“protocol”的搜索结果

Designs and audits closed, ordered, replay-safe message protocols between already admitted agent bodies. Use when a multi-agent exchange needs explicit epochs, audiences, per-sender sequencing, gathers, terminal fences, acknowledgements, and deterministic replay. NOT for selecting or spawning agents, granting identity or authority, choosing a runtime topology, general human facilitation, wire transport implementation, or deciding whether evidence is true.

中文简介正在准备中。当前显示原文说明。

Data structures and serialization formats for agent-to-agent communication. Covers message envelopes, structured output schemas, capability declarations, task handoff payloads, error/retry signaling, and context windows as data structures. Compares the version-pinned A2A, MCP, and JSON-RPC role boundaries covered by this bundle; OpenAI and LangChain-specific APIs require their own current sources. Teaches when to use rigid schemas versus free-form content with validation, typed versus untyped boundaries, and streaming versus batch. Activate on: "agent message format", "agent communication schema", "agent-to-agent protocol", "A2A protocol", "MCP message format", "structured output for agents", "agent interop", "interchange format", "agent serialization", "task handoff format", "capability declaration". NOT for: what agents say to each other (use agent-conversation-protocols), orchestration topology (use multi-agent-coordination), building agent infrastructure (use agentic-infrastructure-2026).

中文简介正在准备中。当前显示原文说明。

Agent-to-Agent (A2A) protocol implementation patterns for Google ADK - exposing agents via A2A, consuming external agents, multi-agent communication, and protocol configuration. Use when building multi-agent systems, implementing A2A protocol, exposing agents as services, consuming remote agents, configuring agent cards, or when user mentions A2A, agent-to-agent, multi-agent collaboration, remote agents, or agent orchestration.

中文简介正在准备中。当前显示原文说明。

Integration patterns for combining Agent-to-Agent (A2A) Protocol with Model Context Protocol (MCP) for hybrid agent communication. Use when building systems that need both agent-to-agent communication and agent-to-tool integration, implementing composite architectures, or when user mentions A2A+MCP integration, hybrid protocols, or multi-agent tool access.

中文简介正在准备中。当前显示原文说明。

Interactive guide for integrating new DeFi modules or protocols into OneKey. Use when adding new DeFi features like staking protocols, lending markets, or entirely new DeFi modules. Triggers on DeFi, protocol, integration, Earn, Borrow, staking, lending, supply, borrow, withdraw, repay, claim, new module, Pendle, Aave, Compound.

中文简介正在准备中。当前显示原文说明。

Protocol-based dependency injection for testable Swift code — mock file system, network, and external APIs using focused protocols and Swift Testing.

中文简介正在准备中。当前显示原文说明。

Detect command injection attacks against Modbus TCP/RTU protocol in ICS environments by monitoring for unauthorized write operations, anomalous function codes, malformed frames, and deviations from established communication baselines using ICS-aware IDS and protocol deep packet inspection.

中文简介正在准备中。当前显示原文说明。

This skill covers detecting anomalies in Modbus/TCP and Modbus RTU communications in industrial control systems. It addresses function code monitoring, register range validation, timing analysis, unauthorized client detection, and deep packet inspection for malformed Modbus frames. The skill leverages Zeek with Modbus protocol analyzers, Suricata IDS with OT rules, and custom Python-based detection using Markov chain models for normal Modbus transaction sequences.

中文简介正在准备中。当前显示原文说明。

帮助应用迁移到Swift 6.2并设计并发代码，通过MainActor保护共享状态，解决数据竞争编译错误，梳理协议遵循，并将高负载计算显式移至后台执行。

• 将现有应用迁移到Swift 6.2
• 解决数据竞争编译错误
• 将高负载计算移至后台

先确定前后端或服务间共享的API与事件数据规范，再生成类型，并按同一规范验证测试数据和实际响应，通过共同审查变更，减少并行开发中的字段偏差与兼容性问题。

• 并行开发前端和后端
• 统一服务间的API与事件格式
• 核对模拟响应与生产响应

这是使用mcp-use设计MCP服务器操作、数据资源、可复用提示词及交互界面的旧指南。该技能已弃用，并指引用户迁移至mcp-app-builder。

• 理解现有mcp-use服务器结构
• 查阅Tool、Resource和Prompt示例
• 查看交互式Widget设计

为Paperclip Runner添加或扩展行为评估，定义判定条件、执行目标和报告验证数据，利用正常及异常证据验证结果，并保留执行记录与费用。

• 添加Runner行为评估
• 用有效与无效证据检验判定
• 更新执行列表和持续评估

Use the command line to send tasks to OmniRoute's A2A server, which supports communication between agents. Inspect execution history and logs, monitor or cancel tasks, and interactively test the JSON-RPC 2.0 communication protocol.

中文简介正在准备中。当前显示英语简介。

• Check server status and available skills
• Invoke a skill with JSON input
• Inspect task history and logs

Query OmniRoute through A2A, a protocol for communication between agents. Get provider and model recommendations, check remaining quotas, find providers with required features, estimate request costs, and review system health.

中文简介正在准备中。当前显示英语简介。

• Find a provider and model for a prompt
• Check remaining provider or account quotas
• Find providers with required features

Plan study sample sizes, estimate statistical power—the chance of detecting an assumed effect—and find the smallest detectable effect. Supports standard tests and simulations for complex designs, with sensitivity analyses and sample size justifications.

中文简介正在准备中。当前显示英语简介。

• Estimating participant or sample counts before data collection
• Finding the smallest effect detectable with a fixed sample
• Preparing sample size justifications for grants or protocols

Prepare constructive review drafts for scientific manuscripts, protocols, preprints, and proposals. Organize checks of claims, evidence, methods, statistics, reproducibility, ethics, figures, and citations into specific comments that a responsible human reviewer can verify and revise.

中文简介正在准备中。当前显示英语简介。

• Draft evidence-based comments on a scientific manuscript
• Check methods, statistics, and reproducibility reporting
• Choose reporting guidelines and identify missing information

Automate Electron desktop apps with agent-browser through CDP, a browser debugging connection. Click controls, enter text, extract content, and capture screenshots while switching between app windows or embedded pages for routine work and testing.

中文简介正在准备中。当前显示英语简介。

• Automating clicks and form entry in desktop apps
• Extracting text and screen information from apps
• Capturing screenshots for application testing

Plan and build an MCP server, a connection that lets Claude use external tools. Choose hosting, tool structure, authentication, and a framework, then scaffold a server or hand off to specialized packaging and interface skills.

中文简介正在准备中。当前显示英语简介。

• Connect a cloud API to Claude
• Choose how to run and distribute an MCP server
• Organize tools for an API with many actions

Set communication rules for teams of AI agents. The skill explains when to use direct messages or broadcasts, how leads review plans, how teammates shut down safely, and how to troubleshoot stalled handoffs or missing communication tools.

中文简介正在准备中。当前显示英语简介。

• Establishing communication rules for a new agent team
• Choosing direct messages or team-wide broadcasts
• Reviewing and approving a teammate's work plan

Build and troubleshoot MCP servers, which connect AI agents to external tools, for codewhale. Covers local and remote connections, credential configuration, tool validation, and testing both successful requests and failures.

中文简介正在准备中。当前显示英语简介。

• Building an MCP server for a local tool
• Connecting codewhale to a remote service
• Configuring credentials and connection headers

Review source code for MCP, a protocol connecting AI applications to tools. Check authentication, input validation, unsafe execution, and other security risks, then report findings with file and line references and separate manual follow-ups.

中文简介正在准备中。当前显示英语简介。

• Reviewing an MCP server before release
• Checking authentication and validation on a network-exposed server
• Auditing tool code for unsafe execution paths

Use the command line to discover and run tools on MCP servers, which connect agents to external systems. Inspect required inputs, pass JSON arguments, and retrieve results as JSON or raw text for scripts.

中文简介正在准备中。当前显示英语简介。

• Listing available MCP servers and tools
• Searching for tools by name
• Checking tool inputs before calling an external API

Build a Java MCP server, a service that lets AI agents call Java code, APIs, or databases. The skill prepares a Maven or Gradle project, implements tools, adds tests, and configures client connections.

中文简介正在准备中。当前显示英语简介。

• Expose existing Java code to AI agents
• Connect agents to APIs or databases
• Build an MCP server in Spring Boot

Build web apps connecting a CopilotKit React interface to agents hosted in Microsoft Foundry. Covers AG-UI, the communication protocol between them, plus tool approvals, conversation history, shared state, deployment, debugging, and dependency upgrades.

中文简介正在准备中。当前显示英语简介。

• Build a chat interface for a Foundry hosted agent
• Add approval screens for agent tool execution
• Investigate failures across the agent and web interface