tokens&
For enterprises
Submit a resource
tokens&

Find tools, check provider offers, save a build plan, and share your work when you’re ready.

For buildersFor enterprises

For builders

  • Startup credits and perks
  • Agent Skills
  • Publish a project

For enterprises

  • Start free company workspace
  • Submit a tool, product, or perk

Community

  • Community
  • Newsletter
  • Events
Xin

© 2026 tokensand, LLC. All rights reserved.

  • Terms
  • Privacy
  • Security
  • Data Processing
  • Status
  1. Home
  2. Agent Skills
  3. Agent Platform skill registry
GoogleAgents
SKILL.md
License identified

Agent Skill

Agent Platform skill registry

Discover, register, version, generate, update, and inspect skills in Gemini Enterprise Agent Platform.

skill-registrydiscoverylifecycle
Install this skillView repository

Package facts

Sourced from the vendor's own repository.

Vendor
Google
Category
Agents
License
Apache-2.0
License review
License identified
Supported clients
Codex, Cursor, Claude Code, VS Code, GitHub Copilot, Gemini CLI
SKILL.md size
2,314 bytes

Source snapshot: 2026-09-04. This listing does not verify installation, security, vendor participation, or product use.

Raw SKILL.mdSource repositoryInstall the Tokens& Agent Pack

Skill specification

Declared by Google in the package front matter. Trigger conditions are what the coding agent matches on before it loads the skill.

Agent Platform skill registry SKILL.md front matter fields
Skill nameagent-platform-skill-registry
Trigger conditionsInteract with the Gemini Enterprise Agent Platform Skill Registry to create and search for available skills. Use this skill to enable agents to register functionality or discover new capabilities.
Upstream categoryAiAndMachineLearning

Install agent-platform-skill-registry

In a terminal with Node.js, npm and Git, run the command for your agent. The Skills CLI installs the complete package directory, including referenced files within it. Review its install prompt, then start a new agent session. A skill package does not set up an MCP server connection.

Claude Code

.claude/skills/agent-platform-skill-registry/SKILL.md

Project skills are committed with the repo. Use the user directory for a personal install across every project.

Project install

npx skills add 'https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry' --skill 'agent-platform-skill-registry' --agent 'claude-code'

Personal install

npx skills add 'https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry' --skill 'agent-platform-skill-registry' --agent 'claude-code' --global

Codex

.agents/skills/agent-platform-skill-registry/SKILL.md

Codex reads `.agents/skills/` as its primary location, which is also the cross-platform default other clients honour.

Project install

npx skills add 'https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry' --skill 'agent-platform-skill-registry' --agent 'codex'

Personal install

npx skills add 'https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry' --skill 'agent-platform-skill-registry' --agent 'codex' --global

Cursor

.agents/skills/agent-platform-skill-registry/SKILL.md

Cursor also loads `.agents/skills/`, `.claude/skills/`, and `.codex/skills/`, so one committed copy can serve several clients.

Project install

npx skills add 'https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry' --skill 'agent-platform-skill-registry' --agent 'cursor'

Personal install

npx skills add 'https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry' --skill 'agent-platform-skill-registry' --agent 'cursor' --global

Gemini CLI

.agents/skills/agent-platform-skill-registry/SKILL.md

Gemini CLI reads `.agents/skills/` first when both directories exist.

Project install

npx skills add 'https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry' --skill 'agent-platform-skill-registry' --agent 'gemini-cli'

Personal install

npx skills add 'https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry' --skill 'agent-platform-skill-registry' --agent 'gemini-cli' --global

GitHub Copilot

.agents/skills/agent-platform-skill-registry/SKILL.md

The Skills CLI uses the shared `.agents/skills/` directory for Copilot project installs.

Project install

npx skills add 'https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry' --skill 'agent-platform-skill-registry' --agent 'github-copilot'

Personal install

npx skills add 'https://github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry' --skill 'agent-platform-skill-registry' --agent 'github-copilot' --global

SKILL.md

View raw source

Source snapshot fetched 2026-09-04 from github.com/google/skills/tree/main/skills/cloud/agent-platform-skill-registry. The install command fetches the upstream package, which may have changed since this snapshot.

Skill Registry

This skill provides instructions for interacting with the Skill Registry on the Gemini Enterprise Agent Platform.

Core Capabilities

  • Skill Discovery - Query the registry to easily search, list, get specific skills, and inspect revision histories.
  • Skill Lifecycle Management - Upload, update, or permanently delete skills.
  • Operation Monitoring - Utility to check the completion status of long-running state changes (LROs).
  • Generate Skill - Automate the initial scaffolding of new agent skills locally.

Core Directives

  • Mandatory Validation: ALWAYS execute the environment validation check before performing any operations.

Before any operation, you must validate the core environment.

    # Execute the validation script
    python3 scripts/validate_env.py

Prerequisites & Authentication

Library & Authentication

Ensure you have the latest Google Cloud credentials and libraries installed.

# Install required libraries
pip install google-auth requests

# Authenticate with Google Cloud
gcloud auth application-default login

Environment Variables

The following variables are required for operations:

  • GCP_PROJECT_ID: Your Google Cloud Project ID.
  • GCP_LOCATION: The region (e.g., us-central1).

Quickstart

Quickly search for available skills in the registry:

python3 scripts/skill_registry_ops.py search \
  --query "test skill" \
  --top-k 5

Operations

  • Skill Discovery: query-skills.md
  • Skill Lifecycle: manage-skills.md
  • Monitor Operations: monitor-operations.md
  • Generate Skill: generate-skill.md

Add the registry badge

Maintainers can link this listing from the skill's own README. Free, no account needed, and it points back at the rendered package for anyone browsing the repo.

Markdown

[![Agent Platform skill registry on tokens&](https://tokensand.com/api/badges/skill/google-agent-platform-skill-registry)](https://tokensand.com/agent-skills/google-agent-platform-skill-registry)

HTML

<a href="https://tokensand.com/agent-skills/google-agent-platform-skill-registry" target="_blank" rel="noopener">
  <img src="https://tokensand.com/api/badges/skill/google-agent-platform-skill-registry" alt="Agent Platform skill registry on tokens&" />
</a>

More Google Agent Skills

All Agent Skills

Agent Platform eval flywheel

Build eval datasets, choose quality metrics, analyze failures, and compare agent improvements systematically.

Agents

Agent Platform model inference

Call Gemini and OpenMaaS models with current SDKs, correct endpoints, authentication, and error handling.

Models

Agent Platform prompt management

Create, retrieve, version, list, and safely delete managed prompts using repeatable Python workflows.

Agents

Agent Platform RAG engine

Manage RAG corpora and files, retrieve grounded context, and generate corpus-grounded responses.

Docs

AI Studio to Agent Platform migration

Move Gemini applications from Google AI Studio to cloud IAM, billing, telemetry, and enterprise infrastructure.

Models

Gemini API on Agent Platform

Build multimodal, tool-using, streaming, cached, and batch Gemini applications with current Google Gen AI SDKs.

Models