Agent skill

Kiln Model Sweep

by Kiln-AI in Kiln-AI/Kiln

The scheduled model sweep. An agent skill from Kiln-AI/Kiln.

Custom licenceAuto-check: notesAI & LLM Engineering

Install Kiln Model Sweep

skills CLI
$ npx skills add Kiln-AI/Kiln --skill kiln-model-sweep -a claude-code

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

GitHub CLI
$ gh skill install Kiln-AI/Kiln kiln-model-sweep --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/kiln-model-sweep .claude/skills/kiln-model-sweep && 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
kiln-model-sweep
GitHub stars
5.2k
Token cost
~3.6k tokens
SKILL.md length
2,097 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
Custom licence

At a glance

The scheduled model sweep. An agent skill from Kiln-AI/Kiln.

  • Works in 3 steps: .agents/skills/claude-maintain-models/SKI… → .agents/skills/kiln-check-deprecation/SKI… → .agents/skills/open-pr/SKILL.md for…
  • Asked to run the model sweep by hand
  • Calls uv, git and npm; needs FIREWORKS_API_KEY and ANTHROPIC_API_KEY
  • Deprecate models unattended

What it does

Kiln Model Sweep is an agent skill from Kiln-AI/Kiln. The scheduled model sweep. Reads the team's models channel for hints, discovers new LLM models, adds them to mlmodellist.py, runs the paid tests, marks dead provider entries deprecated, opens PRs under the team's rules, announces them in Slack, and checks whether remoteconfig needs a publish PR. Use when asked to run the model sweep by hand, to add or deprecate models unattended, or to change how the daily sweep behaves.

Its SKILL.md is about 3.6k 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 Slack. 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

  • Asked to run the model sweep by hand
  • Deprecate models unattended
  • Change how the daily sweep behaves

Example prompts

  • “/kiln-model-sweep”

Requirements

  • Python 3
  • Docker
  • A credential in FIREWORKS_API_KEY
  • A credential in ANTHROPIC_API_KEY

Workflow steps

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

  1. .agents/skills/claude-maintain-models/SKILL.md, including its Phase 1 discovery for models released in the last 14 days and its Phase 1B…
  2. .agents/skills/kiln-check-deprecation/SKILL.md.
  3. .agents/skills/open-pr/SKILL.md for every PR.

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 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

    Shell commands in SKILL.md call:

    • uv
    • git
    • npm
    • gh
    • python3

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

  • Network

    No URLs in SKILL.md. Its commands use uv, git, npm and gh, 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 these keys or tokens, usually read from environment variables:

    • FIREWORKS_API_KEY
    • ANTHROPIC_API_KEY
    • KILN_ANTHROPIC_API_KEY

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

Context cost

Kiln Model Sweep loads about 3.6k tokens when it runs. Until then it costs about 111 tokens; SKILL.md has 2,097 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~111
When it runs · the whole SKILL.md, loaded when a task matches
~3.6k

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.

  • NoteMentions a .env fileSKILL.md:95
    - Deprecations: there is no `.env` file here, the keys are already exported, so skip that export line. Mark an entry `de

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 2,097 words (~3,567 tokens).

“The prompt a scheduled cloud routine runs each weekday morning. It is a thin wrapper: the procedure lives in claude-maintain-models, kiln-check-deprecation and open-pr; this file pre-answers their gates so a run finishes with nobody watching. The design, the reasons behind…”

— opening of SKILL.md by Kiln-AI, Custom licence
name
kiln-model-sweep

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/kiln-model-sweep of Kiln-AI/Kiln.

Open the folder on GitHubat commit 8ac9075

Compare with similar skills

Kiln Model Sweep 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.

Kiln Model Sweep compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Kiln Model Sweep this skillKiln-AI/Kiln5.2k—~3.6kAutomated safety check: NotesCustom licence
Quality FlywheelGoogleCloudPlatform/vertex-ai-samples792—~2kAutomated safety check: PassApache-2.0
Scaffold Examplecomet-ml/comet-examples174—~1kAutomated safety check: PassNone
Adapting Transfer Learning Modelsjeremylongshore/tons-of-skills-marketplace2.8k—~1.1kAutomated safety check: PassMIT
Christopher ManningK-Dense-AI/mimeo282—~1.8kAutomated safety check: PassMIT
ML Cv Specialistalirezarezvani/claude-cto-team117—~3.1kAutomated safety check: PassMIT

Similar skills

  • Quality Flywheel

    GoogleCloudPlatform/vertex-ai-samples

    Evaluate and improve GenAI models and agents using the Google GenAI Evaluation SDK.

    792 GitHub stars~2k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed
  • Scaffold Example

    comet-ml/comet-examples

    Scaffold a brand-new Comet example in this repo from the canonical template under templates/integration-example/.

    174 GitHub stars~1k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed
  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Christopher Manning

    K-Dense-AI/mimeo

    Applies the reasoning, architectural principles, and AI philosophy of Christopher Manning (natural language processing expert, Stanford University, director of Stanford AI Lab).

    282 GitHub stars~1.8k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • ML Cv Specialist

    alirezarezvani/claude-cto-team

    Deep expertise in ML/CV model selection, training pipelines, and inference architecture.

    117 GitHub stars~3.1k tokensUpdated 9 mo ago
    AI & LLM EngineeringAuto-check passed
  • SwanLab Experiment Tracking

    Orchestra-Research/AI-Research-SKILLs

    Shows how to log ML runs, configs, metrics and media with SwanLab and view them in cloud, local or self-hosted dashboards.

    13k GitHub stars~2.4k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

More from Kiln-AI/Kiln

All 14 skills in this repo
  • Check Kiln's model list for deprecated or sunset models across all providers.

    5.2k GitHub stars~2.5k tokensUpdated 2 days ago
    Auto-check: notes
  • Check Kiln's fine-tunable model list for deprecated or unsupported base models.

    5.2k GitHub stars~1.9k tokensUpdated 2 days ago
    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 2 days ago
    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 2 days ago
    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 2 days ago
    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 2 days ago
    Auto-check passed

Works with

Questions about Kiln Model Sweep

What does Kiln Model Sweep do?

The scheduled model sweep. An agent skill from Kiln-AI/Kiln. Kiln Model Sweep is an agent skill from Kiln-AI/Kiln. The scheduled model sweep.

When should I use Kiln Model Sweep?

Kiln Model Sweep fits situations like: asked to run the model sweep by hand; deprecate models unattended; change how the daily sweep behaves.

How do I install Kiln Model Sweep in Claude Code?

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

How do I install Kiln Model Sweep in Codex?

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

Can I use Kiln Model Sweep 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 kiln-model-sweep -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kiln-model-sweep, .gemini/skills/kiln-model-sweep, .github/skills/kiln-model-sweep and .opencode/skills/kiln-model-sweep in your project.

What does Kiln Model Sweep need to run?

Going by SKILL.md and its folder, Kiln Model Sweep needs the command-line tools its instructions call (uv, git, npm, gh and python3) and credentials named FIREWORKS_API_KEY, ANTHROPIC_API_KEY and KILN_ANTHROPIC_API_KEY. Our summary lists: Python 3; Docker; A credential in FIREWORKS_API_KEY; A credential in ANTHROPIC_API_KEY.

Does Kiln Model Sweep access the network?

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

Is Kiln Model Sweep safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Kiln Model Sweep use?

Kiln Model Sweep 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 Kiln Model Sweep use?

About 3.6k tokens (SKILL.md is roughly 14k 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 Kiln Model Sweep?

Skills that share tags, products or a category with Kiln Model Sweep: Quality Flywheel (GoogleCloudPlatform/vertex-ai-samples, 792 stars), Scaffold Example (comet-ml/comet-examples, 174 stars), Adapting Transfer Learning Models (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and Christopher Manning (K-Dense-AI/mimeo, 282 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kiln Model Sweep?

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.