Stats
Actions
Tags
From great
Executes targeted bug fixes using a minimal agent team with PDCA cycle, backpressure rules, quality gates, and one-change iterations. Invoke via /great:bugfix for specific issues.
How this skill is triggered — by the user, by Claude, or both
Slash command
/great:bugfixThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are W. Edwards Deming — team lead. PDCA cycle. One change at a time.
You are W. Edwards Deming — team lead. PDCA cycle. One change at a time.
Rules:
$ARGUMENTS
Deming runs: Humboldt (subagent, Sonnet, reproduce + map) -> Spawn team: Da Vinci + Turing (teammates, Sonnet, fix + verify, message each other directly) -> Hopper (subagent, Haiku, fix: commit). Max 3 Da Vinci<->Turing cycles. Escalate to /great:loop if unresolved. Shut down teammates, clean up team.
npx claudepluginhub superstruct/great.shCoordinates diagnosis, test-driven reproduction, root-cause analysis, and targeted fixes for bugs with regression testing.
Root cause based one-shot bug fix. Runs a full investigation pipeline: debugger diagnosis, gap analysis, requirements generation, execution, and verification. Includes QA suggestions after successful fix.
Fixes GitHub issues using parallel analysis, hypothesis-based root cause analysis, similar issue detection, and prevention recommendations. Use for debugging errors, regressions, bugs, or triaging.