Conversation patterns and interaction protocols for multi-agent systems. Covers request/response, pub/sub, blackboard, delegation chains, debate, critique, consensus,…
Data structures and serialization formats for agent-to-agent communication. Covers message envelopes, structured output schemas, capability declarations, task handoff payloads,…
Guides the design and structuring of workflow-based Claude Code skills with multi-step phases, decision trees, subagent delegation, and progressive disclosure.
PCI DSS compliance assessment and reporting for cardholder data protection, SAQ automation, and ASV scan orchestration
Business war game orchestration skill for competitive response simulation and strategic testing
This skill creates a Dapr workflow application in .NET. Use this skill when the user asks to "create a workflow in .NET", "write a .NET workflow application" or "build a workflow…
This skill creates a Dapr workflow application from a diagram. Use this skill when the user provides a workflow image (PNG, JPG, JPEG, GIF, WebP) or a BPMN 2.0 XML file (.bpmn,…
This skill creates a Dapr workflow application in Python. Use this skill when the user asks to "create a workflow in Python", "write a Python workflow application" or "build a…
Claude Fable 5's operating doctrine — calibration, reasoning moves, problem framing, planning, debugging, execution, orchestration, verification, communication, recovery, context…
Execute complex tasks through sequential sub-agent orchestration with intelligent model selection, meta-judge → LLM-as-a-judge verification — from TuYv/ccpm
Validates that a DAG node's output matches its declared JSON schema before passing to downstream nodes. The glue that makes multi-agent DAGs reliable.
End-to-end live production — OBS as the mixer with obs-websocket control, MIDI/OSC cue triggers, DMX lighting sync, PTZ camera moves, system audio routing, NDI/SDI I/O, and…
Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.
Specialist knowledge of the addyosmani/agent-skills project (Shell, JavaScript). Use when working with or extending agent-skills: understanding its architecture, patterns, and…
opencode-advisor 플러그인 빌드를 처음부터 끝까지 조율하는 오케스트레이터. 'advisor 플러그인 만들어줘', 'opencode-advisor 빌드', 'model routing 플러그인 구현', '모델 라우팅 플러그인', 'advisor 구현' 요청 시 반드시 이 스킬을 사용.
Build, configure, and debug agent-actions agentic workflows. Trigger on workflow YAML, UDFs, context_scope, guards, versions, schemas, seed data, prompts, reprompt, HITL,…
Inter-agent communication patterns including message passing, shared memory, blackboard systems, and event-driven architectures for LLM agentsUse when "agent communication,…
Diagnoses and debugs A2A agent communication issues including agent status, message routing, transport connectivity, and log analysis.
Knowledge base for designing AI agents — persona crafting, system prompt patterns, multi-agent orchestration, memory design, evaluation.
Multi-agent orchestration enforcement for /team command. Validates session directory paths and ensures /team Tasks use a valid agent from the routing whitelist.
Build deterministic, multi-step workflows with the Microsoft Agent Framework .NET SDK (Microsoft.Agents.AI.Workflows).
Provides best practices for AI agent orchestration including MCP servers, A2A protocol, multi-agent coordination, and swarm architectures.
Create, use, and manage Agent Skills for Claude. Use when working with Skills, creating custom capabilities, or understanding how Skills extend Claude's functionality.
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems.
Build and operate a multi-agent task queue in OpenClaw with priority queues, delayed/dead-letter queues, scheduling, retry/timeout control, dependency management, parallel…
AI agent workflow patterns including ReAct agents, multi-agent systems, loop control, tool orchestration, and autonomous agent architectures.
Generate a reusable agent-driven project workflow as filesystem-based Agent Skills. Use when bootstrapping planning, refinement, architecture, implementation, review, and…
Use when reviewing or auditing an existing agent / LLM-pipeline architecture — e.g. 'is my workflow actually decomposed or secretly a mega-agent?', 'are my task boundaries and…
Route an AI-agent engineering task to the right skill among 14 meta specialists — planning a multi-session build, decomposing a plan into an agent chain, orchestrating a squad,…
Multi-model AI collaboration via orchestrator MCP. Use when seeking second opinions, debugging complex issues, building consensus on architectural decisions, conducting code…
Choose multi-agent architectures using environment-first analysis, coordination pressure, commitment tuning, and knowledge levels.
Game development orchestrator. Routes to platform-specific skills based on project needs. — from engineering/workflow-orchestration
Build a complete web scraping Actor with Crawlee and deploy to Apify. Use when implementing end-to-end scraping: input schema, crawler, data extraction, dataset output, and…
Expert knowledge for building AI agents with Argentic - a Python microframework for async MQTT-based agents with multi-LLM support, custom tools, and multi-agent orchestration
Route an Astro task to the right spoke — building the site (components, islands/hydration, content, SSR, actions, i18n) or publishing a docs/wiki/press-kit site.
Use when an approved ai-architecture.md defines a multi-agent workflow and AutoGen is the chosen framework.
Use when an approved ai-architecture.md defines a tool surface and AutoGen is the chosen framework. Produces tool schemas, an authorization-enforcing execution adapter,…
Automatisation par scripts (PowerShell, Python, Bash) pour tâches répétitives — cron jobs, batch processing et orchestration.
Build and operate the "Autonomous Workflow Authoring for software engineering delivery" capability for software engineering delivery.
Expert in background job processing with Bull/BullMQ (Redis), Celery, and cloud queues. Implements retries, scheduling, priority queues, and worker management.
Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees.
Scrape structured data with Bright Data Scraping Browser using Playwright/Puppeteer. Use when scraping JavaScript-rendered pages, SPAs, or sites requiring browser interaction.
Browser Use is an open source browser automation framework for AI agents that turns websites into controllable interfaces for multi-step tasks.
Use Inngest AgentKit to build TypeScript agent networks with deterministic routing, shared state, MCP tools, and local tracing.
Rate-limit-resilient pipeline with checkpoint/resume for long multi-phase sessions. Saves progress to .claude/pipeline-state.json after each phase.
Authors and refactors GitHub Actions workflows and composite actions for this monorepo using required conventions, minimal permissions, pinned SHAs, and observability steps.
Use when you have a GitHub repository with published CI workflow badges (e.g., unit test or package test badges in the README) and need to independently verify that the workflows…
Guide to SGLang CI workflow orchestration — stage ordering, fast-fail, gating, partitioning, execution modes, and debugging CI failures.
You are a workflow automation expert specializing in creating efficient CI/CD pipelines, GitHub Actions workflows, and automated development processes.
Use when setting up or optimizing CI/CD pipelines. Generates GitHub Actions workflow configurations following best practices — matrix builds, caching, artifact management, and…
Orchestrate quality engineering across CI/CD pipeline phases. Use when designing test strategies, planning quality gates, or implementing shift-left/shift-right testing.
Orchestrate quality engineering across CI/CD pipeline phases. Use when designing test strategies, planning quality gates, or implementing shift-left/shift-right testing.
Multi-agent orchestration for Claude Code — automatic task decomposition via Opus 4.6, parallel execution with dependency-aware scheduling, file conflict prevention, quality gate,…
云运维编排器为 AI Agent 提供以基础设施即代码（IaC）为核心的多云运维能力。它明确划分 Terraform（资源生命周期）与 Ansible（系统配置）的职责边界，覆盖
Executes ComfyUI image generation workflows via the /prompt REST API endpoint with WebSocket progress tracking.
Regulatory and legal compliance audit. Discovers which frameworks apply based on jurisdiction, industry, and data types, then checks the codebase against the applicable controls.
Docker and Kubernetes patterns. Triggers on: Dockerfile, docker-compose, kubernetes, k8s, helm, pod, deployment, service, ingress, container, image.
Use when when a software tool is distributed as a Docker image and you need to confirm it is available on a registry (e.g., Docker Hub), that the image pulls without corruption,…
Principles for designing context-efficient AI agents and tools. Use when designing LLM tools, agents, MCP servers, or multi-agent systems.
Entry point for context engineering work. Routes to the right skill based on what the user needs — creating instructions, debugging agent failures, building documentation, or…