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

Claude Maintain Models

by Kiln-AI in Kiln-AI/Kiln

Add new AI models to Kiln's mlmodellist.py and produce a Discord announcement.

Custom licenceAuto-check: notesAI & LLM Engineering

Install Claude Maintain Models

skills CLI
$ npx skills add Kiln-AI/Kiln --skill claude-maintain-models -a claude-code

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

GitHub CLI
$ gh skill install Kiln-AI/Kiln claude-maintain-models --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/Kiln-AI/Kiln.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/claude-maintain-models .claude/skills/claude-maintain-models && 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
claude-maintain-models
GitHub stars
5.2k
Token cost
~15k tokens
SKILL.md length
6,858 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
Custom licence

At a glance

Add new AI models to Kiln's mlmodellist.py and produce a Discord announcement.

  • Works in 5 steps: Model Discovery (only when asked to find… → Gather Context → Code Changes → …
  • The user wants to add
  • SKILL.md covers Global Rules, Phase 1 – Model Discovery…, Phase 1B – Lagging-Provider… and Phase 2 – Gather Context, plus 6 more sections
  • Calls jq, curl and uv; reaches models.dev and api.litellm.ai; needs TOGETHERAI_API_KEY and CLOUDFLARE_API_KEY

What it does

Claude Maintain Models is an agent skill from Kiln-AI/Kiln. Add new AI models to Kiln's mlmodellist.py and produce a Discord announcement. Use when the user wants to add, integrate, or register a new LLM model (e.g. Claude, GPT, DeepSeek, Gemini, Kimi, Qwen, Grok) into the Kiln model list, mentions adding a model to mlmodellist.py, asks to discover/find new models that are available but not yet in Kiln, or wants to add a net-new AI provider to Kiln.

Its SKILL.md is about 15k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Machine learning. It works with DeepSeek, Discord, Kimi and Qwen. The repository describes itself as: Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

When your agent uses it

  • The user wants to add
  • Register a new LLM model (e.g

Example prompts

  • “/claude-maintain-models”

Requirements

  • Pre-approved tools (allowed-tools): Read, Edit, Write, Bash, Grep, Glob, Agent, WebSearch, WebFetch

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Model Discovery (only when asked to find new/missing models)
  2. Gather Context
  3. Code Changes
  4. Run Tests
  5. Create Pull Request

What it can do on your machine

Read from SKILL.md and the folder at commit 8ac9075. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Edit
    • Write
    • Bash
    • Grep
    • Glob
    • Agent
    • WebSearch
    • WebFetch

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • jq
    • curl
    • uv
    • git
    • gcloud
    • gh
    • make

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • models.dev
    • api.litellm.ai
    • openrouter.ai
    • vercel.com
    • fireworks.ai
    • api.together.xyz
    • siliconflow.com
    • github.com
    • developers.openai.com
    • api.featherless.ai
    • ai-cloudflare-com.pages.dev

    Also links to:

    • platform.claude.com
    • docs.anthropic.com
    • inference-docs.cerebras.ai
    • developers.cloudflare.com

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • TOGETHERAI_API_KEY
    • CLOUDFLARE_API_KEY
    • KILN_ANTHROPIC_API_KEY
    • ANTHROPIC_API_KEY
    • TOGETHER_API_KEY
    • FEATHERLESS_AI_API_KEY

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

Context cost

Claude Maintain Models loads about 15k tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 6,858 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~105
When it runs · the whole SKILL.md, loaded when a task matches
~15k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Edit, Write, Bash, Grep, Glob, Agent, WebSearch, WebFetch

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); files beside SKILL.md 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 6,858 words (~15,042 tokens).

“Branch check first: if the request involves a provider Kiln does not support yet, start at Adding a Net-New Provider. That workflow spans core, server, UI, tests, and tooling, and is gated on a client release — the model-entry steps…”

— opening of SKILL.md by Kiln-AI, Custom licence
name
claude-maintain-models
allowed-tools
Read, Edit, Write, Bash, Grep, Glob, Agent, WebSearch, WebFetch

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/claude-maintain-models of Kiln-AI/Kiln.

Open the folder on GitHubat commit 8ac9075

Compare with similar skills

Claude Maintain Models 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.

Claude Maintain Models compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Claude Maintain Models this skillKiln-AI/Kiln5.2k—~15kAutomated safety check: NotesCustom licence
Agent Platform Inferencegoogle/skills21k—~9.5kAutomated safety check: PassApache-2.0
Dingo VerifyMigoXLab/dingo757—~833Automated safety check: PassApache-2.0
Bridgic LLMsbitsky-tech/bridgic155—~839Automated safety check: NotesMIT
Visionxiincs/claude-code-vision-skill170—~1.2kAutomated safety check: PassMIT
PiDeck Usage Probe Helperayuayue/PiDeck1.1k—~1.4kAutomated safety check: PassMIT

Similar skills

  • Agent Platform Inference

    google/skills

    Official

    Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.).

    21k GitHub stars~9.5k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Dingo Verify

    MigoXLab/dingo

    A skill your agent uses when the user wants to fact-check an article or verify factual claims in a document.

    757 GitHub stars~833 tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

  • Bridgic LLMs

    bitsky-tech/bridgic

    LLM provider initialization for bridgic projects. An agent skill from bitsky-tech/bridgic.

    155 GitHub stars~839 tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check: notes

  • Vision

    xiincs/claude-code-vision-skill

    Call vision models (Doubao, Qwen, DeepSeek, OpenAI) to analyze images.

    170 GitHub stars~1.2k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • PiDeck Usage Probe Helper

    ayuayue/PiDeck

    Helps show a model provider's usage, balance or quota in PiDeck: checks built-in support, points to the dialog templates, or writes a custom probe entry.

    1.1k GitHub stars~1.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Mesh API

    mr-tbot/mesh-api

    Interact with a Meshtastic LoRa mesh network through MESH-API — list nodes, read messages, send texts, and check connection status.

    180 GitHub stars~1.8k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed

More from Kiln-AI/Kiln

All 14 skills in this repo

  • Kiln Check Deprecation

    Kiln-AI/Kiln

    Check Kiln's model list for deprecated or sunset models across all providers.

    5.2k GitHub stars~2.5k tokensUpdated yesterday
    Auto-check: notes

  • Kiln Check Finetune Deprecation

    Kiln-AI/Kiln

    Check Kiln's fine-tunable model list for deprecated or unsupported base models.

    5.2k GitHub stars~1.9k tokensUpdated yesterday
    Auto-check: notes

  • Release Digest

    Kiln-AI/Kiln

    Post a "what's changed since the last release" recap to the release Slack channel for final QA.

    5.2k GitHub stars~2.7k tokensUpdated yesterday
    Auto-check passed

  • Kiln Conventions

    Kiln-AI/Kiln

    Kiln's code conventions and per-area gotchas, plus a diff gate that enforces the mechanical ones.

    5.2k GitHub stars~1.7k tokensUpdated yesterday
    Auto-check: notes

  • Playwright

    Kiln-AI/Kiln

    Look at Kiln's UI in a real browser, and run its end-to-end tests.

    5.2k GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

  • Open PR

    Kiln-AI/Kiln

    Open a pull request on the Kiln repo for a human to complete.

    5.2k GitHub stars~6.1k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Claude Maintain Models

What does Claude Maintain Models do?

Add new AI models to Kiln's mlmodellist.py and produce a Discord announcement. Claude Maintain Models is an agent skill from Kiln-AI/Kiln.py and produce a Discord announcement.

When should I use Claude Maintain Models?

Claude Maintain Models fits situations like: the user wants to add; register a new LLM model (e.g.

How do I install Claude Maintain Models in Claude Code?

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

How do I install Claude Maintain Models in Codex?

Run `npx skills add Kiln-AI/Kiln --skill claude-maintain-models -a codex`. Or copy the skill folder (.agents/skills/claude-maintain-models in Kiln-AI/Kiln) into .agents/skills/claude-maintain-models in your project. Codex loads it when a task matches its description.

Can I use Claude Maintain Models 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 Kiln-AI/Kiln --skill claude-maintain-models -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/claude-maintain-models, .gemini/skills/claude-maintain-models, .github/skills/claude-maintain-models and .opencode/skills/claude-maintain-models in your project.

What does Claude Maintain Models need to run?

Going by SKILL.md and its folder, Claude Maintain Models needs the command-line tools its instructions call (jq, curl, uv, git, gcloud and gh) and credentials named TOGETHERAI_API_KEY, CLOUDFLARE_API_KEY, KILN_ANTHROPIC_API_KEY and ANTHROPIC_API_KEY. Its frontmatter pre-approves these tools: Read, Edit, Write, Bash, Grep, Glob, Agent, WebSearch, WebFetch.

Does Claude Maintain Models access the network?

SKILL.md names 15 domains. In commands or code: models.dev, api.litellm.ai, openrouter.ai, vercel.com, fireworks.ai, api.together.xyz, siliconflow.com, github.com, developers.openai.com, api.featherless.ai and ai-cloudflare-com.pages.dev; the agent is likely to contact these when it follows the instructions. As links in the text: platform.claude.com, docs.anthropic.com, inference-docs.cerebras.ai and developers.cloudflare.com. This is read from the text; nothing was executed.

Is Claude Maintain Models safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Claude Maintain Models use?

Claude Maintain Models 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 Claude Maintain Models use?

About 15k tokens (SKILL.md is roughly 60k 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 Claude Maintain Models?

Skills that share tags, products or a category with Claude Maintain Models: Agent Platform Inference (google/skills, 21k stars), Dingo Verify (MigoXLab/dingo, 757 stars), Bridgic LLMs (bitsky-tech/bridgic, 155 stars) and Vision (xiincs/claude-code-vision-skill, 170 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Claude Maintain Models?

Kiln-AI (a GitHub organization) maintains it in Kiln-AI/Kiln, which has 5,181 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 9, 2026.

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