Skip to content

farnooshmemari/soc-benchmark-author

v1.0.0

Extend the Adaptive Agent Harness security-alert benchmark safely: author labelled alerts plus deterministic mock responses for both strategies, then validate schema, mock coverage, and the expected panel-vs-hierarchical outcome before running the benchmark.

GitHub
skills

add-benchmark-alert

Add or edit a labelled security alert in the Adaptive Agent Harness benchmark, write matching deterministic mock responses for both strategies, and validate the dataset before re-running the benchmark.

Read SKILL.md at the source

Pinned to revision 6475dd4ba575, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.