The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx @claude-flow/cli@latest, which downloads and executes the latest version of a package from the npm registry at runtime without version pinning.
[COMMAND_EXECUTION]: Provides instructions for the agent to execute shell commands using npx and mcp tool call to route tasks and record outcomes.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted task descriptions through routing and prediction tools.
Ingestion points: Task descriptions are ingested as the primary argument in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the task description are present.
Capability inventory: The skill has access to the Bash tool and multiple mcp__claude-flow__ hooks for model routing and prediction.
Sanitization: No sanitization or validation of the input task description is defined before it is passed to the routing tools.

intelligence-route