anthropics/skills180kfrontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
前端开发
Create, inspect, and safely update project-scoped ReachAI Agents; edit and publish Supervisor config drafts; discover published bindable Skills; and attach or detach exact Skill versions through the Agent AI Coding REST API. Use when an AI coding tool is asked to add an Agent, configure its model or prompt, bind a Skill, remove a Skill binding, or attach a published Workflow as a Tool.
把这段话发给 Claude Code、Codex 或 Cursor。智能体会先检查安全性,你确认后才安装。
读取 https://funcoding.ai/skills/w8123/enterpriseagentframework/agent-ai-coding/install.md ,按里面的步骤帮我安装这个 Skill。
通过项目级 AI Coding 凭据完成受约束的 Agent 编排,不直接调用控制台 /api/agents/** 或 /api/skills/**,不直接写 runtime_agent、runtime_agent_config_version 或 Agent Skill 绑定表。
认证方式:每次请求都发送 X-ReachAI-AiCoding-Key。该 Key 只放在请求头,不得写入 URL、生成代码、日志、浏览器运行时代码或仓库文件。API Base URL 和 projectId 必须来自当前项目 handoff 或 GET /api/ai-coding/projects/{projectId}/manifest,不要猜测。
凡是 Agent 名称、描述、System Prompt、审计说明和返回给业务用户的内容,默认使用清晰的简体中文;keySlug、ID、枚举、路径和协议字段保持原样。
projectId 与 projectCode 同时匹配的 Agent。visibility=PROJECT;不能通过 AI Coding 改写项目归属、keySlug、可见性或内部 ID。PUBLISHED Skill 版本。可绑定范围为 PUBLIC、SHARED,或当前同项目的 PROJECT Skill;PRIVATE Skill 永远不可发现、不可绑定。scriptPolicy=DENY。不能申请或伪造 SANDBOX_REVIEWED,也不能批准脚本执行。AGENT_A2A_REQUIRES_CONSOLE 时转交控制台人工处理。enabled=false。GET /api/ai-assist/skills/agent-ai-coding/latest.zip。GET /api/ai-coding/projects/{projectId}/manifest。GET /api/ai-coding/projects/{projectId}/agents。mutableBase.configVersionId。若已有 DRAFT,后续写请求必须显式携带该 DRAFT id;不要覆盖未读草稿。publish=false,完成全部修改后再显式发布 DRAFT。GET /api/ai-coding/projects/{projectId}/agents
GET /api/ai-coding/projects/{projectId}/agents/{agentId}
第二个接口返回 agent、configVersions 和 mutableBase。必须用真实返回的内部 agent.id 调用后续 Agent authoring 接口。
POST /api/ai-coding/projects/{projectId}/agents
Content-Type: application/json
{
"keySlug": "orders-assistant",
"name": "订单助手",
"description": "处理订单查询与协作任务",
"enabled": true,
"allowedRoles": ["ORDER_OPERATOR"],
"supervisorConfig": {
"modelInstanceId": "从平台返回值中选择的 ACTIVE LLM id",
"systemPrompt": "你是订单助手,只使用已允许的 Skill 和 Workflow。",
"maxPlanSteps": 6,
"maxWorkflowCalls": 4,
"maxReplans": 2,
"policyProfile": "DEV_ALLOW_ALL"
},
"activate": true,
"requestedBy": "Codex"
}
modelInstanceId 必须是 ACTIVE LLM;省略时平台选择第一个可用 ACTIVE LLM。默认 activate=true,创建后立即得到 ACTIVE AgentScope Supervisor 配置。不要为占位而创建空 Workflow。
PUT /api/ai-coding/projects/{projectId}/agents/{agentId}
只允许 name、description、enabled、allowedRoles。不允许发送 projectId、projectCode、keySlug、visibility、activeConfigVersionId 或其他受保护字段。
PUT /api/ai-coding/projects/{projectId}/agents/{agentId}/config/draft
{
"baseConfigVersionId": 101,
"systemPrompt": "更新后的系统提示词",
"modelInstanceId": "active-llm-id",
"maxPlanSteps": 8,
"maxWorkflowCalls": 5,
"maxReplans": 2,
"totalTimeoutMs": 120000,
"workflowTimeoutMs": 60000,
"pageBridgeTimeoutMs": 30000,
"parallelReadOnly": true,
"policyProfile": "DEV_ALLOW_ALL",
"config": {"purpose": "orders"}
}
只发送需要修改的字段。baseConfigVersionId 来自最新 Agent context;当 mutable base 是未发布 DRAFT 时必须提供。AGENT_DRAFT_CONFLICT 或 AGENT_CONFIG_BASE_CONFLICT 表示先重新读取上下文,不能盲目重试。
POST /api/ai-coding/projects/{projectId}/agents/{agentId}/config/publish
{
"configVersionId": 102,
"requestedBy": "Codex"
}
只允许发布当前 Agent 的 DRAFT。发布前平台会重新证明所有 Skill 仍为可绑定的 PUBLISHED 精确版本,并再次拒绝脚本批准和 A2A 远程绑定。
GET /api/ai-coding/projects/{projectId}/agent-skills/bindable?search={optional}
从 bindings[].skill.id 和 bindings[].version.id 选择精确组合。不要从名称推断 ID,不要绑定未出现在该响应中的版本。响应 scriptPolicy 固定为 DENY。
POST /api/ai-coding/projects/{projectId}/agents/{agentId}/skills/attach
{
"skillId": 11,
"skillVersionId": 21,
"baseConfigVersionId": 101,
"activationMode": "MODEL_SELECTED",
"required": false,
"enabled": true,
"publish": true,
"requestedBy": "Codex"
}
默认 activationMode=MODEL_SELECTED、required=false、enabled=true、publish=true。同一 skillId 已存在时会替换成请求的精确版本;完全相同的 ACTIVE 绑定会幂等复用。请求中不要发送 scriptPolicy,平台固定使用 DENY。
POST /api/ai-coding/projects/{projectId}/agents/{agentId}/skills/detach
{
"skillId": 11,
"baseConfigVersionId": 102,
"publish": true,
"requestedBy": "Codex"
}
该操作只移除当前 Agent 配置中的绑定,不删除 Skill 包。目标不存在时幂等返回 removed=false。
POST /api/ai-coding/projects/{projectId}/agent-supervisor/workflow-tools/attach
发送已发布 workflowId,可选使用目标 Agent 的 agentKeySlug 或 agentId。添加默认是增量操作;只有明确替换一个已附加的前序 Workflow 时才发送精确 replaceWorkflowId。Workflow GraphSpec 的创建、修改、验证和发布遵循 workflow-ai-coding Skill。
Agent authoring 错误使用 agent-ai-coding-error.v1,至少包含 code、message、requestId 和可选 details。401 表示缺少 Key;403 表示 Key 无效、已停用或越过项目/Skill 可见性边界;409 通常表示草稿基线冲突、状态冲突或必须转人工控制台。
完成前至少回读一次 Agent context,并报告:Agent id/keySlug、ACTIVE configVersionId、绑定的 Skill id/version、Workflow Tool 列表、是否发布,以及未执行的运行时或业务验收。只有 HTTP 写入成功但未回读时,不要宣称闭环完成。
anthropics/skills180kGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
前端开发
anthropics/skills180kSuite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
前端开发
addyosmani/agent-skills103kGuides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
前端开发
addyosmani/agent-skills103kBuilds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.
前端开发
addyosmani/agent-skills103kOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
前端开发
nexu-io/open-design100kOpenDesign's feature business case for the plugin marketplace: the user pain, options, tradeoffs, and the measure of success. Built as a decision-grade product management deck for PM, eng, design, leadership.
前端开发