The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes diagnostic commands such as claude mcp, npm list, and Rscript to verify the state of the local environment and installed tools.
[EXTERNAL_DOWNLOADS]: Connectivity checks and authentication verification are performed against huggingface.co, which is a well-known service. The skill also suggests the installation of the mcp-remote package through npm.
[PROMPT_INJECTION]: The skill processes untrusted data from local configuration files, presenting a surface for indirect prompt injection if these files are manipulated.
Ingestion points: Reads ~/.claude.json and Windows-specific claude_desktop_config.json files.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when reading these files.
Capability inventory: The skill has access to Bash, Write, Edit, Read, Grep, and Glob tools.
Sanitization: No validation or sanitization of the configuration file content is performed prior to processing.

troubleshoot-mcp-connection