The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by reading project configuration and component source code to determine framework compatibility and animation targets.
Ingestion points: The skill reads package.json and previously generated component files (e.g., Next.js or Svelte components) as described in Step 1 and Step 2 of SKILL.md.
Boundary markers: There are no explicit instructions for the agent to use delimiters or 'ignore' directives when processing the content of these external files.
Capability inventory: The skill has the capability to modify existing files via Write and execute shell commands using Bash (specifically to install packages like framer-motion).
Sanitization: The skill does not perform validation or sanitization of the ingested code strings before they are incorporated into the agent's reasoning or modification tasks.

stitch-animate