The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands through npm scripts and a local open-press binary for lifecycle tasks such as building, serving, and exporting artifacts (PDF, image, Word). It also employs ripgrep (rg) to search for specific markers within the project source.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from workspace source files and project-specific metadata, which may contain malicious instructions.
Ingestion points: MDX/TSX source files located in press/, as well as memory/AGENTS.md and openpress/settings.json.
Boundary markers: The skill does not define explicit delimiters or instructions for the agent to ignore embedded content within these files.
Capability inventory: The agent can execute shell commands via npm and the open-press CLI, and possesses write access to workspace files.
Sanitization: No sanitization or validation of the ingested external source content is specified.

openpress