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
0installs0uses~552
v1.0Saved May 20, 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

76/100

Grade

B

Good

Safety

78

Quality

75

Clarity

82

Completeness

70

Summary

This skill provides instructions for interacting with the Gemini Enterprise Agent Platform Skill Registry API. It enables agents to search for skills, manage skill lifecycle (upload, update, delete), monitor long-running operations, and generate new skill scaffolding. The skill is implemented as a Python wrapper around REST API calls to Google Cloud AI Platform, with mandatory environment validation and proper authentication via Google Cloud credentials.

Detected Capabilities

http request (REST API calls to Google Cloud AI Platform)google cloud authentication (gcloud login, service account tokens)file write (local skill folder/zip uploads)file read (reading local skill folders and zip files)environment variable read (GCP_PROJECT_ID, GCP_LOCATION)json parsing and outputlong-running operation monitoring

Trigger Keywords

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

register skill to registryupload agent skillsearch skill registrymanage skill lifecycledeploy skill platformgenerate skill scaffoldmonitor skill operations

Risk Signals

INFO

REST API calls to external Google Cloud endpoint with Bearer token authentication

scripts/skill_registry_ops.py, lines 15-50, 80-90, 105-115, 130-145, 160-175, 190-210
WARNING

Environment variable dependency on GCP_PROJECT_ID and GCP_LOCATION without validation of format or special characters

scripts/skill_registry_ops.py, line 290-295
WARNING

Local file reads from user-specified paths (--folder, --zip-file) without path traversal validation

scripts/skill_registry_ops.py, lines 45-56, 180-188
INFO

Google Cloud credentials obtained via google.auth.default() and refreshed with Request()

scripts/skill_registry_ops.py, lines 15-18

Referenced Domains

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

www.apache.org{endpoint}

Use Cases

  • Register new agent skills to the platform registry
  • Search and discover available skills by keyword or semantic query
  • Update or delete existing skills in the registry
  • Monitor async operations (uploads, updates, deletes) to completion
  • Generate standardized scaffolding for new agent skill projects
  • Inspect skill revision history and retrieve specific versions

Quality Notes

  • Positive: Clear separation of concerns with dedicated reference docs for discovery, lifecycle, operations, and generation
  • Positive: Mandatory environment validation check enforced before operations
  • Positive: Comprehensive command documentation with examples for all operations
  • Positive: Error handling with HTTP status code checks and informative error messages
  • Positive: All required fields explicitly documented with usage examples
  • Positive: Proper argument parsing with mutually exclusive groups (--zip-file vs --folder)
  • Negative: Path traversal vulnerability not explicitly documented or guarded against in --folder parameter
  • Negative: No rate limiting or retry logic for API calls
  • Negative: Limited guidance on handling API failures or partial uploads
  • Negative: generate-skill.md references 'execution workflow' but lacks concrete implementation details
Model: claude-haiku-4-5-20251001Analyzed: May 20, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

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

Command Palette

Search for a command to run...