The Agent Skills Directory

[NO_CODE]: The skill is composed entirely of Markdown documentation and YAML configuration files. It does not include any scripts (Python, JavaScript, shell), binaries, or automated installation commands.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and process user-supplied drama concepts, premises, and scripts. This constitutes an indirect prompt injection surface where a user could potentially embed instructions intended to influence the agent's behavior. However, the skill lacks any tools or capabilities (such as network access, file system modification, or command execution) that could be exploited via such an injection.
Ingestion points: User-provided drama premises and episode scripts processed via the hook engine and workflow defined in SKILL.md and references/method.md.
Boundary markers: The instructions do not define specific delimiters or guardrails for user-supplied input.
Capability inventory: None. The skill does not request or use any tools.
Sanitization: No input sanitization or validation logic is present.
[EXTERNAL_DOWNLOADS]: The references/source-notes.md file contains several URLs to reputable Chinese news and entertainment media outlets (Mtime, China News, Sina, The Paper). These are provided as reference materials for the user and are not accessed or downloaded programmatically by the skill.

wong-jing-commercial-hooks