The Agent Skills Directory

[SAFE]: The skill defines structured formats for the agent to present technical information, including Mermaid diagrams for sequence flows, pseudocode for algorithms, and diffs for code changes.
[INDIRECT_PROMPT_INJECTION]: The skill uses a pattern where user-influenced descriptions are interpolated into a shell command path used to display generated HTML files.
Ingestion points: The {description} variable, derived from the conversational topic, is included in the filename for generated HTML artifacts in SKILL.md.
Boundary markers: No explicit boundary markers or instructions to ignore instructions within the user-provided topic are defined.
Capability inventory: The skill instructs the agent to use Bash to execute an open command on generated local files.
Sanitization: There are no instructions to sanitize or validate the {description} string before it is passed to the shell environment.

show-me