The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads and installs the booksy-pp-cli and booksy-pp-mcp tools from the author's own repositories.
Sources include the NPM package @mvanhorn/printing-press-library (via npx) and the GitHub repository github.com/mvanhorn/printing-press-library (via go install).
These resources are owned by the skill's author ('mvanhorn') and represent the intended functionality of the toolset.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from the Booksy marketplace, such as business profiles, services, and reviews, which could potentially contain untrusted content.
Ingestion points: Data enters the agent's context through command outputs from businesses search, get, and reviews.
Boundary markers: None explicitly defined in the instructions, although the --agent flag ensures structured JSON output which helps the agent distinguish data from instructions.
Capability inventory: The skill uses the Read Bash tool to execute the booksy-pp-cli binary.
Sanitization: The skill provides a --select flag to allow the agent to filter specific JSON fields, reducing the amount of processed untrusted data.
[COMMAND_EXECUTION]: The skill relies on executing shell commands via the booksy-pp-cli binary to interact with the Booksy API. The book command includes a dry-run safety mechanism by default, requiring an explicit --confirm flag for mutations.

pp-booksy