NEVER escalate without investigation first. This is the Iron Law. Use when evaluating whether to escalate models, facing genuine complexity requiring deeper reasoning, novel patterns with no existing solutions, high-stakes decisions requiring capability investment. Do not use when thrashing without investigation - investigate root cause first. DO NOT use when: time pressure alone - urgency doesn't change task complexity. DO NOT use when: "just to be safe" - assess actual complexity instead.

Consult this skill for Python performance profiling and optimization. Use when debugging slow code, identifying bottlenecks, optimizing memory, benchmarking performance, production profiling. Do not use when async concurrency - use python-async instead. DO NOT use when: CPU/GPU system monitoring - use conservation:cpu-gpu-performance.

Consult this skill when searching or navigating stored knowledge. Use when searching for stored knowledge, cross-referencing concepts, discovering connections, retrieving from palaces, finding past PR decisions. Do not use when creating new palace structures - use memory-palace-architect. DO NOT use when: processing new external resources - use knowledge-intake.

Authentication patterns for external services: API keys, OAuth, token management, verification. authentication, API keys, OAuth, token management, credentials.

Outputs markdown digests and CSV exports for GitHub issues and PRs. Use when creating status reports, weekly updates, stakeholder briefings, generating GitHub comment digests, tracking initiative health. Do not use when release gates/readiness - use release-health-gates. DO NOT use when: project planning - use spec-kit:speckit-orchestrator.

Interactive selector and router for architecture paradigms. Use when selecting architecture patterns for new systems, comparing paradigm trade-offs, creating architecture decision records, evaluating architecture fit for team size and domain complexity, planning implementation roadmaps. Do not use when implementing a specific known paradigm - use the specific architecture-paradigm-* skill (hexagonal, layered, microservices, etc.) instead. reviewing existing architecture - use architecture-review instead. Use this skill BEFORE making architecture decisions. Check even if unsure about needs.

Use this skill BEFORE resource-intensive operations. Establish baselines proactively. location: plugin token_budget: 400. Use when session starts (auto-load with token-conservation), planning builds or training that could pin CPUs/GPUs for >1 minute, retrying failed resource-heavy commands. Do not use when simple operations with no resource impact. DO NOT use when: quick single-file operations.

Cross-plugin testing quality metrics and standards. Referenced by pensive:test-review and parseltongue:python-testing. testing standards, quality metrics, coverage thresholds, anti-patterns Use when: test quality evaluation, coverage thresholds, quality standards DO NOT use when: simple scripts without quality requirements.

Consult this skill for session-scoped temporary knowledge structures. Use when working on complex multi-step projects, preserving context across interruptions, tracking session-specific state. Do not use when permanent knowledge structures needed - use memory-palace-architect. DO NOT use when: searching existing knowledge - use knowledge-locator.

Retrospective workflow evaluation and improvement of skills, agents, commands, and hooks. workflow improvement, retrospective, workflow efficiency Use when: workflow felt slow, confusing, or needs optimization DO NOT use when: simple one-off fixes - use fix-pr or do-issue instead.

Use this skill BEFORE building complex tool chains. Optimize proactively. location: plugin token_budget: 200. Use when >3 tools chained sequentially, large datasets (>10k rows), large files (>50KB), context usage >25%. Do not use when simple tool calls that do not chain. DO NOT use when: context pressure is low and tools are fast.

Consult this skill when designing permanent memory palace structures. Use when creating new memory palace structures, organizing complex domains, designing spatial layouts for knowledge retention. Do not use when quick knowledge search - use knowledge-locator instead. DO NOT use when: session-specific context - use session-palace-builder.

Consult this skill when implementing service registry patterns. Use when managing multiple external services, implementing health checks, centralizing service configuration, unified service execution. Do not use when single service integration without registry needs.

Consult this skill when implementing layered patterns or enforcing layer boundaries. Use when building traditional applications with clear boundaries, working with moderate-sized teams, needing familiar and well-understood patterns, compliance requirements demand clear separation. Do not use when selecting from multiple paradigms - use architecture-paradigms first. DO NOT use when: high scalability needs independent component scaling. DO NOT use when: teams need independent deployment cycles - use microservices.

CQRS and Event Sourcing for auditability, read/write separation, and temporal queries. Triggers: CQRS, event-sourcing, audit-trail, temporal queries, distributed-systems Use when: read/write scaling differs or audit trail required DO NOT use when: selecting paradigms (use architecture-paradigms first), simple CRUD without audit needs.

Consult this skill when designing data pipelines or transformation workflows. Use when data flows through fixed sequence of transformations, stages can be independently developed and tested, parallel processing of stages is beneficial. Do not use when selecting from multiple paradigms - use architecture-paradigms first. DO NOT use when: data flow is not sequential or predictable. DO NOT use when: complex branching/merging logic dominates.

Decouple domain logic from infrastructure using Hexagonal (Ports & Adapters) pattern. Triggers: hexagonal, ports-adapters, infrastructure-independence, domain-isolation, testability Use when: business logic separation, infrastructure changes needed, testability critical DO NOT use when: selecting paradigms (use architecture-paradigms first), simple CRUD.

TDD-style testing methodology for skills using fresh subagent instances to prevent priming bias and validate skill effectiveness. Use when validating skill improvements, testing skill effectiveness, preventing priming bias, measuring skill impact on behavior. Do not use when implementing skills (use skill-authoring instead), creating hooks (use hook-authoring instead).

Serverless FaaS for event-driven workloads with minimal infrastructure management. serverless, FaaS, Lambda, event-driven, pay-per-use Use when: workloads are event-driven with bursty traffic DO NOT use when: long-running processes or stateful operations required.

Minimal core system with plugin-based feature extensibility for platform development. Triggers: microkernel, plugin-architecture, extensibility, platform-design Use when: platforms/IDEs/marketplaces, core stability critical, plugin isolation needed DO NOT use when: selecting paradigms (use architecture-paradigms first), no extensibility needed.