The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches the ruvector package from the npm registry. This package is a vendor-owned resource associated with the author's identity (ruvnet).
[COMMAND_EXECUTION]: The instructions utilize Bash commands to verify the local environment, install dependencies, and execute the clustering CLI via npx.
[PROMPT_INJECTION]: The skill is designed to process external files for community detection, which establishes an indirect prompt injection surface.
Ingestion points: Local files are passed as arguments to the graph-cluster and graph-mincut commands in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded instructions within the analyzed files.
Capability inventory: The skill utilizes Bash for command execution and MCP tools for memory storage (mcp__claude-flow__memory_store).
Sanitization: No sanitization or validation of the input file content is performed within the skill instructions, relying on the ruvector tool's internal logic.

vector-cluster