The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes several scripts designed to automate the management of search experiments by interacting with the system shell and the service's CLI tool.
scripts/run-and-export-search-experiment.py and scripts/cost-receipt.py use Python's subprocess.run() to execute commands via the deepline CLI. These operations include checking play status, running plays, and exporting results.
scripts/evaluate-source-plan-corpus.ts uses Node.js child_process.spawnSync() to execute a Python-based strategy planner for offline evaluation.
[EXTERNAL_DOWNLOADS]: The skill documentation provides instructions for setting up the execution environment which involves downloading external code.
SKILL.md contains instructions to install the deepline CLI globally using npm install -g deepline from the standard npm registry or a vendor-hosted registry at code.deepline.com.

deepline-plays