В каталоге 182 820 навыков в 14 категориях.
Psychrometric Analysis Agent
Quality Assurance & Design Validation Agent
Coil Selection & Thermal Design Agent
Godot AI developer — use when implementing NPC pathfinding, NavigationAgent3D, behavior state machines, or detection sys...
Use when calling the app's AI gateway from agent tools — chat completions, embeddings, listing models, configuring defau...
扮演人工智能辅助医生，结合最新AI工具（如医学成像、机器学习）和传统方法（如体检、实验室测试）来诊断病人症状的最可能原因。
Cheat sheet for AI tools including GEMINI and CODEX configurations.
Master AI, machine learning, LLMs, prompt engineering, and blockchain development. Use when building AI applications, wo...
Use when working with AI agent protocols, standards, and interoperability specifications. Covers MCP, A2A, ACP, Agent Sk...
AI Agent stack: Hermes Agent (self-improving AI assistant) routed through in-cluster LiteLLM proxy with OpenRouter fallb...
LLM and AI application security testing — prompt injection, jailbreak resistance, OWASP LLM Top 10 (2025), RAG and agent...
Comprehensive evaluation patterns for AI agents including multi-turn conversation testing, LLM-as-judge frameworks, benc...
Pre-flight check for GPU cluster nodes — node validation before training, check cluster node health, is my GPU node read...
Implements ML models, embeddings, and AI-powered features with ethical considerations
AI video and image prompt engineering — video generation, image generation, product video, social media video, cinematic...
当用户搜索 360商品旋转、商品转台、产品环绕动图、360主图、电商图片、商品视频、AIGC营销、淘宝、京东、抖音、小红书、Amazon、Shopify、AI-HIVE MCP 时使用。帮助商家完成用参考图规划商品旋转展示：先锁定SKU与授...
为由结构、空间、装配、剖面或材料机理主导的段落或单镜头提供专业视觉策略、资产证据和动态约束，支持独立任务及与抽象创意、实景合成、VFX 的组合路由；被总导演选中时必须回写独立专业贡献和 PASS／REVISE／BLOCKED，不接管其他媒介...
A/B 测试设计助手适合市场营销、产品、运营、software在用户提出“这个改动值得测吗”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成转化问题优先级、可复制改稿、实验或跟进行动清单。
Use this skill when staff already use AI assistants, coding tools or AI features and the company needs rules people will...
无障碍体验诊断助手适合内容创作者、市场营销、运营、内容媒体在用户提出“这个页面好用吗”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成问题归因、服务改进建议、SOP 或 FAQ 清单。
Designs absolute guardrails and grounds AI outputs against a named source of truth to counter sycophancy and hallucinati...
Check construction AI systems against the EU AI Act (Regulation 2024/1689): classify risk of estimation, scheduling, CV...
/compliance-os:ai-act-readiness [system] — EU AI Act 6-question forcing interrogation. Use during AI-system intake, befo...
Use this skill when a company must work out where each of its AI systems sits under the EU AI Act, and asks "is this hig...
AI 影视演员表演推理与提示词编译系统。将简单粗糙的人物动作与情绪形容词升级为具有戏剧逻辑、深层心理动机、阻碍策略、潜台词博弈、镜头景别克制以及跨镜头连续性的专业影视表演指令，并自动编译为适配 Kling、Veo、Runway、Sora 等...
<name>ai-ad-api-automation-test</name>
后端代码生成 Skill，负责在 SoT 约束下生成 FastAPI 后端代码。
──────────────────────────────────────────────
══════════════════════════════════════════════════════════════════
Turns an AI video ad into a compliance report for TikTok Shop, TikTok ads, Meta, YouTube, the FTC, New York's synthetic-...
广告创意诊断助手适合technical、产品、市场营销、software在用户提出“这条广告会被点吗”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成创意诊断、卖点强化建议、迭代方向。
前端代码生成 Skill，负责在 SoT 约束下生成 Next.js/React 前端代码。
<skill>
══════════════════════════════════════════════════════════════════════
你是一个 严格可控的 SoT 文档流水线执行器（Pipeline Runner）：
<name>ai-ad-spec-kit</name>
测试用例生成 Skill，负责根据 SoT 文档和业务代码生成 pytest 测试用例。
Use this skill when creators, video editors, advertisers, e-commerce teams, social-commerce teams, and short-form story...
AI自适应学习 (AI Adaptive Learning) Master OS — automated mastery of AI Adaptive Learning: top builders' mental models, tool...
Creates a multi-tab analytics dashboard for tracking AI tool adoption across your engineering organization. Includes exe...
Create AI adoption and change-management plans for teams and organizations. Use when Codex is asked to plan AI rollout,...
A structured assessment framework that scores your organization across five critical dimensions of AI readiness. Produce...
Develop research-backed AI competitive strategies combining academic research, market trends, and social sentiment analy...
Write, wire and test an in-process AI agent with @guren/plugin-ai (an Agent class that calls a language model and reache...
Build AI agents with tools, memory, and multi-step reasoning - ChatGPT, Claude, Gemini integration patterns
AI tooling: write/merge/audit skills and plugins, package safety, MCP servers, ChatGPT apps, model choice, context budge...
Structure and write design case studies for AI agents, copilots, autonomous workflows, multi-agent systems, and other pr...
企业/高校承接 AI 智能体项目时出方案、报价、demo 的全流程。
**Domain**: AI/ML Architecture
AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI,...
Build production-ready AI agents with Microsoft Foundry and Agent Framework. Use when creating AI agents, selecting LLM...
Design, implement, and evaluate tool-using AI agents with explicit authority, typed tools, bounded loops, state, observa...
Implement the 4 Pillars Framework for AI agent governance (Lifecycle, Risk, Security, Observability). Use when deploying...
Apply safety controls when an LLM agent has authority to act on real systems. Covers blast-radius classification, dry-ru...
Review AI agent systems for agent impersonation, capability escalation, missing agent identity primitives, and authoriza...
Step-by-step checklist and best practices for implementing new AI agent tools in the omer-akben portfolio. Use when crea...
Orchestrate multiple AI agents for construction workflows: estimator, scheduler, document, QA and safety agents coordina...
Эксперт по оркестрации AI агентов. Используй для multi-agent systems, agent coordination, task delegation и agent workfl...
Advanced guide for developing and orchestrating AI agents using LangChain, LangGraph, and Swarm patterns. Covers memory...
Orchestrates multi-agent AI systems with task delegation, agent communication, shared memory, and workflow coordination....
Add GitHub-visible AI agent and AI code-review metadata and exact agent labels without adding AI attribution to commits,...
Better proposals, faster closes. Use when creating AI agent pricing, automation proposals, ROI calculations, or sales ma...
Use when red-teaming an agentic AI / LLM application — indirect & zero-click prompt injection, MCP tool poisoning, persi...
Make an AI agent or automation reliable enough to trust — the tests, checks, and guardrails that catch its failures befo...
Route AI agent engineering prompts to architecture, orchestration, evaluation, safety, debugging, context, prompt, MCP,...
Secure AI agents against prompt injection, tool abuse, and data exfiltration with defense-in-depth controls.
Here’s a complete breakdown of how to configure and set up the Scoring Skill in raiaAI’s Launch Pad. This skill allows y...
The Escalation Skill ensures that critical user requests are addressed quickly and accurately by enabling seamless escal...
Update skills installed FROM THE AI-Agent-skills GitHub REPO (github.com/whobat/AI-Agent-skills) to their latest publish...
Use this skill when you need to test AI agent goals, state, planning, recovery, and safety boundaries; triggers include...
Abuse an LLM agent's tools/functions — coerce it to call tools with attacker-chosen args for SSRF, RCE, data exfil, or p...
Comprehensive L&D framework for upskilling DevOps/IaC/Automation teams to become AI Agent Engineers. Covers LLM literacy...
Production-grade AI agent patterns with MCP integration, agentic RAG, handoff orchestration, multi-layer guardrails, and...
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-...
I build AI systems that can act autonomously while remaining controllable. I understand that agents fail in unexpected w...
Builds and implements AI agents, automation workflows, and tool integrations — MCP servers (2025 async, OAuth, stateless...
Command-line tools that delegate analysis tasks to AI models. Includes image description, screenshot comparison, essay g...
Use when Claude Code permissions have accumulated in settings.local.json and you want to audit, consolidate, or clean up...
AI驱动的综合健康分析系统，整合多维度健康数据、识别异常模式、预测健康风险、提供个性化建议。支持智能问答和AI健康报告生成。
Эксперт по data annotation. Используй для ML labeling, annotation workflows и quality control.
Ask Claude, ChatGPT, and Gemini a question and capture the full trace behind the answer (the search queries each engine...
当想知道一段 AI 回答"哪些能直接用、哪些必须先验证、哪些只能当建议"时使用。按声明类型分四级——低风险草稿材料、观点与策略建议、可查证的事实声明、会改变状态的可执行指令——每级配一句默认处置动作；再按影响半径排序，给出最小的下一步检查。...
This skill should be used when reviewing AI-generated text, checking for AI writing patterns, detecting undisclosed AI c...
How to use AI APIs like OpenAI, ChatGPT, Elevenlabs, etc. When a user asks you to make an app that requires an AI API, u...
Full-stack AI application generator. Use when creating chatbots, agent dashboards, or custom AI applications with Next.j...
Use when an LLM, RAG, agent, chatbot, copilot, extraction, classification, generation, or prompt/model change needs a ri...
Assess the approaches for an AI feature — prompt only, retrieval over the team's content, tool use or a multi-step agent...
Designs the outbound AI ports of an already-scoped use case — a language model asked for a structured answer (classify,...