lcmp-recommendation
Suggest LCMP compaction when explicitly requested - provides guidance on promoting durable information to decisions.md, insights.md, and gotchas.md without auto-compaction
Suggest LCMP compaction when explicitly requested - provides guidance on promoting durable information to decisions.md, insights.md, and gotchas.md without auto-compaction
Modern coding patterns for clean, maintainable code - use before implementing complex logic; includes orchestration, pure functions, function decomposition, vertical slice, composition, DI, SOLID, anti-patterns; prevents code complexity bloat and testability issues
RAN mobility optimization with handover management, cognitive consciousness, and predictive mobility control for seamless user experience. Use when optimizing handover performance, managing mobility robustness, implementing predictive handover, or enabling intelligent mobility management in 5G networks.
Category-theoretic graph rewriting with DPO, SPO, and SqPO pushouts for C-Sets. Declarative transformation of acset data structures.
Master Entity Framework Core migrations with code-first approach, migration strategies, data seeding, rollback procedures, and production deployment patterns. Use when managing database schema changes in .NET applications.
Designs comprehensive software solution architectures including system components, technology stacks, integration patterns, scalability strategies, and deployment models. Produces architecture diagrams, technical specifications, and implementation roadmaps. Use when planning new software systems, modernizing legacy applications, designing microservices, evaluating technology choices, creating architecture documentation, or when users mention system design, architecture patterns, scalability planning, or technical architecture decisions.
Split features into atomic 2–4h tasks with independent tests and minimal dependencies
Convex backend patterns with security, validation, and performance best practices
Use when creating or developing anything, before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning, alternative exploration, and incremental validation | コードや実装計画を書く前に、何かを作成・開発する際に使用 - 体系的なソクラテス式の問いかけ、代替案の探索、段階的な検証を通じて、粗いアイデアを完成度の高い設計に洗練
Amplifier design philosophy using Linux kernel metaphor. Covers mechanism vs policy, module architecture, event-driven design, and kernel principles. Use when designing new modules or making architectural decisions.
GF(3)-balanced structured decompositions for parallel computation. Decomposes problems into MINUS/ERGODIC/PLUS components with sheaf-theoretic gluing. Use for FPT algorithms, skill allocation, or any 3-way parallel workload.
Guide for writing Rust code covering ownership, borrowing, lifetimes, error handling, async programming, and Rust best practices
Game server communication protocols including gRPC, REST, and custom binary protocols
Adhesive categories for incremental query updating and pattern rewriting
Skill creation and validation framework ensuring compliance with PAI architectural standards. USE WHEN user says "create skill", "create a skill", "new skill", "build skill", "make skill", "skill for X", "Create-A-Skill", or any request to create new PAI skills.
Behavioral principle for context preservation through strategic delegation. Use when starting multi-step operations, uncertain about scope, or when direct execution might exhaust context. Complements never-guess and resolve-ambiguity skills.
Example skill demonstrating the Skills-as-Containers pattern with workflows, assets, and natural language routing. This is a teaching tool showing the complete PAI v1.2.0 architecture. USE WHEN user says 'show me an example', 'demonstrate the pattern', 'how do skills work', 'example skill'
Helps design port traits and adapter implementations for external dependencies. Activates when users need to abstract away databases, APIs, or other external systems.
專責處理 CBF (Commanded Behavior Frame) 類型的需求。讀取規格目錄結構,生成/審查 Command Side 設計與實作。支援 Java、TypeScript、Go 多語言。
Spawn and coordinate team-agents and orchestration patterns for parallel execution. Use for complex multi-component work.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when encountering any bug, test failure, or unexpected behavior - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
Production-grade skill for C++ concurrency and parallel programming. Covers threads, synchronization primitives, atomics, async programming, parallel algorithms, and lock-free data structures.
Apply Martin Fowler's refactoring patterns - extract variables to eliminate repetition, split temporary variables, replace temp with query for cleaner, more maintainable code