Skip to content
Skill

Agent platform autorater customization

Customizes an autorater (evaluation metric) for an AI agent so its grades match the user's own judgment, starting from the agent's real traj

Install
Scripts
Python
Platforms
Claude Code, Codex, Cursor
GitHub stars
24.4K
Last commit
today
License
Apache-2.0
Listing updated
today

When your agent uses it

Customizes an autorater (evaluation metric) for an AI agent so its grades match the user's own judgment, starting from the agent's real trajectories. Use when a user wants a metric tailored to their agent, wants to turn failing trajectories into rubrics, says an existing autorater grades their agent wrong, or wants an autorater to agree with human labels (autorater hillclimbing, judge calibration). Don't use for quick evals with built-in metrics or for improving the agent itself (use agent-platform-eval-flywheel).

From the skill's SKILL.md. Your agent reads this description to decide when to load the skill.

What it can access

From a static check of its 12 files (76 KB) on GitHub on 17 November 2026. Nothing was run. Read the files before you install a skill: it can tell your agent to run anything its tools allow.

Install

Copy the skill folder to ~/.claude/skills/agent-platform-autorater-customization to use it in all your projects:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/google/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/agent-platform-autorater-customization &&
cp -R "$tmp/skills/cloud/agent-platform-autorater-customization" ~/.claude/skills/agent-platform-autorater-customization &&
rm -rf "$tmp"

For one project only, put the folder in .claude/skills/agent-platform-autorater-customization inside it instead.

Claude Code docs on skills

Copy the skill folder to ~/.agents/skills/agent-platform-autorater-customization to use it in every repository:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/google/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/agent-platform-autorater-customization &&
cp -R "$tmp/skills/cloud/agent-platform-autorater-customization" ~/.agents/skills/agent-platform-autorater-customization &&
rm -rf "$tmp"

For one repository only, put the folder in .agents/skills/agent-platform-autorater-customization inside it instead.

Codex docs on skills

Copy the skill folder to ~/.cursor/skills/agent-platform-autorater-customization to use it in every project:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/google/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/agent-platform-autorater-customization &&
cp -R "$tmp/skills/cloud/agent-platform-autorater-customization" ~/.cursor/skills/agent-platform-autorater-customization &&
rm -rf "$tmp"

For one project only, put the folder in .cursor/skills/agent-platform-autorater-customization inside it instead.

Cursor docs on skills

Run in a terminal (add --scope workspace to install it for the current workspace only):

gemini skills install https://github.com/google/skills.git --path skills/cloud/agent-platform-autorater-customization

Or copy the folder to ~/.gemini/skills/agent-platform-autorater-customization yourself.

Gemini CLI docs on skills

For GitHub Copilot in VS Code, copy the skill folder to ~/.copilot/skills/agent-platform-autorater-customization:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/google/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/agent-platform-autorater-customization &&
cp -R "$tmp/skills/cloud/agent-platform-autorater-customization" ~/.copilot/skills/agent-platform-autorater-customization &&
rm -rf "$tmp"

For one project only, put the folder in .github/skills/agent-platform-autorater-customization inside it instead.

VS Code docs on skills

Get the folder:

git clone --depth 1 https://github.com/google/skills.git

Then copy skills/skills/cloud/agent-platform-autorater-customization into your agent's skills folder as agent-platform-autorater-customization. Agents that support SKILL.md read one folder per skill.

The SKILL.md format

Agent platform autorater customization FAQ

How do I install Agent platform autorater customization in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/agent-platform-autorater-customization to use it in all your projects, or to .claude/skills/agent-platform-autorater-customization in one project.

Does Agent platform autorater customization run scripts?

Yes. It runs Python scripts. No network calls were found in its scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

Which AI agents can use Agent platform autorater customization?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

What are the best alternatives to Agent platform autorater customization?

The closest alternatives to Agent platform autorater customization are Academy guide, MCP builder, Claude API, Nano banana pro openrouter and Dotnet MCP builder.

More from google/skills

  1. Google platform decision and setup guidance, loaded on demand from Google's skill catalog

    • Open source
    • 24.4K GitHub stars
  2. Provides safety-critical validation, guardrails, and data reduction for gcloud CLI operations across Google Cloud Platform (GCP) services an

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  3. Provides expert guidance on Identity and Access Management (IAM) and authenticating and authorizing to Google Cloud services and APIs, cover

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  4. Guides a developer's first steps on Google Cloud, covering account creation, billing setup, project management, and deploying a first resour

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  5. Searches, retrieves, and synthesizes official Google developer documentation across Google Cloud, AI/Gemini, Android, Chrome, Web, Flutter,

    • Open source
    • 24.4K GitHub stars
  6. Guides developers through managing (adding, removing, and clearing) audience members for Google products using the Data Manager API and its

    • Open source
    • 24.4K GitHub stars

Alternatives to Agent platform autorater customization

  1. Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching cour

    • 196K GitHub stars
    • AI models and LLM tooling
  2. Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-design

    • 196K GitHub stars
    • AI models and LLM tooling
  3. Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model

    • 196K GitHub stars
    • AI models and LLM tooling
  4. Generate or edit images via OpenRouter with the Gemini 3 Pro Image model

    • Open source
    • 41.3K GitHub stars
    • Design and media
  5. Build Model Context Protocol (MCP) servers in C#/.NET against the current ModelContextProtocol 2.x NuGet packages

    • Open source
    • 41.3K GitHub stars
    • AI models and LLM tooling
  6. Generate images using AI

    • Open source
    • 41.3K GitHub stars
    • Design and media