一键导入
这个仓库中的 skills
Use 4-phase root cause analysis (Observe, Hypothesize, Verify, Fix); avoid unverified patches.
Use Git worktrees to create parallel working directories safely; avoid branch-switch contamination.
Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.
Enforce "no evidence = no completion"; run Gate Function verification before declaring done.
Pre-ship observability readiness checklist — ensures errors reach production monitoring, not just debug consoles.
Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.
Evaluate when to dispatch parallel agents; use a 4-step pattern to split, coordinate, and integrate results.
Decompose tasks via subagent collaboration; define interface contracts and integration checkpoints.
Drive changes with Red→Green→Refactor; ensure behavior is verifiable and regression-safe.