rasa-agent-skills

Use when a user wants to evaluate or test a Rasa assistant using the eval scenario framework — at any stage of the process: setting up the evaluation infrastructure for the first time, deciding which scenario types to cover for a flow, writing or generating scenario YAML files, learning about supported assertion types or how to write good success criteria, running goal-driven simulations where an LLM plays the user role against a live Rasa bot, or analyzing whether existing scenarios are comprehensive. Covers both the authoring side ("write scenarios", "generate evals", "help me write criteria") and the execution side ("simulate a conversation", "run my eval scenarios"). Not for scripted end-to-end tests, unit tests, NLU training, or general Rasa bot development.

Builds skills (capabilities) for a Rasa CALM assistant. Use when the user asks to create, add, or build a skill, capability, or feature for their Rasa assistant.

Configures config.yml and endpoints.yml for Rasa CALM assistants. Covers pipeline (command generators, flow retrieval), policies (FlowPolicy), action endpoint, and language settings. Use when setting up a new project or modifying pipeline components.

Configures model_groups in endpoints.yml for LLM and embedding providers. Covers single and multi-deployment setups, routing strategies, failover, self-hosted models, and caching. Use when adding or changing LLM providers or setting up multi-LLM routing.

Enables and configures LLM-powered Contextual Response Rephraser in Rasa CALM. Covers endpoints.yml setup, per-response metadata, and prompt customization. Use when setting up or tuning the Contextual Response Rephraser.

Adds knowledge base search to a Rasa CALM assistant using EnterpriseSearchPolicy, connects vector stores (Faiss, Milvus, Qdrant), and configures generative or extractive search modes. Use when setting up RAG, connecting a vector store, overriding pattern_search, or implementing a custom information retriever.

Configures ReAct sub agents in a Rasa CALM assistant. Use when creating a sub-agent that dynamically selects MCP tools, choosing between general-purpose and task-specific agent types, customizing prompts, filtering tools, adding custom Python tools, or overriding input/output processing.

Writes end-to-end tests for Rasa CALM assistants in YAML. Use when creating or editing test cases, adding assertions, setting up fixtures, stubbing custom actions, or verifying flows, slots, and generative responses.

Builds conversation flows for Rasa CALM assistants using YAML. Use when creating or editing flows, designing flow architecture, adding branching logic, writing flow and collect step descriptions, or connecting flows with call and link steps.

Calls MCP tools directly from Rasa flow steps. Use when invoking an MCP tool via a call step, mapping slot values to tool parameters, or extracting tool results into slots. This replaces custom action code for simple API integrations.

Configures MCP (Model Context Protocol) servers in a Rasa CALM assistant. Use when defining MCP servers in endpoints.yml, setting up authentication (API key, OAuth 2.0, pre-issued token), or connecting to multiple external services.

Defines and manages slots in Rasa CALM assistant domain files. Use when creating or editing slot definitions, choosing slot types and mappings, configuring validation, or controlling how slots get filled and persist across flows.

Connects external sub agents to a Rasa CALM assistant via the A2A (Agent-to-Agent) protocol. Use when adding an external agent, configuring an agent card, setting up A2A authentication, customizing input/output processing, or invoking an external sub agent from a flow.

Writes custom actions in Python for Rasa CALM assistants using the Rasa SDK. Use when creating or editing custom action files, calling external APIs from flows, implementing slot validation actions, or building dynamic ask actions.

Writes response templates for Rasa CALM assistants in domain YAML files. Use when creating or editing responses, adding variations, buttons, images, conditional or channel-specific content, or overriding default pattern responses.