The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads software and dependencies from well-known external sources to perform its primary function.\n
Fetches the create-fumadocs-app utility from the NPM registry using npx.\n
Uses git clone to retrieve source code from GitHub repositories when a URL is provided as the source.\n
Instructs the user to install vercel and Pillow for deployment and image optimization.\n- [COMMAND_EXECUTION]: Shell commands are executed to scaffold and build the documentation project.\n
The script scripts/scaffold_docs.py invokes npx create-fumadocs-app and pnpm build via subprocess.run().\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a potential attack surface for indirect prompt injection.\n
Ingestion points: The scripts/inventory.py script reads the beginning of files to identify titles, and the agent reads entire file contents during the iterative authoring loop.\n
Boundary markers: The instructions do not define delimiters or explicit "ignore" directives to prevent the agent from following instructions embedded within the source files.\n
Capability inventory: The skill possesses the ability to write to the file system (creating MDX pages) and execute build commands.\n
Sanitization: No sanitization or filtering is performed on the content read from the source repositories before it is passed to the agent's context.\n- [DYNAMIC_EXECUTION]: The skill utilizes dynamic execution patterns to load external tools.\n
Invokes npx to fetch and execute the create-fumadocs-app package at runtime.

lov-repo2docs