The Agent Skills Directory

[COMMAND_EXECUTION]: The skill interacts with the local environment by executing cytoscnpy subcommands for code analysis and project initialization. The cytoscnpy init command modifies local files, specifically creating or appending to .cytoscnpy.toml or pyproject.toml.
[INDIRECT_PROMPT_INJECTION]: The skill processes project source code, creating an indirect prompt injection surface.
Ingestion points: cytoscnpy subcommands (raw, cc, hal, mi, stats, table) read Python files from a user-provided <PATH> (found in SKILL.md and references/cli-reference.md).
Boundary markers: None specified in the instructions to separate metrics output from the agent's instruction stream.
Capability inventory: The skill invokes the cytoscnpy CLI for metric calculation and file modification via the init subcommand (found in SKILL.md and references/cli-reference.md).
Sanitization: No content sanitization of the analyzed source code is described.

cli-cytoscnpy