The Agent Skills Directory

[COMMAND_EXECUTION]: The skill leverages the system terminal to execute vendor-specific tools, specifically calling npx @ericrisco/rsc add to install additional skills and npx @ericrisco/rsc audit to inventory the local environment.
[EXTERNAL_DOWNLOADS]: The skill facilitates the download of extensions from the @ericrisco NPM scope. It also suggests integrating an external MCP server located at https://mcp.context7.com/mcp to provide version-accurate library documentation.
[INDIRECT_PROMPT_INJECTION]: The skill identifies the project's technology stack by reading local manifest files such as package.json, pyproject.toml, go.mod, and others. These files act as ingestion points for external data.
Ingestion points: A read-only walk of the workspace root to detect manifest files and project structure (specified in references/discovery.md).
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from processing malicious instructions that might be embedded within these manifest files.
Capability inventory: The skill possesses the capability to execute shell commands via npx, modify project configuration files (like CLAUDE.md), and write new files to the 02-DOCS/ directory.
Sanitization: No specific sanitization or validation logic is detailed for the content extracted from project manifest files.

init