The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow to fetch and process external content from official Render documentation URLs. This pattern introduces a surface where the agent follows instructions found in remote documents.
Ingestion points: Reference files point to Markdown and HTML documentation hosted at https://render.com/docs/ (specifically mcp-server.md, cli.md, and cli-reference.md).
Boundary markers: No specific delimiters or XML tags are specified to wrap the fetched external content; the skill relies on the agent's internal capability to distinguish the retrieved document from the core instructions.
Capability inventory: The skill allows for shell command execution through the render CLI and the claude MCP management tool.
Sanitization: Content fetched via curl is intended to be read directly without specific filtering or schema validation beyond manual inspection by the agent.
[EXTERNAL_DOWNLOADS]: Fetches documentation and configuration guidelines directly from the vendor's official web domains using curl to ensure setup instructions remain current.
[COMMAND_EXECUTION]: Instructs the agent on using the render CLI for authentication and workspace management, and the claude command-line tool for adding the MCP server configuration. All suggested commands are standard for platform integration and use non-interactive output flags.

render-mcp