent-plugins9161 repos~3.5kAutomated safety check: PassApache-2.0

Similar skills

  • SageMaker Serving Image Selection

    huggingface/skills

    Official

    Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.

    11k GitHub starsUsed in 1 repo~4.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Local Model Evals

    huggingface/skills

    Official

    Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.

    11k GitHub starsUsed in 2 repos~1.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Esmfold2

    JimLiu/science-skills

    Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.

    228 GitHub starsUsed in 4 repos~2.5k tokens
    AI & LLM EngineeringAuto-check passed

  • Qwen Mtp Gguf

    R6410418/Jackrong-llm-finetuning-guide

    Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.

    1.7k GitHub stars~1.7k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

  • Dataset Transformation

    awslabs/agent-plugins

    Official

    Generates code that transforms datasets between ML schemas for model training or evaluation.

    916 GitHub starsUsed in 1 repo~3.5k tokens
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Tokenizers

    Orchestra-Research/AI-Research-SKILLs

    Shows how to load, train and use fast Hugging Face tokenizers, with BPE, WordPiece and Unigram models, padding, truncation and alignment tracking.

    13k GitHub starsUsed in 6 repos~3.4k tokens
    AI & LLM EngineeringAuto-check passed

More from lobehub/lobehub

All 51 skills in this repo

  • LobeHub Interactive Prototype

    lobehub/lobehub

    Builds single-file interactive HTML prototypes rendered with the real LobeHub UI components and written as production-style React, so they can later be split into files.

    83k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Acceptance Evidence for Deliveries

    lobehub/lobehub

    Verifies a delivery end to end by driving the real product on a CLI, web, desktop or iOS Simulator surface, capturing evidence and publishing a round with the lh CLI.

    83k GitHub stars~9.7k tokensUpdated today
    Auto-check passed

  • Git Worktree Cleanup

    lobehub/lobehub

    Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.

    83k GitHub stars~2.8k tokensUpdated today
    Auto-check passed

  • LobeHub Alint Rule Set Maintenance

    lobehub/lobehub

    Maintains LobeHub's model-backed alint rule set: writing rules, removing false positives against real code, deciding warn versus error and tracking token cost.

    83k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

  • LobeHub Builtin Tool Authoring

    lobehub/lobehub

    Guides building LobeHub builtin agent tools, from the manifest and execution runtime to executors, chat UI renders and registry wiring.

    83k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • LobeHub Data Fetching Layers

    lobehub/lobehub

    Explains how LobeHub client code fetches data through services, SWR store hooks and cache keys, and when to avoid useEffect fetching or duplicated state.

    83k GitHub stars~1.8k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Model Bank Metadata

What does Model Bank Metadata do?

Fills and maintains the knowledgeCutoff, family and generation fields on model cards in LobeHub's model bank, from a single new model up to repo-wide backfills. The skill explains how to populate three optional metadata fields on model cards in packages/model-bank. knowledgeCutoff is a year and month, or only a year, for the world-knowledge cutoff, using the reliable cutoff when a vendor distinguishes it from the training-data cutoff.

When should I use Model Bank Metadata?

Model Bank Metadata fits situations like: onboarding a new model card with its cutoff, family and generation; correcting a wrong knowledge cutoff using an official source; running a bulk backfill of family or cutoff fields across providers.

How do I install Model Bank Metadata in Claude Code?

Run `npx skills add lobehub/lobehub --skill model-bank-metadata -a claude-code`. Or copy the skill folder (.agents/skills/model-bank-metadata in lobehub/lobehub) into .claude/skills/model-bank-metadata in your project. Claude Code loads it when a task matches its description.

How do I install Model Bank Metadata in Codex?

Run `npx skills add lobehub/lobehub --skill model-bank-metadata -a codex`. Or copy the skill folder (.agents/skills/model-bank-metadata in lobehub/lobehub) into .agents/skills/model-bank-metadata in your project. Codex loads it when a task matches its description.

Can I use Model Bank Metadata in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lobehub/lobehub --skill model-bank-metadata -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/model-bank-metadata, .gemini/skills/model-bank-metadata, .github/skills/model-bank-metadata and .opencode/skills/model-bank-metadata in your project.

What does Model Bank Metadata need to run?

Going by SKILL.md and its folder, Model Bank Metadata needs TypeScript for the scripts in its folder and the command-line tools its instructions call (bun, bunx and git). Our summary lists: A checkout of the LobeHub repository.

Does Model Bank Metadata access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Model Bank Metadata safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Model Bank Metadata use?

Model Bank Metadata has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Model Bank Metadata use?

About 2k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Model Bank Metadata?

Skills that share tags, products or a category with Model Bank Metadata: SageMaker Serving Image Selection (huggingface/skills, 11k stars), Hugging Face Local Model Evals (huggingface/skills, 11k stars), Esmfold2 (JimLiu/science-skills, 228 stars) and Qwen Mtp Gguf (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Model Bank Metadata?

lobehub (a GitHub organization) maintains it in lobehub/lobehub, which has 83,127 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on October 11, 2026.

Source: lobehub/lobehub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.