The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes local codebase files, styles, and rendered views to recreate them in Framer mocks. This represents an attack surface for instructions embedded in source code.
Ingestion points: Processes the current repository's source code, styles, and local development views (SKILL.md).
Boundary markers: No specific delimiters are defined to separate ingested code content from agent instructions.
Capability inventory: Performs file system reads, interacts with the Framer API via extensions, and executes shell commands for environment setup.
Sanitization: The skill does not explicitly describe sanitization or filtering of instructions that might be contained within the code it analyzes.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx @framer/agent@latest setup to fetch and install the official Framer automation agent if the primary skill is missing. This targets the official package registry for a well-known design service.
[COMMAND_EXECUTION]: Executes shell commands via the npx package runner to configure the Framer environment. The execution is limited to the setup of the official @framer/agent package.

create-mock