The Agent Skills Directory

[SAFE]: The skill implements proactive safety measures. It explicitly mandates a full content read before modification to prevent accidental data loss and strictly forbids the deletion of notes.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes user-generated note content.
Ingestion points: Note content is ingested via read_blocks and read_note tools as described in the SKILL.md workflow.
Boundary markers: No explicit delimiters are used when the agent processes the note content.
Capability inventory: The agent has the capability to modify note contents using the edit_block tool.
Sanitization: The skill provides structural instructions to only modify tag elements and preserve the remaining text verbatim, which serves as a functional constraint.

tag-organize