The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires installation of the flow-nexus and claude-flow packages from the NPM registry. These are vendor-provided tools required for the orchestration platform to function.
[DYNAMIC_EXECUTION]: The platform supports specialized agents like 'Coder', which are explicitly described as being capable of code generation and implementation at runtime to fulfill tasks defined in workflows.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from task descriptions and workflow inputs which are then acted upon by AI agents with significant system capabilities.
Ingestion points: Data enters the system via the task parameter in mcp__flow-nexus__task_orchestrate and the input_data object in mcp__flow-nexus__workflow_execute within SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from following commands embedded within the input data.
Capability inventory: The skill can spawn new agents with varied capabilities (mcp__flow-nexus__agent_spawn), orchestrate complex task sequences, and manage cloud-based execution streams.
Sanitization: There is no documentation or evidence of input sanitization to filter out potentially malicious instructions from the data before processing.

flow-nexus-swarm