The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches documentation from module-federation.io and retrieves remote module manifests from unpkg.com. It also facilitates the installation of external tools including the @divebell/cli and various @module-federation ecosystem packages.
[COMMAND_EXECUTION]: The skill executes several local Node.js scripts to analyze project structure, configuration, and shared dependencies. It also utilizes npx to run build-related tools such as tsc for type checking and mf dts for type generation, and interacts with the divebell CLI tool.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data which may contain embedded instructions, creating an attack surface for indirect prompt injection.
Ingestion points: Processes content from https://module-federation.io/llms.txt and remote mf-manifest.json files via scripts/module-info.js.
Boundary markers (absent): The skill lacks explicit boundary markers or instructions to the agent to ignore potential directives within the ingested remote content.
Capability inventory: The skill possesses significant capabilities, including writing to local project configuration files (rsbuild.config.ts, tsconfig.json, .env.local), executing shell commands via bash, and installing global NPM packages.
Sanitization (absent): No explicit sanitization or validation of the remote content is performed before it is processed or presented to the user.

mf