Skip to main content
Run any Skill in Manus
with one click
$pwd:

llm-agent-audit-trace-analyzer

// Turn raw WAGF audit traces (household_governance_audit.csv + raw/*.jsonl) into paper-ready governance metrics — IBR, EHE, rejection taxonomy, retry outcomes, model-condition comparisons. Use when the user says "analyze these traces", "compute governance metrics", "summarize rejection and retry outcomes", or hands over a results directory and asks "what does this say".

$ git log --oneline --stat
stars:0
forks:0
updated:May 26, 2026 at 14:38
File Explorer
5 files
SKILL.md
readonly