The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions direct the agent to use the run_command tool to start a local HTTP server (e.g., python3 -m http.server or npx http-server). This is a necessary step to serve the demo.html file so it can be accessed by the DevTools MCP for automated testing.
[EXTERNAL_DOWNLOADS]: The protocol mentions using npx http-server, which involves the automated download and execution of the http-server utility from the npm registry. This is a well-known and standard development tool.
[PROMPT_INJECTION]: The skill processes external, untrusted content from project files such as guide.md and demo.html to perform its validation tasks.
- Ingestion points: Content is read from guide.md, demo.html, and expectations.md located in the local workspace.
- Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore instructions that might be embedded within the files being validated.
- Capability inventory: The agent has the ability to execute shell commands (via run_command) and interact with a browser instance (via chrome-devtools-mcp).
- Sanitization: The skill does not describe any specific sanitization or filtering of the content read from the target files before it is processed.

project-guide-validation