Static ReadonlyAuthorizesTrue when the action authorizes its caller itself, so a public entry point such as the
RunAction mutation may run it for an authenticated user without an MJ: Action Authorizations link. Set it only on an action that either checks an authorization the caller
must hold, or reads and writes only with the caller's own permissions. Leave it false for an
action that acts with more authority than its caller, or that reaches data or sends messages
the caller chooses but could not otherwise reach.
The engine reads the marker only from the class that runs, never from its parent classes. A subclass that overrides a marked action must declare the marker again.
ProtectedactionHuman-readable label included in error messages (find candidate skills vs find best skill).
ProtecteddefaultDefault MaxResults when the caller omits the parameter.
Whether this action can bound what it returns to an audience (RunActionParams.Audience): everyone
besides the caller who will see its output, such as the other participants of a shared conversation.
false by default, and the engine enforces it: when a run's audience adds a reader beyond the caller,
ActionEngineServer.RunAction refuses the action with result code AUDIENCE_UNSUPPORTED, without running
it. Override to return true only when the action honours the audience in full — every record, snippet
and count it returns is something every reader may see (pass the audience to the search engine, check each
reader's entitlement to anything it scopes by, and leave out aggregates computed before that filtering).
ProtectedhydrateHydrates a skill entity into a MatchedSkillResult including its bundled action names and sub-agent names.
ProtectedInternalInternal method that must be implemented by derived action classes. This is where the actual action logic should be implemented.
The action execution parameters including typed context
Promise resolving to the action result
Executes the action with the provided parameters.
The action execution parameters including context
Promise resolving to the action result
Protectedset
Finds candidate AI Skills for a given task using hybrid semantic + full-text search (backed by the
"AI Skills Search"EntityDocument) with automatic lexical fallback.Returns top N matching skills hydrated with their bundled
ActionNamesandSubAgentNamesso an agent can discover and activate the right skill from catalogs containing hundreds or thousands of skills without loading every skill into the prompt.Inputs:
TaskDescription(required): Natural-language description of the task or capability needed.MaxResults(default 10, max 50): Maximum number of candidate skills to return.MinimumSimilarityScore(default 0.35): Minimum similarity threshold in[0, 1].Category(optional): Filter by skill category name.AgentID(optional): Filter to skills eligible for a specific agent.IncludeRequestedOnly(optional, default false): IncludeRequestedOnlyskills whenAgentIDis supplied.