The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes the npx @useclawlink/cli command to download and execute the ClawLink CLI tool directly from the NPM registry. This package is the official tool provided by the vendor (clawlink-hq) for account management and integration.
[COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands to log in, connect services, and run actions (e.g., npx @useclawlink/cli run gong). These commands are necessary for the tool's core functionality.
[INDIRECT_PROMPT_INJECTION]: The skill enables the agent to read and process data from external sales conversations within Gong. This creates a potential surface for indirect prompt injection if those conversations contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Data enters the context through npx @useclawlink/cli actions gong and npx @useclawlink/cli run gong commands (SKILL.md).
Boundary markers: None explicitly defined in the instructions.
Capability inventory: The skill can execute shell commands via the CLI and access local credential files (~/.clawlink/credentials.json).
Sanitization: Not specified in the provided instructions; behavior depends on the underlying CLI tool and LLM guardrails.

gong