搜索

building-ai-agent-on-cloudflare

2.5Kresearch-knowledge

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

获取

videoagent-audio-studio

751mcp-integrations

厌倦了管理多个音频API？此技能让你通过一条命令即可访问TTS、音乐生成、音效和语音克隆。当你想要生成任何音频而无需管理多个API密钥时使用。

pexoai

获取

videoagent-image-studio

748design-ui

厌倦了管理8个API密钥？这个技能让你通过一条命令就能访问Midjourney、Flux、Ideogram等模型，无需任何设置。当你想要生成任何图像而又不想操心API密钥时，请使用此技能。

pexoai

获取

videoagent-video-studio

745backend-api

从文本或图像生成AI短视频——文本转视频、图像转视频及基于参考的生成，无需设置API密钥。当用户想要创建视频片段、为图像添加动画或根据描述生成视频时使用。

pexoai

获取

pexo-agent

736agent-workflows

AI视频生成技能，自动选择Seedance 2、Kling 3.0、HappyHorse等10+模型。从文本、图片、URL、脚本或音频生成完整的多镜头视频（5–120秒），包括AI音乐、口型同步和多镜头序列。无需编写提示词，无需选择模型。用途：视频制作、AI视频、制作视频、产品视频、品牌视频、宣传片、解说视频、短视频、TikTok视频、Instagram Reel、YouTube Short、产品广告、文生视频、图生视频、视频生成、AI视频代理。

pexoai

获取

godot-master

453design-ui

Consolidated expert library for professional Godot 4.7+ game and application development. Orchestrates 92 Domain Skills through architectural workflows, anti-pattern catalogs, performance budgets, and Server API patterns. Use when: (1) starting a new Godot project, (2) designing game or app architecture, (3) building entity/component systems, (4) debugging performance or physics issues, (5) choosing between 2D/3D approaches, (6) implementing multiplayer, (7) optimizing draw calls or script time, (8) porting between platforms, (9) migrating from 4.6 to 4.7. Primary entry point for ALL Godot development tasks. Keywords: Godot 4.7, AreaLight3D, HDR, Asset Store, godot-master.

thedivergentai

获取

firebase-ai-logic-basics

357backend-api

将 Firebase AI Logic（Gemini API）集成到 Web 应用中的官方技能。涵盖设置、多模态推理、结构化输出和安全性。

firebase

获取

ai-agent-builder

316research-knowledge

使用工具、记忆和多步推理构建AI智能体——ChatGPT、Claude、Gemini集成模式

claude-office-skills

获取

okx-agent-payments-protocol

314research-knowledge

Use when an agent hits HTTP 402 / payment-required, or the user mentions x402, x402Version, X-PAYMENT, PAYMENT-REQUIRED, PAYMENT-SIGNATURE, WWW-Authenticate: Payment, permit2, upto, metered billing, a payment channel / voucher / session, channelId / channel_id, opening / closing / topping up / settling / refunding a channel, a paymentId or a2a_ link, creating / checking a payment link, A2MCP / an A2MCP endpoint, or sending a request to / calling an Agent's endpoint with a concrete endpoint URL. Covers x402 (exact, exact+Permit2, upto, aggr_deferred), MPP (charge / session), and a2a-pay paymentId flows. Any close / topup / settle / voucher / refund near a channel_id or session is an MPP mid-session op. The full bilingual trigger list (including Chinese) lives in the skill body.

okx

获取

okx-agentic-wallet

312security

OKX Agentic Wallet — 用户钱包与链上执行的单一技能。当用户希望操作钱包或执行链上操作时使用，包括：登录与账户、余额/持仓、钱包地址/充值/收款、发送/转账、合约调用（授权/存款/提现）、交易历史与状态、消息签名、钱包导出与策略；使用稳定币支付Gas（Gas Station，Solana）；兑换/交易/买入/卖出/转换、获取报价；跨链桥接与到账跟踪；限价单（抄底/止盈/止损/追涨）及取消/列表/恢复；广播/估算Gas/模拟/跟踪交易；查询任意公开地址的持仓；安全扫描（代币/蜜罐/貔貅、DApp钓鱼、交易与签名检查、授权）；审计日志。一旦匹配，遵循本技能的意图路由分发到具体操作。

okx

获取

owasp-security

257security

遵循 OWASP Top 10 实施安全编码实践。用于预防安全漏洞、实现身份验证、保护 API 或进行安全审查。触发词：OWASP、安全、XSS、SQL 注入、CSRF、身份验证安全、安全编码、漏洞。

hoodini

获取

github-trending

256frontend

获取并显示 GitHub 趋势仓库和开发者。用于构建展示趋势仓库的仪表盘、发现热门项目或跟踪 GitHub 趋势。触发词：GitHub 趋势、趋势仓库、热门仓库、GitHub 发现。

hoodini

获取

mongodb-search-and-ai

164research-knowledge

指导 MongoDB 用户实施和优化 Atlas Search（全文搜索）、Vector Search（语义搜索）和 Hybrid Search（混合搜索）解决方案。当用户需要构建基于文本的查询（自动补全、模糊匹配、分面搜索）、语义相似度（嵌入、RAG 应用）或组合方法时使用此技能。当用户需要文本包含、子串匹配（'contains'、'includes'、'appears in'）、不区分大小写或多字段文本搜索，或跨多个字段进行可变组合过滤时也使用此技能。提供选择正确搜索类型、创建索引、构建查询以及使用 MongoDB MCP 服务器优化性能的工作流程。

mongodb

获取

agent-email-inbox

148security

在构建任何由邮件内容触发动作的系统时使用——AI代理收件箱、自动支持处理程序、邮件转任务管道，或任何处理不可信入站邮件的工作流。当用户希望以编程方式接收邮件并对其执行操作时，始终使用此技能，即使他们未提及“代理”——该技能包含关键安全模式（发件人白名单、内容过滤、沙箱处理），可防止不可信邮件控制您的系统。

resend

获取

building-pydantic-ai-agents

114testing-qa

Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydantic_ai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents from YAML, or test agent behavior.

pydantic

获取

magicpath

83design-ui

Use MagicPath through the magicpath-ai CLI to find, preview, inspect, install, export, create, and edit UI components and manage MagicPath skills. Trigger for MagicPath designs/components; personal or team projects; active canvases and selected components/images/revisions; themes/design systems; teams, members, ownership, attribution, installed-component audits, and share/view links. Use when exporting exact MagicPath components or revisions to local folders/apps; replacing, adapting, or translating local UI with 1:1 fidelity and explicit requested changes; installing React/TypeScript components with inspect/add; authoring responsive interactive canvas components with code start/submit; importing or recreating UI from local paths or GitHub/GitLab/Bitbucket repositories into MagicPath; or creating, retrieving, updating, importing, enabling, disabling, or deleting MagicPath skills. In hosts with an embedded browser, keep the project canvas open via share URLs for visual work.

magicpathai

获取

claimable-postgres

82database

Provision instant temporary Postgres databases via Claimable Postgres by Neon (neon.new) with no login, signup, or credit card. Supports REST API, CLI, and SDK. Use when users ask for a quick Postgres environment, a throwaway DATABASE_URL for prototyping/tests, or "just give me a DB now". Triggers include: "quick postgres", "temporary postgres", "no signup database", "no credit card database", "instant DATABASE_URL", "npx neon-new", "neon.new", "neon.new API", "claimable postgres API".

neondatabase

获取

ci-cd-security

76security

扫描 GitHub Actions 工作流文件中的安全漏洞，通过直接读取 YAML 并报告发现结果——无需外部工具、无需安装、无需执行 shell 命令。当用户分享 `.github/workflows/` 文件、粘贴工作流 YAML、请求 CI/CD 安全审查、提及 `pull_request_target`、`workflow_run`、操作固定、`GITHUB_TOKEN` 权限、pwn 请求、模板注入、缓存投毒、秘密泄露、供应链风险或任何 GitHub Actions 加固主题时，使用此技能。当用户正在加固开源仓库、进行 CI/CD 红队评估、评估供应链扫描目标或公开撰写 CI/CD 安全相关内容时，也触发此技能。倾向于触发此技能而非凭记忆回答——CI/CD 安全默认值几乎在所有地方都是错误的，且规则不直观。

superagent-ai

获取

skill-security

76backend-api

在安装或信任AI智能体技能之前，审计其安全风险。运行确定性扫描器（正则模式、Python AST分析、源到汇污点追踪和YARA签名），然后推理意图——捕获提示注入、凭证窃取、持久化、内存投毒、恶意代码、供应链风险以及描述与行为不匹配。确保在用户想要扫描、审计、审查或检查技能、插件、SKILL.md或智能体工具的安全性时使用此技能——无论是本地文件夹、zip/.skill文件还是克隆的仓库——以及当有人问“这个技能安装安全吗？”时。

superagent-ai

获取

tailwind-4-docs

57research-knowledge

全面的 Tailwind CSS v4 文档快照与工作流指南。用于回答 Tailwind v4 相关问题、选择工具类/变体、配置 Tailwind v4，或借助官方文档和常见陷阱检查将项目从 v3 迁移到 v4。

lombiq

获取

convex-explain-app

42mcp-integrations

Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.

get-convex

获取

convex-domains

42devops-cloud

Point a domain you already own at your Convex app (DNS records, custom-domain attach, auth-origin rebind).

get-convex

获取

multi-agent-orchestration

39research-knowledge

Design and coordinate multi-agent systems where specialized agents work together to solve complex problems. Covers agent communication, task delegation, workflow orchestration, and result aggregation. Use when building coordinated agent teams, complex workflows, or systems requiring specialized expertise across domains.

qodex-ai

获取

word-document-processor

35writing-content

全面的 Word 文档处理，支持完整格式。涵盖创建、编辑、格式保留、修订跟踪和元数据管理。

qodex-ai

获取