Use Morfx when Codex needs deterministic AST-based code queries, replacements, staged edits, or recipe-driven refactors through the Morfx MCP server instead of brittle text-only…
Tech Lead and Architect. Use for architectural decisions, design guidance, task planning, code quality, and refactoring strategy.
Expert guidance for building production-ready tool-calling agents with Databricks Mosaic AI Agent Framework.
Deliver repeatable MotherDuck architectures across multiple clients. Use when a consultancy, agency, or multi-client product team needs to standardize isolation, provisioning,…
Use when you have a GNPS-generated classical or feature-based mass spectral molecular network (graphml or JSON format) and a corresponding MS2LDA experiment with Mass2Motif…
Expert guidelines for building performant animations with Motion (formerly Motion One) vanilla JavaScript animation library
Complete production-ready guide for Motion Canvas with ESM/CommonJS workarounds, full setup templates, and troubleshooting for programmatic video creation using TypeScript
Motoko language pitfalls, modern syntax, and architecture patterns for the Internet Computer. Covers persistent actors, stable types, mo:core standard library, dot notation,…
Analista de vigilancia científica en TI para entornos doctorales. Conecta noticias recientes con evidencia científica verificable y entrega metadatos completos, trazables y listos…
Move smart contract development on Sui. Use when writing, reviewing, or debugging Move code, Move.toml configuration, or Sui object model patterns.
Use when working in a GitHub repository connected to Moxie Docs — read its living documentation, conventions, and architecture context over the Moxie Docs MCP server before…
找出架構摩擦與 deep module 候選，但不直接修改實作程式碼。 Use when: 使用者要架構回看、找重構候選、改善可測性、 或把實作中暴露的架構摩擦整理成 OpenSpec 候選。
在 mp_Net-Core 專案的 MicroPython slave 中新增功能模組 (command/action/task/config)。 每當使用者提到「新增指令」「新增 action」「新增 task」「新增功能模組」「新增 schema」、 或者要在 slave/ 底下加入任何新功能、或者 mp_Net-Core / mp_Net-Light…
Orchestrates Multi-Page Application (MPA) architecture within a single repository, integrating with relevant skills / Mengorkestrasi arsitektur Multi-Page Application (MPA) dalam…
Kompletní skill pro práci s mPohoda API (api.mpohoda.cz). Použij tento skill VŽDY, když uživatel zmíní mPohoda, Stormware, faktury, objednávky, sklad, ceník, nebo jakoukoliv…
TypeScript SDK for the Payment HTTP Authentication Scheme. Handles 402 Payment Required flows with Tempo, Stripe, and other payment methods.
TypeScript SDK for the Payment HTTP Authentication Scheme. Handles 402 Payment Required flows with Tempo, Stripe, and other payment methods.
Architecture de messaging IoT avec MQTT incluant brokers, topics, QoS, sécurité et patterns. Se déclenche avec "MQTT", "broker MQTT", "Mosquitto", "IoT messaging", "topic — from…
MQTT/Homie/Home Assistant Discovery debugging for the pool-controller. Use when asked to debug MQTT communication, verify HA Discovery payloads, test Homie convention compliance,…
You are an advanced Docker containerization expert with comprehensive, practical knowledge of — from MrJmpl3/opencode_____data_____configuration
Use when when you have MS/MS spectral data (raw or intermediate format) that must be fed into the Mass2SMILES Docker container or similar deep learning models for…
Parse and analyze multiple sequence alignments using Biopython. Extract sequences, identify conserved regions, analyze gaps, work with annotations, and manipulate alignme — from…
MS-DIAL-based metabolomics preprocessing as alternative to XCMS. Covers peak detection, alignment, annotation, and export for downstream analysis.
Use when training embeddings from multi-modal spectral data (peak information + metadata) where you need to ensure both contrastive discriminability AND reconstruction fidelity.
Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text/image analysis, blocklist management, or harm detection for hate,…
MessagePack binary encoding for compact inter-agent payloads. Pack/unpack, typed arrays, extension types, streaming decoder, and performance comparison with JSON.
Use when executing and reporting the analysis for a Manufacturing & Service Operations Management (M&SOM) manuscript — proving structural results and running numerical studies for…
Implement, review, or test Market Signal Pipeline Google Cloud and Terraform deployment work. Use for Cloud Scheduler, Pub/Sub, authenticated push subscriptions, Cloud Run,…
design step of mspec workflow — write design.md + design-rationale.md + architecture-overview.md, full Constitution Check
Morning Star (启明星) 跨角色通用编码行为准则 —— Think Before Coding（显式假设、不静默猜测）、Simplicity First（最小实现、拒绝投机抽象）、Surgical Changes（只改与任务直接相关的行、不顺手重构、不 piggyback）、Goal-Driven…
Morning Star (启明星) QC 审查基线与 QA 验证契约 —— 三名 QC reviewer 的共享审查工作流、代码质量/安全正确性/性能可靠/可维护性清单、标准审查报告 Markdown 模板（YAML frontmatter + Findings 三档 + Source Trace + Summary + Verdict）、QC…
Morning Star (启明星) harness 与 Superpowers 技能的对齐与消解契约 —— 未装插件时的加载方式（Read SKILL.md 执行）、优先级（harness > 技能正文）、最小技能声明契约（Superpowers 行需含 Trigger + Expected evidence）、`Delegation` 与…
Generates MSTest tests in C#. Microsoft's built-in testing framework for .NET. Use when user mentions "MSTest", "[TestMethod]", "[TestClass]", "Assert.AreEqual".
Use for any Magic: the Gathering deckbuilding, tuning, playtesting, simulation, spoiler review, or card-shopping work in this repo.
Suggests using Microsoft Testing Platform (MTP) hot reload to iterate fixes on failing tests without rebuilding.
Guia completo de MUI V7 para React + TypeScript. Ensina migração V6→V7, design responsivo avançado, theming profissional, padrões de componentes e detecção automática de sintaxe…
Use when designing or evaluating MuleSoft Anypoint Platform deployment topology, runtime model selection, API governance with API Manager, or Anypoint Exchange strategy.
Production-tested blueprint for building 5-10 agent teams in OpenClaw with cross-agent routing, Telegram integration, and role-based architecture
Bootstrap and migrate an OpenClaw workspace from single-agent to beginner-friendly multi-agent mode with visible routing.
Use when coordinating multiple concurrent agents that need to communicate, share state, synchronize work, and handle distributed failures across a system.
Multi-agent debate / Society of Mind — N agents × R rounds converge on consensus. Du et al. 2023 beats zero-shot CoT on MMLU/GSM8K/MATH.
Multi-agent parallel E2E validation for database refactors. TRIGGERS - E2E validation, schema migration testing, database refactor validation.
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents…
Advanced multi-agent patterns — capability registry, durable state (Redis/DynamoDB), task decomposition, testing multi-agent systems, pattern quick-selection guide, failure…
Multi-agent system prompt design and orchestration patterns. 多代理系統提示設計與編排模式。 Use when: building orchestrator-worker architectures, designing worker agent prompts, coordinating…
A complete 10-agent team architecture with roles, model routing, cron templates, meeting system, and phased deployment guide.
Run a structured pre-merge review across correctness, readability, architecture, security, and performance instead of relying on a shallow spot check.
Use when designing a unified multi-channel service strategy spanning phone (Service Cloud Voice), email (Email-to-Case), chat (Messaging for In-App/Web), social, and SMS with…
Decision framework and patterns for architecting applications across AWS, Azure, and GCP.
Design multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, and GCP.
Fetches additional perspectives from OpenAI Codex and Google Gemini for architecture, review, and debugging. Transparently displays all LLM calls. — from engineering/testing
Fetches additional perspectives from OpenAI Codex and Google Gemini for architecture, review, and debugging. Transparently displays all LLM calls.
Fetches additional perspectives from OpenAI Codex and Google Gemini for architecture, review, and debugging. Transparently displays all LLM calls.
Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container set — from…
Designing, orchestrating, and maintaining multi-package architectures in Salesforce DX: dependency DAG design, layered package decomposition, install ordering, cross-package API…
다각도 코드 리뷰 스킬. UI/UX, 성능, 디자인, 코드 품질, 엣지케이스, 보안 등 6가지 관점에서 체계적인 코드 리뷰를 수행합니다. 코드 변경 후, PR 생성 전, 기능 구현 완료 후에 사용하세요.
Build and deploy the same feature consistently across web, mobile, and desktop platforms using API-first architecture and parallel implementation strategies.
Build and deploy the same feature consistently across web, mobile, and desktop platforms using API-first architecture and parallel implementation strategies.
One piece of content becomes 10 — blog to Twitter thread, LinkedIn article, YouTube script, newsletter, TikTok
一键将视频导出为多个投放平台所需的不同规格（抖音/快手/视频号/头条/朋友圈）。 在以下场景使用：(1) 导出多平台视频规格，(2) 视频裁切为竖屏/方形，(3) 批量生成不同时长版本。 触发关键词："多平台导出"、"抖音规格"、"竖屏"、"方形视频"、"平台适配"、"导出"。