The Agent Skills Directory

[SAFE]: The skill does not contain any malicious patterns such as command execution, remote code downloads, or credential exfiltration. All external references are to legitimate professional organizations.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided concerns through therapeutic commands.
Ingestion points: User input is ingested via the /pct and /pct:reflect commands in SKILL.md.
Boundary markers: The skill does not explicitly define boundary markers for user input, though it uses structured templates for responses.
Capability inventory: The skill utilizes platform tools Read, Write, and Skill, which are within the expected scope for note-taking or referencing materials.
Sanitization: No specific input sanitization is implemented, which is standard for behavioral skills of this nature.

pct