Analyse code repositories and generate comprehensive architecture documentation. Use when the user asks to: analyse a codebase, understand project structure, document…
Generate a layered HTML architecture diagram from a real GitHub repo URL. Walks the tree, classifies modules into semantic layers (user / application / ai / data / infra /…
Verifies claims from repo-bfs-architecture. Three passes: (A) code-first grep of all claims, (B) DFS traversal of ARCH_GRAPH to verify component relationships, (C) targeted web…
Create, update, or consolidate adopted current-state documentation under docs/context/. Use for durable implemented architecture, ownership, runtime, domain, flow, terminology, or…
Use when the task is to understand an unfamiliar codebase, locate key entry points, or summarize architecture before editing.
Onboard quickly to this repository. Use when asked to understand architecture, locate ownership, choose the right module, or identify the correct commands and verification…
Six-layer governance hierarchy (Vision → Principles → Conventions → Development → Agents → Workflows).
Wayfind repository documentation by tracing real tasks to code-owned authority. Use when the user wants to audit scattered, stale, duplicated, or mixed-role docs; decide whether…
Use after architecture design to define the on-disk repository layout — single-repo vs monorepo, app/package boundaries, directory conventions, and shared-code placement.
Master orchestration for repository governance, North Star impact, sub-Star boundaries, and repair-first or evidence-first drift checks.
处理 BK-CI 代码库接入、代码库授权、Webhook、SCM 集成、PAC 开关与仓库类型差异时使用。当用户提到 Git/SVN/GitHub/TGit、Webhook、仓库认证、PAC 代码库或提交记录时优先使用。
Design and implement the Repository pattern in a TypeScript DDD clean architecture project — define repository interfaces in the domain layer and implementations in the…
Manage architecture requirements throughout the TOGAF ADM cycle. Produces Requirements Impact Assessments, maintains Architecture Requirements Repository entries, and builds a…
Use when your task requires a pretrained convolutional encoder (ResNet18) to produce fixed-size representation vectors of a specific dimensionality (e.g., 512 dimensions) rather…
Frameworks for designing agents that must reason and act under time pressure, limited computational resources, and changing environments — based on Bratman, Israel, and Pollack's…
Use when a layout must adapt across screen sizes — breakpoints, container queries, fluid type, touch targets, zoom, or mobile overflow bugs.
Retell AI reference architecture — AI voice agent and phone call automation. Use when working with Retell AI for voice agents, phone calls, or telephony.
Revenue analytics architecture - ARR / NRR / GRR decomposition, cohort retention, expansion drivers, segment economics, and CAC payback diagnostics.
Quarto agente do Time de Migração. Opera em duas fases. Fase 1: detecta a topologia do legado, sempre propõe uma topologia moderna alternativa e produz topology_decision.md (com…
Reverse-engineer Architecture Decision Records (ADRs) from an existing codebase. Use when a project has no ADRs but you want to document WHY architectural decisions were made…
Reverse engineer native, managed, Electron/JavaScript, packaged, and browser applications with REA. Use shipped-artifact or approved runtime evidence to explain features, compare…
Coordinates evidence-driven reverse engineering of existing software. Use when planning a bounded recovery effort across repository reconnaissance, observable behavior, as-built…
Claude Code plugin tự động thiết kế agent team + sinh skill từ domain description — 6 architecture patterns, tạo .claude/agents/ + .claude/skills/ tự động. +2098⭐/week.
Reviews whether a design is SOUND — solving the right problem, derived from its stated goals and constraints — and emits ranked, evidence-backed findings, not edits.
Audit a module for Clean Architecture and boundary compliance
Enforce evidence-based responses by requiring primary source verification before making claims. Use when accuracy matters and guessing is unacceptable -- audits, debugging,…
Review an entire repository for architecture quality — coupling, interfaces, naming, tech debt, test coverage, stale docs.
Revisar la arquitectura de software en cuanto a acoplamiento, cohesión, principios SOLID, diseño de API, escalabilidad y deuda técnica.
Use when reviewing a proposed architecture, a tech plan, or a PR for soundness — drive it to correctness/simplicity/fit, enable rather than gatekeep, flag the open gate without…
Analyzes a codebase's modularity imbalances using the Balanced Coupling model and produces a review of design issues.
Opt-in, collaborative system-design workflow based on Juval Löwy's iDesign methodology in *Righting Software*.
Direct the risk architecture subdomain — route questions about position sizing, tail risk, correlation regimes, and drawdown psychology to the right specialist skill.
3-Phase Knowledge Search strategy for the RLM Factory ecosystem. Auto-invoked when tasks involve finding code, documentation, or architecture context in the repository.
CRITICAL: Use for Robius app architecture patterns. Triggers on: Tokio, async, submit_async_request, 异步, 架构, SignalToUI, Cx::post_action, worker task, app structure, MatchEvent,…
Use when assigning Roblox feature ownership, code location, dependencies, startup, or client-server boundaries without imposing a framework.
Design and build a Roblox game's economy from the developer's own vision — currencies, income, luck/rarity/mutations, modifiers, progression, rebirths, shops, sinks.
Nightly code and architecture health scan. Passively triggered by scheduler (cron or GitHub Actions), not invoked by users directly.
Analyzes Claude Project context budget using the two-pool architecture: knowledge files (~66,500 token RAG threshold) vs. threshold-exempt overhead.
Specialized agentic and context engineering prompt methodology for Claude. Use when designing AI agents — system prompts, tool definitions, context window architectures, failure…
Specialized software engineering prompt methodology for Claude. Use when building prompts for system design, code review, incident response, security analysis, API design,…
Generates a structured Project Brief — a comprehensive markdown document that extracts goals, architecture, knowledge file inventory, Custom Instructions summary, Memory contents,…
Builds complete, optimized Claude prompts and Project scaffolds from task descriptions. Use when building, designing, creating, or structuring a Claude prompt or system prompt.
Evaluates and scores Claude prompts and system prompts using a six-dimension Scorecard with anchored 1-5 rubrics.
Enforces routing through domain routers before invoking individual tools, abstracting tool selection into deterministic intent-to-command mappings.
LiteLLM-RS Routing Architecture. Covers 7 routing strategies, lock-free design with DashMap, health-aware selection, fallback chains, and load balancing.
Use when optimizing RTL microarchitecture for area or clock frequency (Fmax), a design is too big to fit or too slow to meet timing, a wide multiply or barrel shifter is the…
Non-negotiable Jardis architecture rules — five constitutional pillars, hexagonal dependency direction, Closure-Orchestrator pattern.
Use when you operate coding-agent infrastructure with a feedback signal — eval suites, run-level telemetry, A/B baselines, or a skill catalog under test — and want to cap — from…
Use to validate architecture rules against a diff -- hard gate that blocks PR creation on violations
Guides Markdown-capable coding agents through large changes with deep analysis, intent refinement, task decomposition, GitHub issue tracking, batch PRs, adaptive control, and…
AOSP Part V — Runtime. Use when reasoning about ART (dex2oat, AOT/JIT, baseline profiles, GC, oat/vdex/odex files, class loaders, JNI bridge) or the Native Bridge (Berber — from…
Assess whether a feature is stateful or exempt, create and check its seven-part Runtime State Integration Contract, and summarize validation gaps.
Runway reference architecture — AI video generation and creative AI platform. Use when working with Runway for video generation, image editing, or creative AI.
Checklist executor for Rust architecture reviews. Detects the Rust edition, async runtime, and workspace structure, then runs a systematic checklist covering ownership discipline,…
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential).
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential).
Design precise architecture and data flow for SaaS, workflows, automations, and AI-enabled systems. Use for system boundaries, C4 views, DFDs, sequences, tenancy, APIs/events,…
วิเคราะห์และสร้างเอกสาร Plan, Architecture และ Database Schema สำหรับระบบ SaaS ที่เน้นตลาดประเทศไทยเป็นหลัก รวบรวม Best Practice สำหรับคนไทย (Beam Checkout, LINE Login/Notify,…
Turn a confirmed specification, root-cause finding, or impact analysis into an atomic, verifiable, reversible implementation plan with explicit scope and risk controls.
Production architecture for SalesLoft API integrations with service layer, webhook processing, and CRM sync patterns.