Loading...
Loading...
Found 11,902 Skills
Install groove backends, companions, and AGENTS.md bootstrap. Run once per repo.
Orchestration workflow for orchestrator role ONLY. Use when: - Agent's role name (tmux pane title) is "orchestrator"
Why build on Ethereum specifically. The AI agent angle — ERC-8004, x402, composability, permissionless deployment. Use when a user asks "should I build on Ethereum?", "why blockchain?", or when an agent needs to recommend a chain for a project.
Graduate a workflow insight from learned/<topic>.md into AGENTS.md as a permanent constraint. Use when a lesson is stable enough to apply to every future session.
MUST READ before setting up observability for ADK agents or when analyzing production traffic, debugging agent behavior, or improving agent performance. ADK observability guide — Cloud Trace, prompt-response logging, BigQuery Agent Analytics, third-party integrations, and troubleshooting. Use when configuring monitoring, tracing, or logging for agents, or when understanding how a deployed agent handles real traffic.
Set up the Google Workspace CLI (gws) from scratch. Guides through GCP project creation, OAuth credentials, authentication, and installing 90+ agent skills for Claude Code. Use when setting up gws for the first time, configuring Google Workspace API access, or troubleshooting gws auth issues. Triggers: "set up gws", "google workspace cli", "gws setup", "install gws".
Search and discover 50,000+ AI models on ModelsLab, check usage analytics, and monitor generation history via the Agent Control Plane API.
Implement OpenAI Harness Engineering practices in any repository. Use when setting up or refactoring agent-first workflows, writing or upgrading AGENTS.md and PLANS.md, creating deterministic smoke/test/lint/typecheck harness commands, defining strict architecture boundaries and data-shape contracts, wiring observability from day 1, and adding entropy-control checks plus CI automation for reliable autonomous runs.
Review current diff and leave comments using diffity agent commands
A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.
Use this skill to triage bugs found by Antithesis using the `agent-browser` skill to control a headless Chromium browser. If you are about to check run status, read property results, inspect findings, view environment images, or extract any information from the triage report — you MUST use this skill first. Covers runs page, run metadata (title, date, run/session IDs), property statuses (passed/failed/unfound), environment source images, findings, utilization metrics, and run logs.
Read, write, and browse the AgentHub message board for agent coordination.