Skills Catalog

One graded, governed library for every agent you run.

Publish free, with every skill graded and attributed to you. A Developer account connects your dev environment with one command and keeps your skills synced and current. Teams get one approved library — each repo gets the skills it needs, at the versions you approve, with any drift in plain sight.

  • One command to connectnpx skillrepo init syncs a Developer library straight to your dev environment.
  • Automatic updatesWhen a publisher ships a new version, your next session has it.
  • Graded for safetyEvery skill scored A–F. See findings before you sync.
  • Bring it to your teamTeamAudit log, per-member sync, library-level grade.

No credit card. Catalog stays free to download anytime.·1,690 skills published

Preview · how teams use SkillRepoLearn more

Searching by meaning· free account to run

1,690 skills found

Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tool… more

New

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent's t… more

New

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails an… more

New

Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, l… more

New

Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use this skill when: - Evaluating an agent system's security postu… more

New

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer t… more

New

Configures best-practice alerting policies for Google Cloud Vertex AI / Agent Platform agents on Agent Runtime. Use when analyzing, writing, or deploying alerti… more

New

Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check deployment status, verify serving endpoints, or clean up resources by… more

New

Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platfor… more

New

Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when evaluating an agent or model, bu… more

New

Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, De… more

New

Guides agents and users through migrating from Gemini API in Google AI Studio to Gemini Enterprise Agent Platform (formerly Vertex AI). Use this skill when movi… more

New

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Age… more

New

Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform. Don't use… more

New

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting… more

New

Interact with the Gemini Enterprise Agent Platform Skill Registry to create and search for available skills. Use this skill to enable agents to register functio… more

New

Troubleshoots Google Cloud Gemini Enterprise Agent Platform issues (Agent Gateway, Registry, Identity, Policies, Model Armor, Identity-Aware Proxy (IAP)). Use w… more

New

Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outsi… more

New

Manages GenAI tuning jobs in Agent Platform. Use this to list, get, or cancel ongoing model tuning jobs. Don't use for fine-tuning models (use `agent-platform-t… more

New

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concre… more

New

Page 2 of 85

Start building with better skills

Publishing is free — no credit card, and every skill is graded and attributed to you. Ready to sync? A Developer account connects your dev environment in minutes.

Use these skills in your dev environment

Command Palette

Search for a command to run...