Loading...
Loading...
Found 2 Skills
Guides failure-prevention culture and operational excellence for mission-critical engineering— zero-defect aspiration vs error budgets; HRO principles; defense-in-depth; fail-safe/fail-closed; verification gates and independent checks; redundancy and graceful degradation; pre-mortems and FMEA; stop-the-line; defect escape, near-miss, and repeat-incident metrics; leadership against normalization of deviance—not blame culture. Use for failure-prevention programs, HRO practices, verification gates, fail-safe design, pre-mortem/FMEA, stop-the-line, near-miss reporting, or defect-escape metrics—not SRE error budgets only (site-reliability-engineer), incident command only (incident-management-engineer), backup/restore only (cyber-resilience-engineer), CI lint only (build-validator), agile coaching, HR discipline, or classified ATO without ops-excellence lens (classified-cyber-security-senior-manager).
When a task is blocked by missing or unverified information (an undocumented protocol, an unknown API shape, a value only real hardware/prod can confirm), build everything that does NOT depend on the unknown right now, and quarantine the unknown behind a single adapter boundary — best-guess defaults + a verified flag + a conformance/adapt kit — so adapting later means editing one file, not rewriting the project. Trigger when the user says "làm những gì có thể trước", "build what we can now", "wrap the unknowns", "isolate/quarantine the unknown parts", "don't block on missing info", "adapter so we can swap later", "ready to adapt", or invokes /build-now-adapt-later. Also applies whenever a spec has ⚠️ "to be verified" items but most of the work doesn't actually depend on them.