The Agent Skills Directory

[SAFE]: The skill performs legitimate productivity tasks, converting conversation into a structured Markdown document. All requested tools (Read, Grep, Glob, Write) are appropriate for the defined scope of managing files and documentation.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user responses to generate a document.
Ingestion points: User input collected during the "Who is it going to?" and "What do you need back?" interview phases.
Boundary markers: Employs a specific Markdown template with headers and blockquotes to structure the output.
Capability inventory: Uses the Write tool to create a local file named to-questionnaire-<slug>.md.
Sanitization: No explicit sanitization of user input is documented, but the output is intended for human review and asynchronous communication rather than automated execution.

to-questionnaire