The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to run the @useclawlink/cli package using npx, which downloads the executable code from the public NPM registry at runtime. This package is the official tool provided by the skill author.
[COMMAND_EXECUTION]: The skill functions by executing shell commands (npx @useclawlink/cli) to find actions, describe inputs, and run operations on Freshdesk data.
[CREDENTIALS_UNSAFE]: The documentation specifies that the login command stores authentication credentials in a local file at ~/.clawlink/credentials.json. This is the intended behavior for the CLI tool's local session management.
[INDIRECT_PROMPT_INJECTION]: The skill provides a surface for processing untrusted user input into shell command arguments.
Ingestion points: User-provided strings used in the npx @useclawlink/cli actions freshdesk "<what you want to do>" command.
Boundary markers: None identified in the provided command examples to separate user input from the command structure.
Capability inventory: The skill can perform write operations (create agents, add notes, update tickets) and execute external CLI tools.
Sanitization: The skill instructions do not specify sanitization or validation steps for the input strings before they are passed to the shell.

freshdesk