The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions include running npm run validate:posts within the templates/next directory to verify the created Markdown files.
[INDIRECT_PROMPT_INJECTION]: The skill processes external user-supplied data (article bodies or outlines) to generate files and metadata, creating a surface where malicious instructions in the input could potentially influence agent behavior.
Ingestion points: Processes user-supplied article body, outline, or brief in SKILL.md.
Boundary markers: No explicit delimiters or guardrails are defined to isolate user-provided content from the skill's execution logic.
Capability inventory: The skill is capable of writing new Markdown files to the filesystem and executing local npm scripts.
Sanitization: No sanitization of the user-provided Markdown body is specified, although frontmatter is validated against a schema.

create-post