Stats
Actions
Tags
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentguard:diagnose-traceThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
`$ARGUMENTS` is a path to a trace JSON file. Run this and paste the output verbatim:
$ARGUMENTS is a path to a trace JSON file. Run this and paste the output verbatim:
${CLAUDE_PLUGIN_ROOT}/bin/agentguard diagnose "$ARGUMENTS"
The [artifacts] block lists the trace path and a companion HTML report generated next to it. Do not add any summary unless the user asks.
npx claudepluginhub betahi/agentguard --plugin agentguardCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.