Use when auditing site navigation, hierarchy, taxonomy, URLs, depth, clusters, and discoverability.
Systematically evaluate architecture decisions, document trade-offs, and select appropriate patterns for context.
Use when when training a dual-encoder architecture (bi-encoder + cross-encoder) on NMR spectral data where independent encoding and joint pair processing produce competing or…
为内容设计、生成、质检、上传并嵌入架构图、流程图、信息图和示意图，涵盖提示词设计到 最终落图的完整流程。当用户要求“画个架构图”“画流程图”“生成配图”“生成图片”“把图画出来” “渲染一下”或“帮我生图”，或使用 "draw an architecture diagram", "generate an image", "create a…
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration.
Turn photos of a whiteboard, sticky-note wall, or napkin sketch into a structured spec the team can execute.
Generate structured documentation from codebases — architecture mapping, page writing, and onboarding guides.
Explain the LLM Wiki pattern — architecture, concepts, and how to use wiki-init/ingest/query/lint skills.
The living embodiment of WinDAGs V3 — the AI orchestration platform where agents accumulate genuine expertise.
State management, checkpoint architecture, and recovery strategy selection for WinDAGs V3 execution infrastructure.
Expert in building modern Windows applications using WinUI 3, WPF, and the Windows App SDK. Specializes in MSIX packaging, XAML styling, and MVVM architecture.
Choose workspace architectures for different project scales in Windsurf. Use when deciding how to structure Windsurf workspaces for monorepos, multi-service setups, or polyglot…
Implement Windsurf reference architecture with optimal project structure and AI configuration. Use when designing workspace configuration for Windsurf, setting up team standards,…
Wispr Flow reference architecture for voice-to-text API integration. Use when integrating Wispr Flow dictation, WebSocket streaming, or building voice-powered applications.
Use when a /design-complete ai-dev-assistant task must become N self-contained, gate-verifiable work-orders — decomposes architecture.md Components into units, attaches…
Major architectural shift protocol. ADR creation, migration strategy, rollback plan. For: layer changes, pattern adoption, system redesign, breaking API changes, infrastructure…
Use when you need to understand how a complex MS/MS spectral search system routes query spectra through multiple parallel processing pipelines with different objectives (e.g.,…
Workhuman reference architecture for employee recognition and rewards API. Use when integrating Workhuman Social Recognition, or building recognition workflows with HRIS systems.
Úsala cuando el usuario pida crear una nueva funcionalidad (feature), configurar rutas con React Router Dom, agregar componentes de UI, usar Shadcn, organizar la estructura de…
Twenty-minute diagnostic mapping a team to a world-model paradigm (vector DB, structured ontology, signal-fidelity).
THC Wake-on-Touch (WoT) — corrected architecture (GPIO IP / vGPIO wake path), WoG (Not POR / ISH-based), Linux/Windows implementation, platform config, validation, debug
Step-by-step instructions for deep analysis of a WordPress plugin — architecture, execution flows, hook chains, data lifecycle, and extensibility — from a local path or GitHub…
Generate WPF MVVM architecture with ViewModelBase, RelayCommand, INotifyPropertyChanged, and dependency injection setup
Write an architecture document from goals and requirements
Write an implementation plan from architecture documents
Write database models following the Epic architecture patterns. Use when creating Active Record models for database tables with CRUD operations.
Draft or revise a design RFC that explains architecture from first principles — why the system exists, how layers interact, what trade-offs were made, and where it's headed.
Write routes following the Epic architecture patterns. Use when creating HTTP endpoints for behaviors, webhooks, or streaming.
Use when handing an initiative or a chunk of work to the engineer — produce a brief with C4-level structure, the exact contract, acceptance, file/seam pointers, illustrative code,…
Use when writing or modifying the kimi-code terminal UI in apps/nori-code/src/tui — components, dialogs/selectors, slash commands, themes, streaming render, or the KimiTUI…
Use when a design discussion has produced a real architecture decision, when future readers would ask "why did we do it this way?", when capturing tradeoffs and rejected…
Decomposes the apply-skill produced by designing-isucon-architecture into atomic tasks, materializes one Claude Code subagent per task, and emits a dispatcher slash command that…
Read this before authoring or substantially changing a plugin, agent, or skill for Archie. It's the conceptual playbook for building plugins that fit Archie's multi-agent,…
Use when writing, reviewing, or improving RFCs, requests for comments, technical design docs, architecture proposals, engineering decision records, API proposals, migration plans,…
Use when creating technical design documents, architecture documentation, or implementation specifications. Use when documenting technical decisions and component responsibilities.
Use when reasoning about how WSDM reviews and decides papers - the hybrid single/double-blind architecture with Associate-Chair metadata visibility, at-least-three PC reviews plus…
Implement x86_64 architecture-specific code: GDT, IDT, paging, syscalls. Follow AMD64 architecture manual conventions and use proper memory barriers.
USE WHEN: writing system prompts, structuring complex instructions, engineering context for Claude agents, optimizing attention efficiency in long prompts.
z88dk newlib vs classic architecture for targets, CRT m4 driver instantiation, serial/character FILE* wiring, disk fcntl (asm_target_open, open_max, FCB vs FatFs), mixed multi-CPU…
Prüft ZGPM-Konsistenz-Regeln (≥1 A je MS, genau 1 F/L, "e" nie ohne "E"). Trigger wenn `plan/pvm.yaml` validiert wird (durch reviewer-agent, architecture-agent, /validate-plan).
Extract and store learnings from the current work/coding session into your work knowledge base. Run at the end of a session or whenever the user invokes /zingage-learn.
Step up one layer of abstraction and surface a map of relevant modules and callers when the local view is too narrow.
Agent architecture patterns for Google ADK — when and how to use LlmAgent, LoopAgent, SequentialAgent, ParallelAgent, and multi-agent hierarchies.
ADK architectural knowledge — graph orchestration, resumption, execution flow, node contracts, observability, and LLM context orchestration.
Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or…
Record and maintain Architecture Decision Records (ADRs) in Nygard format under docs/ADRs. Use this whenever the user wants to document an architecture or design decision, asks to…
Conversational interview skill that bridges the "I want to build X" to "here are tickets" gap. It classifies the idea against an archetype, designs a complete architecture using…
Conversational interview skill that bootstraps a project for agent-first engineering by producing lean, progressive-disclosure documentation.
This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory…
Restructures a chaotic or overgrown MEMORY.md into a clean 2-layer architecture based on how Claude Code's autoDream system organizes memory — a lightweight pointer index (always…
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context w — from…
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or bui — from…
This skill should be used when building AI agents using prompt-native architecture where features are defined in prompts, not code.
This skill should be used when conducting a scored agent-native architecture review. It launches 8 parallel sub-agents to audit action parity, context injection, CRUD…
This skill should be used for the tool-interface layer of an agent system specifically: writing tool descriptions agents can route on, designing tool schemas and response formats,…
Use when working in a repo organized for AI-agent effectiveness — tiered docs (guides/architecture/features/reference), AGENTS.md/CLAUDE.md per crate, change-impact tables,…
Use this skill when designing AI agent architectures, implementing tool use, building multi-agent systems, or creating agent memory.
When the user wants to price an AI product, choose a charge metric, design pricing tiers, or optimize margins.
Use this skill whenever asked to prepare, review, or classify transactions for an Albanian VAT (TVSH) return for any client.
Explain blockchain fundamentals including distributed ledger architecture, consensus mechanisms, and block structure.