agentic-memory-architecture skills

tygryso/hypotree

Skill Claude CodeCodex

Render evaluation run reports and interpret gate metrics. Use for: reading eval JSONL logs as a markdown report (uv run python -m eval.seedreader --run-id ID), listing available run-ids, scoring the GO/STOP/ITERATE gate decision, understanding what each metric means, diagnosing why an arm won or lost, reviewing probe…