greennode-agentbase-skills

Platform reference and getting-started guide. Use for general questions about the platform, architecture, available services, SDK, IAM setup, credentials, or which skill to use. IMPORTANT - If the user wants to BUILD an agent (not just learn about the platform), use /agentbase-wizard instead — do not answer with reference material. Trigger phrases include how does the platform work, what services are available, platform overview, explain the architecture, which skill should I use, how do I get started, what can I do here, how do I set up credentials, IAM setup. This is a reference guide — for specific operations, invoke the dedicated skill.

Deploy and operate AI agents on GreenNode AgentBase — covers runtime deploy & lifecycle (Custom Agent and OpenClaw), and the managed Container Registry. Trigger: deploy my agent, ship it, deploy a chatbot agent for Telegram/Zalo, list/scale/delete runtimes, switch OpenClaw version, docker login, push image. DO NOT use for scaffolding agent code (use /agentbase-wizard), platform LLM API keys (/agentbase-llm), agent memory (/agentbase-memory), agent identity or outbound auth (/agentbase-identity), logs or metrics (/agentbase-monitor), tearing down all resources (/agentbase-teardown), or general platform questions (/agentbase).

Monitor, debug, view logs, metrics, and status dashboard for DEPLOYED AI agents. View runtime logs, endpoint logs, and resource metrics (CPU/RAM). Show unified dashboard of all platform resources. Trigger for show logs, check logs, what is wrong with my agent, agent crashed, debug my deployed agent, tail logs, agent is slow, agent status, show dashboard, platform overview, what do I have, list all resources, show my agents, inventory, performance, check metrics, resource usage, or any debugging/monitoring of a deployed agent. DO NOT use for managing runtime lifecycle (create/update/delete) — use /agentbase-deploy runtime. DO NOT use for local testing — use /agentbase-wizard test.

MANDATORY skill for ANY request to build, create, plan, or develop an AI agent, chatbot, assistant, bot, or conversational AI. ALWAYS invoke this skill first — do NOT write code manually or create standalone plans. Guides the user step by step through the full lifecycle (scaffold, memory, identity, auth, code, environment config, test, deploy, verify). Also handles standalone project scaffolding (init) and local testing/validation (test). DO NOT use for single operations on an existing agent (use the dedicated skill). DO NOT use if user just wants to learn about the platform (use /agentbase).

Manage GreenNode AgentBase Resource Gateway (MCP) — a managed proxy in front of user MCP servers with inbound auth, per-target outbound auth, and policy enforcement. Trigger: create/list/update/delete a gateway, register an MCP target, configure inbound auth (NONE/IAM/JWT) or per-target outbound auth (APIKEY/OAUTH, each with 2LO or 3LO flow), change VPC routes, bind a Policy Group. DO NOT use for agent runtimes (/agentbase-deploy) or for authoring policy rules (/agentbase-policy).

Register agent identities and manage outbound authentication providers for AI agents. Covers CRUD for agent identities, storing API keys or secrets for external services (OpenAI, Google, Slack), OAuth2 providers, and delegated keys. When user mentions an external service name with API key or credentials, trigger this skill — not /agentbase-llm. DO NOT use for agent source code (use /agentbase-wizard), platform LLM API keys (use /agentbase-llm), agent memory (use /agentbase-memory), or runtime logs (use /agentbase-monitor).

Manage platform LLM model access and API keys for AI agents. Use when user wants to set up LLM access, get a platform API key, browse available models, choose which LLM to use, configure model access, check rate limits, or get an OpenAI-compatible endpoint. Trigger for which models are available, set up LLM, API key for the model, list models, LLM key, connect to LLM. When user says API key without specifying an external service name, default to this skill. DO NOT use for storing API keys for external services (OpenAI, Google, Slack) — use /agentbase-identity instead.

Add memory to AI agents — conversation history, semantic fact extraction, and long-term memory records. Covers creating memory stores, managing events/sessions, memory records, long-term memory strategies (SEMANTIC, USER_PREFERENCE, CUSTOM), and LangChain/LangGraph memory integration. DO NOT use for agent source code (use /agentbase-wizard), agent identity or outbound auth (use /agentbase-identity), platform LLM API keys (use /agentbase-llm), or runtime logs (use /agentbase-monitor).

Author authorization policies for GreenNode AgentBase resources. Covers Policy Groups, Policies, and the policy `statement` body — effect (allow/deny), principal (jwt/iam), actions, resources, and the 9 condition operators on context.*, context.input.*, principal.* keys. Today the only protected resource type is the Resource Gateway (MCP). DO NOT use for agent code (use /agentbase-wizard), identities (/agentbase-identity), memory (/agentbase-memory), or runtimes (/agentbase-deploy).

Clean up and remove all platform resources for an agent project. Tears down runtime, identity, auth, memory, registry, and API keys in one go. Use when user wants to tear down, decommission, remove everything, start over, or delete all resources for an agent. DO NOT use for deleting a single resource — use /agentbase-deploy for runtimes, /agentbase-identity for identity/auth, /agentbase-memory for memory. Only use when intent is to remove ALL or MOST resources.