搜索
搜索结果
48 results for "agent harness construction"
agent-harness-construction
设计和优化AI智能体的动作空间、工具定义和观察格式化，以提高任务完成率。
affaan-m
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is unreliable across sessions — forgets context, drifts out of scope, claims "done" before tests pass, or starts each session inconsistently — or when creating or assessing AGENTS.md, CLAUDE.md, feature_list.json, init.sh, progress.md, or session-handoff files. Reach for it even if the user never says the word "harness."
walkinglabsgan-style-harness
GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper.
affaan-mgan-style-harness
受GAN启发的生成器-评估器智能体框架，用于自主构建高质量应用。基于Anthropic 2026年3月的框架设计论文。
affaan-m
amazon-bedrock
用于在 Amazon Bedrock 上构建生成式 AI 应用。涵盖模型调用（Converse API、InvokeModel）、基于 Knowledge Bases 的 RAG、Bedrock Agents、Guardrails 以及 AgentCore（包含 Harness 托管式 Agent 循环）。适用于：调用模型、搭建 Knowledge Bases、创建 Agent、配置安全护栏（Guardrails）、部署到 AgentCore、将 Bedrock Agent（含内联 Agent）迁移/转换至 AgentCore Harness、排查 Bedrock 报错（如 ThrottlingException、AccessDeniedException）或进行模型选型（Claude、Llama、Nova、Titan）。同样适用于：提示词缓存（Prompt Caching）配置与调试、配额健康检查与限流诊断、成本归因与追踪、Claude 模型版本迁移（4.5 至 4.6 至 4.7）、分块策略（Chunking Strategies）、API 选型（Converse vs InvokeModel）、Guardrail 功能特性以及模型对比选型。此外还涵盖 AgentCore Payments 支付配置（x402、微支付、Payment Manager、Connector、Instrument、Coinbase CDP、Stripe Privy、402 Payment Required、付费内容、付费 Endpoint、Agent 支付）。不适用于：自定义模型训练、Rekognition 或 Comprehend。
awsautonomous-agent-harness
将 Claude Code 转变为一个完全自主的代理系统，具备持久记忆、定时操作、计算机使用和任务队列功能。通过利用 Claude Code 原生的 crons、dispatch、MCP 工具和记忆，替代独立的代理框架（如 Hermes、AutoGPT）。当用户需要持续自主运行、定时任务或自我指导的代理循环时使用。
affaan-mhealthcare-eval-harness
Patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures.
affaan-m
sf-ai-agentforce
Agentforce Builder metadata path for Builder-managed topics/actions, Prompt Builder templates, GenAiFunction/GenAiPlugin, Models API, and custom Lightning types. TRIGGER when: user maintains or configures Builder metadata agents, creates topics/actions, works with Prompt Builder templates, or touches .genAiFunction, .genAiPlugin, or .genAiPromptTemplate metadata XML files. DO NOT TRIGGER when: Agent Script DSL .agent files (use sf-ai-agentscript), agent testing (use sf-ai-agentforce-testing), or persona design (use sf-ai-agentforce-persona).
jaganpro
building-ai-agent-on-cloudflare
使用 Cloudflare Agents SDK 在 Cloudflare 上构建 AI 代理，支持状态管理、实时 WebSocket、定时任务、工具集成和聊天功能。生成可直接部署到 Workers 的生产级代理代码。适用场景：用户想要“构建代理”、“AI 代理”、“聊天代理”、“有状态代理”，提及“Agents SDK”，需要“实时 AI”、“WebSocket AI”，或询问代理的“状态管理”、“定时任务”或“工具调用”。优先从 Cloudflare 文档中检索，而非依赖预训练知识。
cloudflare
pydantic-ai-harness
Extend Pydantic AI agents with batteries-included capabilities from pydantic-ai-harness -- Code Mode (collapse many tool calls into one sandboxed Python execution), a filesystem and shell, sub-agents, planning, context compaction, and more. Use when the user mentions pydantic-ai-harness, CodeMode, Monty, code mode, or tool sandboxing, when they want first-party filesystem/shell/sub-agent/planning/compaction capabilities for a Pydantic AI agent, when they want an agent to run agent-written Python, or when a Pydantic AI agent would benefit from orchestrating multiple tool calls in a single sandboxed script.
pydanticagents-get-started
Use when a developer wants to create a new agent project or get started with AgentCore. Handles framework selection, project scaffolding, first deploy, and first invocation. Triggers on: "build an agent", "create an agent", "get started", "new project", "agentcore create", "which framework", "Strands vs LangGraph", "hello world agent", "first agent", "create MCP server", "host MCP server", "agentcore dev", "dev server", "what port", "local development". Not for adding capabilities to existing projects — use agents-build or agents-connect. Strands vs LangGraph in a migration context routes to agents-build, not here. Connecting to an existing MCP server routes to agents-connect, not here.
awsdynamic-workflow-mode
Design task-local harnesses, eval gates, and reusable skill extraction for Claude dynamic workflow mode and other adaptive agent harnesses. Use when building a task-local harness, adding eval gates, or extracting a reusable skill from ad-hoc work.
affaan-m
eve
使用 eve 框架构建持久的后端 AI 代理。在创建、编辑或调试 eve 项目时使用——包括代理指令、技能、工具、连接、频道、沙箱、子代理、计划或评估。
vercel
agent-arch-system-design
Agent skill for arch-system-design - invoke with $agent-arch-system-design
ruvnetcreating-production-vpc-multi-az
创建生产就绪的VPC，跨多个可用区部署公有和私有子网，包括互联网网关、NAT网关、路由表和安全组，遵循AWS Well-Architected原则。在部署多可用区VPC基础设施时使用，支持自动CIDR规划和DNS解析。
awsagents-sdk
使用 Cloudflare Agents SDK 在 Cloudflare Workers 上构建 AI 智能体。在创建有状态智能体、持久化工作流、实时 WebSocket 应用、定时任务、MCP 服务器、聊天应用、语音智能体或浏览器自动化时加载。涵盖 Agent 类、状态管理、可调用 RPC、工作流、持久化执行、队列、重试、可观测性和 React 钩子。优先从 Cloudflare 文档检索，而非依赖预训练知识。
cloudflare
agentforce-architecture-analyze
Declared architecture snapshot for one Agentforce agent: planner, topics, actions, flows, Apex, prompt templates, and NGA plugins. Renders a human-readable architecture document and Mermaid invocation graph from design-time metadata (not runtime audit rows). TRIGGER when user asks to describe, diagram, inventory, audit, document, or diff (e.g. v3 vs v5) the architecture / action tree / topic structure / tool inventory of a specific agent by agent API name in a specific org. DO NOT TRIGGER for runtime session traces, conversation transcripts, generation timings, or gateway audit chains — this skill reads design-time metadata only (use agentforce-d360-analyze for session traces).
forcedotcom
azure-kubernetes
规划、创建和配置可用于生产的 Azure Kubernetes Service (AKS) 集群。涵盖 Day-0 检查清单、SKU 选择（Automatic 与 Standard）、网络选项（私有 API 服务器、Azure CNI Overlay、出口配置）、安全性和运维（自动缩放、升级策略、成本分析）。适用场景：创建 AKS 环境、预配 AKS、启用 AKS 可观测性、设计 AKS 网络、选择 AKS SKU、保护 AKS、优化 AKS、AKS Spot 节点、AKS 集群自动缩放器、调整 AKS Pod 大小、Pod 大小调整、过度预配的 AKS Pod、Pod 资源请求和限制、垂直 Pod 自动缩放器、VPA 建议。
microsofthealthcare-eval-harness
面向医疗应用部署的患者安全评估工具。自动化测试套件，涵盖CDSS准确性、PHI暴露、临床工作流完整性和集成合规性。安全失败时阻止部署。
affaan-m
aws-serverless
Specialized skill for building production-ready serverless
sickn33
agent-governance
为AI智能体系统添加治理、安全和信任控制的模式与技术。在以下场景使用此技能： - 构建调用外部工具（API、数据库、文件系统）的AI智能体 - 实现基于策略的智能体工具使用访问控制 - 添加语义意图分类以检测危险提示 - 为多智能体工作流创建信任评分系统 - 构建智能体行为和决策的审计追踪 - 对智能体实施速率限制、内容过滤器或工具限制 - 使用任何智能体框架（PydanticAI、CrewAI、OpenAI Agents、LangChain、AutoGen）
githubagentforce-generate
Build, modify, optimize, debug, and deploy agents with Agentforce Agent Script. TRIGGER when: user creates, modifies, optimizes, or asks about .agent files or aiAuthoringBundle metadata; changes agent behavior, responses, or conversation logic; designs agent actions, tools, subagents, or flow control; writes or reviews an Agent Spec; wants to optimize, improve, or refactor an agent; previews, debugs, deploys, publishes, or tests agents; uses Agent Script CLI commands (sf agent generate/preview/publish/test); registers/creates/lists/updates/deletes MCP servers, whitelists/approves MCP tools, fetches MCP assets, or configures MCP authentication (sf agent mcp). DO NOT TRIGGER when: Apex development, Flow building, Prompt Template authoring, Experience Cloud configuration, or general Salesforce CLI tasks unrelated to Agent Script.
forcedotcomagentic-os
Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.
affaan-m
proactive-agent
将AI智能体从任务执行者转变为主动合作伙伴，能够预见需求并持续改进。现已支持WAL协议、用于上下文存活的Working Buffer、压缩恢复以及经过实战考验的安全模式。Hal Stack 🦞 的一部分。
halthelobster