Stateful, phased test-rollout orchestrator for existing products. Writes context/foundation/test-plan.md, then drives each rollout phase through /10x-new → /10x-research →…
Generate optimized Vercel Edge Functions with geolocation, authentication, and data transformation — from engineering/cloud-platforms
Design rigorous A/B/n experiments — hypothesis, power analysis, MDE, randomisation unit, guardrails, decision criteria — and route to stats-reviewer for peer-review.
Drop in a 3-paragraph "what is this?" page for new users, per frontend framework; optionally collapses into the architecture page when both standards are enabled
Acceptance testing - execute handler tests via real Claude Code tool calls in main thread
Use when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this test significant — promote or kill?"; produces a…
주제·청중·목적에 맞춘 편집 가능한 PowerPoint(.pptx)를 결론과 다음 행동이 먼저 보이도록 만듭니다. 필요한 조사 → 스토리라인 → python-pptx 제작 → 렌더 검증 순으로 실행하며 고정 템플릿 없이 내용에 맞게 구성합니다.
Create a new Architecture Decision Record in .context/decisions/. Use when documenting an architectural decision.
Build a capability end-to-end — backend vertical slice (Contracts→handler→validator→endpoint) AND the React page wired to it.
SAM-style feature initiation workflow: discovery -> codebase analysis -> architecture spec -> task decomposition -> validation -> context manifest.
Adds support for a new MoE language model to PithTrain. Use when the user asks to "add support for model X", "implement model Y in pithtrain", "port model Z", or otherwise…
Add documentation for a new AI provider — usage docs, env vars, Docker config, image resources.
Scaffold a test for a react-native-css feature following the project's testing conventions.
Deploy and orchestrate Vertex AI ADK agents using A2A protocol. Manages AgentCard discovery, task submission, Code Execution Sandbox, and Memory Bank.
Audite l'ensemble des ADR (Architecture Decision Records) d'un projet et leur cohérence avec le dossier arc42, les changements OpenSpec et le code : inventaire de tous les…
Create a new Architecture Decision Record with sequential numbering and AgentDB registration
ADR(Architecture Decision Record) 작성 스킬. 두 개 이상의 기술 선택지를 비교하고 추천안과 그 근거, 숨겨진 비용, 확장성, 2년 뒤 기술 부채까지 입체적으로 평가한다. 비개발자도 이해할 수 있도록 한국어 위주 설명 + 추천안 강조.
Verify a component on AEM after deployment — walk dialog fields, create a test page with the component configured, and save verification docs.
Maquina autonoma de construcao. Feature, refactor, UI, issue, integracao, otimizacao — recebe objetivo, entrega PR pronto.
Maquina autonoma de correcao. Bugs, erros TypeScript, tech debt — auto-detecta modo, diagnostica, corrige, verifica em loop convergente. Produz PR com fix verificado.
Ciclo autonomo Test-Fix-Retest. Roda suite completa, documenta achados, corrige em sprints, re-testa ate convergencia. Max 3 ciclos.
Corrige erros TypeScript com auto-routing. Scan (diagnosticar), Fix (batch incremental), Sweep (varredura com ratchet). Substitui workflow manual de typecheck.
Gera testes Playwright production-grade a partir de fluxos reais observados via MCP. Explora o app pelo browser, documenta cada passo, gera codigo TypeScript, valida executando.
Gera e mantém infraestrutura de desenvolvimento e CI/CD: Dockerfile, docker-compose, pipeline, env vars. Dev novo roda em 10 min.
Reestruturacao sem mudanca de comportamento. Extrair modulo, renomear em cascata, reorganizar. Cada passo com commit. Use when refactoring code structure.
Roda suite E2E completa com validacao de infraestrutura. Pre-flight (dev server, env vars, smoke), execucao em batches de 10-20 testes, auto-fix de falhas (seletores, mocks,…
PDCA Orchestrator — executa Quality Acceptance Testing com ciclo Plan-Do-Check-Act. Carrega baselines e knowledge, executa cenarios 4 camadas (L1-L4), classifica falhas em 6…
Configures best-practice alerting policies for Google Cloud Vertex AI / Agent Platform agents on Agent Runtime.
Create governed Hermes agents as auditable enterprise operating units with manifest, capability stack, memory seed, deployment plan, verification contract, registry entry, and…
Bootstrap an AWS EKS cluster optimized for Agentic AI workloads — Karpenter v1.2+ GPU node pools, EKS Auto Mode, Kubernetes 1.32+ with DRA 1.35 GA, VPC CNI, GPU Operator, and…
Use when designing or improving AI engineering workflows after the stack direction is already mostly known.
Guide the user through containerizing and serving a simple website or documentation folder with Docker — inspects the project to detect what to serve (ready-to-serve static HTML,…
22-dimension, 5-tier technical debt audit covering code quality, architecture, infrastructure, quality processes, and operational readiness.
16-dimension test suite audit with depth control (quick/standard/deep), gap matrix, and health scoring.
Writes production code that satisfies stack-context standards on the first pass: interface-first design, backward-compatibility checks, lightweight self-review.
Use when explaining code, concepts, patterns, or architecture: engineer-grade technical explanations with 3-tier depth control, ASCII diagrams, and execution traces.
Saves persistent technical discoveries (debugging insights, non-obvious behaviors, workarounds, integration gotchas) and searches them across sessions.
특정 고객·산업을 위한 실제 동작하는 AI·App Platform 운영 데모를 단일 HTML SaaS 앱으로 생성합니다. Golden Runtime과 고정 GitHub Primer Dark Dimmed 계열 soft-dark 디자인을 재사용하고 고객 주요사업 5개 메뉴와 GitHub Ecosystem·Microsoft…
Standalone post-generation QA pass that lints any frontend output (HTML/JSX/Vue/Svelte/CSS) against the named anti-pattern catalogue and proposes specific rewrites with severity…
Generate architecture guidelines for the project. Analyzes tech stack from DESCRIPTION.md, recommends an architecture pattern, and creates .ai-factory/ARCHITECTURE.md.
Code quality guidelines and best practices for writing clean, maintainable code. Covers naming, structure, error handling, testing, and code review standards.
Adversarial, axis-separated code review. Runs three isolated passes — Standards (code smells + structure/logic/types/perf), Spec (does it match the issue/PRD), and Adversarial…
Analyze project and generate Docker configuration: Dockerfile (multi-stage dev/prod), compose.yml, compose.override.yml (dev), compose.production.yml (hardened), and…
QA workflow for testing a feature or task implementation. Analyzes changes, produces test plans, and describes concrete test scenarios.
Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment.
Analyze a codebase to generate a comprehensive architecture and structure report. Use when user wants to understand a codebase, explore project structure, or generate analysis.
Analyze code review pipeline performance for a specific PR. Use when investigating slow PRs, identifying bottlenecks, or debugging performance issues in code reviews.
Review Android Kotlin code for architecture, performance, correctness, and best practices
Use when writing, reviewing, refactoring, or discussing Angular code. Applies the Angular Style Guide for naming, project structure, dependency injection, templates, and component…
Recherche dans la documentation officielle Anime.js pour créer des animations JavaScript. Utiliser quand l'utilisateur a besoin d'aide avec anime.js pour des animations,…
Turns an answer into a one-page visual HTML explainer: the model writes a short Markdown draft and the bundled CLI builds one page.
Author Test Cases (TCs) and the traceability matrix linking UN→PR→SR→TC. Verify every SR clause has at least one TC.
Systematic development workflow: Analyze → Plan → Execute → eLicit → eXamine. Use for ANY development task: features, bug fixes, refactoring, hotfixes.
Systematic development workflow: Analyze → Plan → Execute → eLicit → eXamine. Use for ANY development task: features, bug fixes, refactoring, hotfixes.
Add a new GraphQL mutation to an existing schema in daily-api with validation, resolvers, and tests
Create a new Laravel API controller following this project's patterns. Use when creating new API endpoints, CRUD controllers, or backoffice controllers.
Add a new GraphQL query endpoint with type safety, GraphORM integration, and tests
Diff an OpenAPI spec across commits and classify each change as major/minor/patch per SemVer-for-APIs
Audits any API documentation site by crawling every endpoint page and scoring each one across 5 checks: description quality, OpenAPI spec presence, body param descriptions,…
Design stable, hard-to-misuse interfaces — REST/GraphQL endpoints, module boundaries, type contracts, component props, anything where one piece of code talks to another.