The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the global installation of the claude-flow tool using npm install -g claude-flow@alpha. This is a core dependency for the skill's functionality.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its design for processing externally sourced data.
Ingestion points: Data is ingested from external research sources and testing results via tools like mcp__claude-flow__memory_usage (SKILL.md) and mcp__claude-flow__parallel_execute (SKILL.md).
Boundary markers: The provided examples do not use delimiters or instructions to prevent the agent from interpreting embedded commands in processed data.
Capability inventory: The skill has powerful capabilities, including shell command execution through mcp__claude-flow__parallel_execute and workflow management via mcp__claude-flow__task_orchestrate.
Sanitization: No sanitization, validation, or escaping of ingested data is demonstrated in the orchestration patterns.

swarm-advanced