Use to stress-test predictions by assuming they failed and working backward to identify why. Invoke when confidence is high (>80% or <20%), need to identify tail risks and unknown unknowns, or want to widen overconfident intervals. Use when user mentions premortem, backcasting, what could go wrong, stress test, or black swans.
Perform threat modeling for a system or feature. Use when a senior developer needs security risk assessment.
Use when designing incident management processes, creating runbooks, or establishing on-call practices. Covers incident lifecycle, communication, and postmortems.
The assistant provides a structured penetration testing checklist covering scope definition, environment preparation, monitoring, and remediation. Activate when users ask about "pentest planning," "security assessment checklist," "penetration test preparation," "pentest scope," or "security testing best practices."
Create phased implementation plans from research findings. Invoke when a task needs an implementation plan.
Generate slack summaries of vLLM CI SIG Slack channel activity for the RHAIIS midstream release team
Use when ranking backlogs, deciding what to do first based on effort vs impact (quick wins vs big bets), prioritizing feature roadmaps, triaging bugs or technical debt, allocating resources across initiatives, identifying low-hanging fruit, evaluating strategic options with 2x2 matrix, or when user mentions prioritization, quick wins, effort-impact matrix, high-impact low-effort, big bets, or asks "what should we do first?".
Adam Dymitruk's Event Modeling methodology with swimlanes
Execute general implementation tasks following a plan. Invoke for non-Lean implementation work.
Establish workflow boundary checklists with clear pass/fail criteria and escalation procedures
Draft an incident postmortem with timeline, RCA, and action items. Use when a senior developer needs a structured post-incident report.
Use when testing plans or decisions for blind spots, need adversarial review before launch, validating strategy against worst-case scenarios, building consensus through structured debate, identifying attack vectors or vulnerabilities, user mentions "play devil's advocate", "what could go wrong", "challenge our assumptions", "stress test this", "red team", or when groupthink or confirmation bias may be hiding risks.
Collaborative domain modeling through pictographic stories. Use when gathering requirements, understanding business workflows, onboarding team members, or preparing for event storming. Follows Stefan Hofer & Henning Schwentner's methodology with actors, work objects, and activities.
Four fundamental team types and interaction modes from Team Topologies
Coordinate implementation phase by delegating tasks and ensuring code quality. Use during implementation phase to manage engineer tasks.
Explain CSS layout issues and propose fixes. Use when a junior developer is struggling with alignment or spacing.
Frameworks for giving and receiving code review feedback effectively. Use for PR comments, review strategies, handling disagreements, and balancing thoroughness with kindness.
Frameworks for effective mentoring and knowledge transfer. Use for 1:1 meetings, pair programming, onboarding, teaching technical concepts, and developing junior engineers.
Use when dealing with complex systems that need simplification, identifying bottlenecks or critical failure points, redesigning architecture or processes for better performance, breaking down problems that feel overwhelming, analyzing dependencies to understand ripple effects, user mentions "this is too complex", "where's the bottleneck", "how do we redesign this", "what are the key components", or when optimization requires understanding how parts interact.
Requirements quality assessment and improvement. Use when evaluating requirements against INVEST criteria, improving clarity, detecting ambiguity, or ensuring completeness. Provides quality checklists, refinement patterns, and MoSCoW prioritization guidance.
Define performance budgets and guardrails. Use when a senior developer needs performance targets and enforcement.
Use when brainstorming feels stuck or generates obvious ideas, need to break creative patterns, working with limited resources (budget/time/tools/materials), want unconventional solutions, designing with specific limitations, user mentions "think outside the box", "we're stuck", "same old ideas", "tight constraints", "limited budget/time", or seeking innovation through limitation rather than abundance.
Use when designing organizational structure (team topologies, Conway's Law alignment), mapping stakeholders by power-interest for change initiatives, defining team interface contracts (APIs, SLAs, decision rights, handoffs), assessing capability maturity (DORA, CMMC, agile maturity models), planning org restructures (functional to product teams, platform teams, shared services), or when user mentions "org design", "team structure", "stakeholder map", "team interfaces", "capability maturity", "Conway's Law", or "RACI".
Operational runbook templates for incident response and procedures
