justcoon

Adding a new TypeScript agent to a Golem component. Use when the user asks to create, add, or define a new agent type, implement an agent class, or add agent methods in a TypeScript Golem project.

Exposing a TypeScript Golem agent over HTTP. Use when the user asks to add HTTP endpoints, mount an agent to a URL path, or expose agent methods as a REST API.

Adding LLM and AI capabilities to a TypeScript Golem agent. Use when the user wants to add LLM chat, embeddings, or any AI provider integration to a TypeScript agent.

Adding secrets to TypeScript Golem agents. Use when the user asks to add secrets, store API keys, manage sensitive config values, or use Secret<T> in TypeScript agents.

Calling Golem agents from external TypeScript/Node.js applications using generated bridge SDKs. Use when the user wants to invoke agents from outside the Golem platform, from a Node.js server, script, or any TypeScript application.

Choosing between durable and ephemeral agents in a TypeScript Golem project. Use when the user asks about agent durability modes, making an agent stateless, or configuring agent persistence.

Enabling snapshot-based recovery and implementing custom snapshot save/load functions for TypeScript agents. Use when adding manual update support, custom state serialization, or — equally importantly — when a long-running agent's oplog is growing large and recovery/replay is becoming slow (heartbeats, polling loops, recurring tasks, frequent state changes). Snapshotting compacts the oplog and lets recovery start from the latest snapshot instead of replaying full history.

Enabling the OpenTelemetry (OTLP) plugin for a TypeScript Golem agent — exporting traces, logs, and metrics to an OTLP collector, adding custom spans with the invocation context API or node:diagnostics_channel.

Invoking a Rust Golem agent method from the CLI. Use when asked to call, invoke, or run a method on a deployed agent using golem agent invoke.

Defining environment variables for Golem agents. Use when configuring env vars in golem.yaml at the component template, component, agent type, or preset level, passing env vars to individual agent instances via CLI, or using template substitution and merge modes.

Exposing a Rust Golem agent over HTTP. Use when the user asks to add HTTP endpoints, mount an agent to a URL path, or expose agent methods as a REST API.

Adding secrets to Rust Golem agents. Use when the user needs to store sensitive configuration such as API keys, passwords, or tokens that should not be checked into source control.

Calling Golem agents from external Rust applications using generated bridge SDKs. Use when the user wants to invoke agents from outside the Golem platform, from a Rust CLI, server, or any native Rust application.

Setting up a Golem Cloud account from scratch. Use when creating a Golem Cloud account, authenticating with Golem Cloud via the CLI, setting up a cloud profile, or deploying to Golem Cloud for the first time.

Enabling snapshot-based recovery and implementing custom snapshot save/load functions for Rust agents. Use when adding manual update support, custom state serialization, or — equally importantly — when a long-running agent's oplog is growing large and recovery/replay is becoming slow (heartbeats, polling loops, recurring tasks, frequent state changes). Snapshotting compacts the oplog and lets recovery start from the latest snapshot instead of replaying full history.

Enabling the OpenTelemetry (OTLP) plugin for a Rust Golem agent — exporting traces, logs, and metrics to an OTLP collector, adding custom spans with the invocation context API.

Comprehensive skill for implementing new features in the Golem RAG System, following a structured 3-phase workflow with planning, confirmation, and quality gates.