The Agent Skills Directory

[SAFE]: The skill defines a structured workflow for creative writing, focusing on converting story beats into a scene outline and initializing story state.
[COMMAND_EXECUTION]: The workflow instructs the agent to execute a command named story-state to initialize the story order. This tool usage is contextually appropriate for the skill's creative writing purpose and is not associated with dangerous operations or privilege escalation.
[INDIRECT_PROMPT_INJECTION]: The skill involves processing external story data which represents a theoretical surface for indirect prompt injection.
Ingestion points: Workflow step 1 reads external content including core contracts, story craft documents, beat sheets, character profiles, world-building data, and creative briefs.
Boundary markers: No explicit boundary markers or delimiters are specified for the ingested content.
Capability inventory: The skill saves output to 01_story/scene_outline.md and executes the story-state command.
Sanitization: No explicit sanitization or validation of the input content is described.
Context: These actions are standard for the intended primary purpose of the skill and no dangerous capabilities are exposed through this vector.

scene-outline