В каталоге 183 730 навыков в 14 категориях.
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decomp...
This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swa...
Multi-agent parallel performance profiling workflow for identifying bottlenecks in data pipelines. Use when investigatin...
Automated generation of MULTIAGENTPLAN.md files with comprehensive task decomposition, dependency analysis, agent role a...
Runs read-only parallel review of a PR, branch, commit, or diff across bugs, security, tests, maintainability, performan...
Use this skill when implementing complex programming tasks that benefit from multi-agent collaboration. This skill coord...
Conduct comprehensive research on any topic by coordinating 2-4 specialized researcher agents in parallel, then synthesi...
Fan a local diff through three independent, axis-focused review passes (correctness, security, conventions), then merge...
Coordinate multiple agents for comprehensive review
Multi-agent review orchestration dispatching parallel specialist reviewers with line-level evidence collection.
Run a structured review gate before merging multi-agent outputs. Use when multiple agents have produced work packets tha...
Master QMIX, MADDPG, CTDE - multi-agent learning with coordination and credit assignment
Design and orchestrate multi-agent AI systems with knowledge harvesting, agent collaboration, and learning loops. Use wh...
マルチエージェントシステム設計を専門とするスキル。複数のエージェント間の効果的な協調、ハンドオフプロトコルの設計、情報受け渡しメカニズムにより、スケーラブルで保守性の高い分散システムを構築する。Anchors:• Building Micr...
Route tasks to specialized AI agents with anti-duplication, quality gates, and 30-minute heartbeat monitoring
Run a gated multi-agent coding workflow for development requests. Use when the user asks Codex to use multiple agents, a...
A virtual 3-person development team with dynamic roles. You act as the Project Manager who assembles a team, assigns tas...
A complete 10-agent team architecture with roles, model routing, cron templates, meeting system, and phased deployment g...
Use this skill when you need evidence-bounded delegation, coordination, shared state, conflicts, ownership, termination,...
Detects agent-to-agent calls without authentication, authorization, or permission scoping. Use when writing code that ca...
Execute multi-agent voting for critical decisions using MAKER-style first-to-ahead-by-k error correction.
/multi-agent-work — Von Research bis Implementierung in einem Durchlauf. 6-Phasen-Workflow: Research → Fixes → Synthese...
Manager session that launches worker Claude instances in parallel git worktrees for concurrent implementations. Observer...
Designs parallel agent workstreams for large feature sets by analyzing dependencies, assigning specialized agent types (...
Use when configuring ARC_PROVIDER_MODE or routing verification work to external AI providers (Codex, Gemini). Claude-onl...
Start the multi-AI pipeline with a given request. Guides through plan -> review -> implement -> review workflow.
Multi-perspective code review using Claude, Gemini, and Codex as specialized agents. 5-dimensional analysis (security, p...
Consult external AIs (Gemini 2.5 Pro, OpenAI Codex, fresh Claude) for second opinions when stuck on bugs or making archi...
Consult external AIs (Gemini 2.5 Pro, OpenAI Codex, Claude) for second opinions. Use for debugging failures, architectur...
Production-ready code generation and incremental development using Explore-Plan-Code-Commit workflow. TDD-driven with <2...
Use when stuck on complex problems, need architecture validation, want code review from multiple perspectives, or debugg...
Ollama-based multi-AI model orchestration with auto-profiling, smart routing, and ensemble execution
Parallel multi-AI cross-validation research workflow (大版本). Dispatch N internal sub-agents + grok + gemini in parallel,...
Test-driven development with independent verification to prevent test gaming. TDD workflows, test generation, coverage v...
Multi-layer quality assurance with 5-layer verification pyramid (Rules → Functional → Visual → Integration → Quality Sco...
Generate a consistent multi-angle product image set (front, back, left/right side, top, 45°, detail macro, packaging, in...
Takes a draft written by two or more contributors and rewrites it as a single, consistent voice — smoothing over clashin...
Turn multiple product shots, event footage, travel clips, gameplay moments, UGC/product footage, B-roll, or mixed media...
Professional Multi Cloud Expert skill. Build robust, automated deployment pipelines and configure cloud infrastructure a...
Design and deploy AI workloads across AWS, Azure, GCP, and OCI with intelligent routing, cost optimization, and cross-cl...
Design multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, and GCP....
Design multi-cloud and hybrid architectures across AWS, Azure, and GCP — covering service selection, networking, cost op...
Decision framework and patterns for architecting applications across AWS, Azure, and GCP.
Use when reviewing identity across multiple cloud providers on an authorized engagement. Covers federated identity desig...
Multi-Cloud IoT Strategy enables deployment of IoT infrastructure across multiple cloud providers to achieve redundancy,...
Production-grade Kubernetes cluster provisioning and management on budget-friendly cloud providers (DigitalOcean DOKS, H...
"Multi-cloud" is a loose word that hides four distinct architectures with
Use when the user explicitly wants multiple Codex agents or a virtual team, the work can be decomposed into safe paralle...
Run this command with user's arguments:
全网内容出海信息源 — 每日扫描全平台(公众号/抖音/视频号/小红书/快手/B站)内容出海爆款作品,按点赞量筛选Top50,智能聚类题材方向后生成包含平台标签、封面、互动数据与创作洞察的HTML日报。支持按平台、关键词、时间范围定向查询。⚠...
复刻蒸馏写作技能 —— 分析一位作者的多篇文章,深度还原其思维方式与写作风格,生成专属写作分身子技能与风格提示词。支持公众号、抖音多平台自动采集素材,也可手动粘贴文章或指定文件路径。触发词:蒸馏写作风格、写作分身、克隆写作风格、复刻蒸馏写作...
Currency settings and formatting for global users in LivestockAI
检索多模态数据处理平台已完成工作流的最新处理结果。适用于网页爬取、文档解析、OCR、Markdown/JSON 转换等已写入数据集的结果问答,并返回可回溯的数据集版本与来源引用。
When the user requests to find, analyze, and merge multiple datasets from Hugging Face or similar repositories into a un...
When the user wants to solve Multi-Depot VRP (MDVRP), optimize routes from multiple warehouses/depots, or handle multi-f...
Help user work from multiple devices. Sync project via git.
This skill should be used when the user asks to "build multiple Dockerfiles", "compile varios dockerfiles", "multi-conta...
When the user wants to optimize inventory across multiple network locations, implement multi-echelon inventory policies,...
Manage finances across multiple businesses or legal entities.
Execute multi-agent orchestrated workflow
Strategies for coordinated changes across multiple files with Claude Code. Use when making API changes, updating interfa...
读取多 Sheet Excel 文件并统计规模,支持大文件向 Parquet 格式转换、分类数据统计及可视化报告生成。
Analyze configuration files for validation and best practices
Implement configuration management supporting TOML/YAML/JSON formats with inheritance and runtime overrides
Use this skill when a company answers to two or more frameworks and is collecting the same evidence twice, and asks "map...
Generate a Next.js Roblox codes page from validated JSON using a reusable TSX template. Use when creating or regeneratin...
Use when one Relayfile workspace must be mounted on several machines and an agent placed on a remote host inside the liv...
Run and troubleshoot multiple parallel Orient instances with isolated ports, databases, and Docker resources. Use for wo...
Use when creating bilingual or multilingual README files from an existing README while preserving Markdown structure.
当用户需要基于现有 README 创建中英或多语言 README,并保持 Markdown 结构时使用。
Process documents in multiple languages with focus on low-resource languages, accented character systems, and cross-ling...
Review a change for defects, then against its spec, its codebase's conventions, the domains trying to emerge from it, an...
Use when facing complex problems, making decisions, seeking creative solutions, or when single-perspective thinking feel...
Fetches additional perspectives from OpenAI Codex and Google Gemini for architecture, review, and debugging. Transparent...
여러 LLM(OpenAI, Gemini, Ollama 등)을 통합하여 멀티 에이전트 협업을 수행합니다. 역할 분담, 토론/합의, 체인 파이프라인, 병렬 처리 등 다양한 협업 패턴을 지원하며, 사용 시점에 시나리오를...
Use AgentPMT external API to run the Multi-Location Route Optimizer W Map tool with wallet signatures, credits purchase,...
사용자가 "모든 방법 총동원해서 이미지로 만들어줘" 같이 이미지 제작에 가진 능력을 다 쓰라고 요청할 때 사용. 코덱스(codex CLI), 제미나이(Gemini API), HTML/CSS 렌더링, 사용자 사진 라이...
Débat multi-agents avec 6 IA pour valider PRD et code. Utiliser pour obtenir des perspectives diverses sur des décisions...
Multi-specialist collaborative analysis for complex decisions. Spawns parallel subagents with diverse domain expertise t...
Multi-modal prompting with vision, audio, and document understanding
When the user requests a complete travel itinerary involving multiple modes of transportation with specific waypoints an...
Multi-model orchestration for ARIA. Activate when dispatching tasks to different LLM providers (OpenAI, local models, cl...
Organize animation and manhwa/webtoon production notes across multiple AI models and reference sources. Use when extract...
Use Gemini to find existing solutions before building from scratch. Leverages Google Search grounding to discover code e...
Synthesize outputs from multiple AI models into a comprehensive, verified assessment. Use when: (1) User pastes feedback...
Use when coordinating complex tasks across multiple AI agents with a centralized handoff document for planning, executio...
多模型协作 — 调用 gemini-agent 和 codex-agent 辅助分析 **触发场景**(主动使用): - 深度代码分析:算法理解、性能瓶颈、架构梳理 - 大范围探索:5+ 文件、模块依赖、调用链追踪 - 复杂推理:方案评估...
Orchestrate multiple frontier LLMs (Claude, GPT-5.1, Gemini 3.0 Pro, Perplexity Sonar, Grok 4.1) for comprehensive resea...
Multi-model ensemble review convergence loop and test gates across Gemini, Claude, and Copilot.
マルチモデルコードレビュー。LLMがコードレビューを行った後、GitHub Copilot CLIに精査させて双方の視点を統合した最終レビューを提供。Use when user wants multi-model code review,...
協調多個 AI 模型(ChatGPT、Gemini、Codex、QWEN、Claude)進行三角驗證,確保「Specification == Program == Test」一致性。過濾假警報後輸出報告,大幅減少人工介入時間。
多模型镜头提示词适配:把一份分镜表改写成适合不同视频生成模型的提示词(中/英、首帧/首尾帧/纯文生视频、运镜词表、负面约束),模型中立、不编造价格或参数。Use when the user wants the same shot list...
Run multi model triangulation.
Run multiple AI models in parallel for 3-5x speedup with ENFORCED performance statistics tracking. Use when validating w...
Unified writing system with intelligent model routing. Default: Claude. Options: GLM-4.7 (cheapest), GPT-4o/mini, Gemini...
Use when working in a multi-module Maven project. Covers parent POM conventions, shared dependency management, inter-mod...
When the user needs to analyze deployments across multiple Kubernetes namespaces with filtering criteria. This skill dis...
Attach, secure and operate additional 3x-ui panels as nodes of a master panel — probe before saving, choose a TLS trust...
When the user wants to optimize two or more conflicting objectives and reason about Pareto trade-offs — Pareto dominance...