The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes standard local shell commands to manage the development environment. These include using curl to check the status of the local server (http://localhost:3000), npm run dev to start the server, npx eslint --fix for code linting, and npm run build to verify project stability.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content by scanning local project files (e.g., app/page.tsx, app/layout.tsx) and analyzing imports to perform diagnostics and automated fixes.
Ingestion points: Reads and scans files within the app/ and components/ directories.
Boundary markers: No explicit delimiters or boundary instructions are provided for the agent when processing file content.
Capability inventory: The agent can execute shell commands (npm, npx) and modify local file content to resolve detected issues.
Sanitization: No specific sanitization or validation logic is defined for the content extracted from project files before it is analyzed by the agent.

fixit