The Agent Skills Directory

[SAFE]: The skill provides a utility for performance engineering. The included Python script scripts/compare_parallel_scaling.py performs deterministic mathematical calculations on benchmark data and outputs a summary report.
[INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface through external JSON files containing benchmark results.
Ingestion points: scripts/compare_parallel_scaling.py reads files specified via the --baseline and --current CLI arguments.
Boundary markers: None; the script expects valid JSON objects conforming to its internal schema.
Capability inventory: The script is limited to calculating performance deltas and printing results to standard output. It does not perform network operations, file system modifications, or dynamic code execution.
Sanitization: The script uses the standard json library for parsing and performs explicit type and existence checks on the input data (e.g., verifying runs is a list and threads/throughput are numeric).

parallel-computing