Catalog
google/agent-platform-skill-registry

google

agent-platform-skill-registry

Interact 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.

global
category:AiAndMachineLearning
New~552
v1.1Saved Jun 28, 2026

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

Files8
8 files · 29.6 KB

Select a file to preview

Overall Score

82/100

Grade

B

Good

Safety

85

Quality

85

Clarity

82

Completeness

76

Summary

This skill provides instructions for interacting with the Gemini Enterprise Agent Platform Skill Registry, enabling agents to create, search, list, and manage skills through Python scripts that call the Google Cloud AI Platform API. It includes operations for skill discovery, lifecycle management (upload/update/delete), operation monitoring, and automated skill scaffolding, all authenticated via Google Cloud credentials.

Detected Capabilities

network request (HTTP GET, POST, PATCH, DELETE)google cloud authentication (google.auth)file read (zip files, local folders)zip file creation and encodingenvironment variable access (GCP_PROJECT_ID, GCP_LOCATION)json parsing and outputcommand-line argument parsing

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

search agent skillsregister skillmanage skill registryupload skilldiscover capabilitiesskill version historygenerate skill scaffold

Risk Signals

INFO

Network requests to googleapis.com endpoints

scripts/skill_registry_ops.py (lines: upload, search, get_skill, list_skills, delete_skill, update_skill, list_skill_revision, get_skill_revision, monitor functions)
INFO

Google Cloud API authentication via google.auth.default()

scripts/skill_registry_ops.py (get_access_token function)
INFO

Environment variable dependency on GCP_PROJECT_ID and GCP_LOCATION

scripts/skill_registry_ops.py (main function), SKILL.md (Prerequisites section)
INFO

File operations: reading local folders and zip files for upload

scripts/skill_registry_ops.py (upload and update_skill functions)
INFO

Validation check mandatory before operations

SKILL.md (Core Directives section)
WARNING

Placeholder endpoint variable {endpoint} referenced in domain extraction

Referenced Domains metadata

Referenced Domains

External domains referenced in skill content, detected by static analysis.

www.apache.org{endpoint}

Use Cases

  • Search and discover available agent skills in a shared registry
  • Upload and register new custom agent skills to the platform
  • Update existing skill metadata and implementations
  • Delete obsolete or no-longer-needed skills from the registry
  • Monitor long-running operations (LRO) from skill lifecycle changes
  • Generate boilerplate SKILL.md and directory structure for new skills
  • Inspect skill revision histories and retrieve specific versions

Quality Notes

  • Comprehensive documentation with clear separation of concerns across four reference guides (query, manage, monitor, generate)
  • Well-structured Python script with distinct functions for each API operation and robust error handling (HTTP status code checks)
  • Mandatory environment validation enforced via Core Directives before operations
  • Clear prerequisites section documenting required libraries and authentication setup
  • Good use of examples showing both folder and zip file upload options
  • Directory structure guidance in generate-skill.md is thorough and production-aware
  • Minor: Placeholder domain {endpoint} appears in static analysis—likely a template variable that should be clarified
  • Mutually exclusive argument groups properly configured in argparse for upload and update operations
  • Extensive reference documentation with supported flags clearly listed for each operation
Model: claude-haiku-4-5-20251001Analyzed: Jun 28, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

v1.1

Content updated

2026-06-28

Latest
v1.0

No changelog

2026-05-20

Add google/agent-platform-skill-registry to your library

Command Palette

Search for a command to run...

google/agent-platform-skill-registry | SkillRepo