A Jido.Action for lazily loading available skill instructions.
Pair this action with Jido.AI.Skill.Prompt.render_registry_index/1 to expose
a compact skill index in an agent prompt. The model can call load_skill only
after selecting a relevant skill, keeping full skill bodies out of the prompt
until they are needed.
The action routes through Jido.AI.Skill.Activation, returning the skill root
and resource listing with the instructions. It scopes activation
from session_id, agent_id, or request_id in the runtime context and tags
the resulting tool message as durable for ReAct compaction.
Parameters
name(required) - Available skill name to load.include_metadata(optional) - Include skill metadata in the response (default:true).
Examples
{:ok, result} =
Jido.Exec.run(Jido.AI.Actions.Skill.LoadSkill, %{name: "code-review"})
result.instructions
#=> "# Code Review..."Summary
Functions
Returns the Action metadata. Alias for to_json/0.
Returns the category of the Action.
Returns the description of the Action.
Returns the name of the Action.
Lifecycle hook called after Action execution.
Lifecycle hook called after output validation.
Lifecycle hook called after parameter validation.
Lifecycle hook called before output validation.
Lifecycle hook called before parameter validation.
Lifecycle hook called when an error occurs.
Returns the output schema of the Action.
Loads and activates the requested skill from the agent catalog or registry.
Returns the input schema of the Action.
Returns the tags associated with the Action.
Returns the Action metadata as a JSON-serializable map.
Converts the Action to an LLM-compatible tool format.
Validates the output result for the Action.
Validates the input parameters for the Action.
Returns the version of the Action.
Functions
Returns the Action metadata. Alias for to_json/0.
Returns the category of the Action.
Returns the description of the Action.
Returns the name of the Action.
Lifecycle hook called after Action execution.
Lifecycle hook called after output validation.
Lifecycle hook called after parameter validation.
Lifecycle hook called before output validation.
Lifecycle hook called before parameter validation.
Lifecycle hook called when an error occurs.
Returns the output schema of the Action.
Loads and activates the requested skill from the agent catalog or registry.
Returns the input schema of the Action.
Returns the tags associated with the Action.
Returns the Action metadata as a JSON-serializable map.
Converts the Action to an LLM-compatible tool format.
Validates the output result for the Action.
Examples
iex> defmodule ExampleAction do
...> use Jido.Action,
...> name: "example_action",
...> output_schema: [
...> result: [type: :string, required: true]
...> ]
...> end
...> ExampleAction.validate_output(%{result: "test", extra: "ignored"})
{:ok, %{result: "test", extra: "ignored"}}
iex> ExampleAction.validate_output(%{extra: "ignored"})
{:error, "Invalid output for Action: Required key :result not found"}Validates the input parameters for the Action.
Examples
iex> defmodule ExampleAction do
...> use Jido.Action,
...> name: "example_action",
...> schema: [
...> input: [type: :string, required: true]
...> ]
...> end
...> ExampleAction.validate_params(%{input: "test"})
{:ok, %{input: "test"}}
iex> ExampleAction.validate_params(%{})
{:error, "Invalid parameters for Action: Required key :input not found"}Returns the version of the Action.