The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes a local command-line utility monologue to retrieve note metadata and content. This tool is a primary component of the skill's workflow and is used to fetch the evidence required for drafting updates.
[PROMPT_INJECTION]: The skill processes external note transcripts which are considered untrusted data, creating a surface for indirect prompt injection. While the structured task of evidence extraction serves as a constraint, the skill lacks explicit markers to prevent the agent from following instructions embedded within the notes. * Ingestion points: Note content is retrieved from the local filesystem using monologue notes get (defined in SKILL.md). * Boundary markers: No explicit delimiters or instructions are used to distinguish note content from system instructions. * Capability inventory: The skill possesses command execution capabilities via the monologue CLI. * Sanitization: No sanitization or filtering is performed on the transcript data before it is processed by the agent.

weekly-work-update