В каталоге 182 820 навыков в 14 категориях.
Expert AI/ML engineer specializing in machine learning model development, deployment, and integration into production sy...
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimo...
Professional Ai Engineer skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.
Production-grade AI engineering for LLM applications, RAG systems, and agent architectures. Use when building AI feature...
Use when building or improving LLM features, RAG systems, or AI agents; Designing production AI architectures and model...
Topic-agnostic research AI engineer for ANY new subject. Use when: starting research on a new/unfamiliar topic, running...
Expert AI/LLM engineering guidance. Use when the user asks about RAG, OpenAI, Azure OpenAI, prompt engineering, AI agent...
Principal AI Architect and Machine Learning Engineer.
MASTER AI: LLM Apps, Advanced RAG, Agents (ReAct/Plan), Prompting (CoT/Few-shot), LangGraph, VectorDBs, RAGAS Eval. Use...
Use when building production LLM applications — designing RAG pipelines, choosing vector databases, implementing agent o...
LLM application and RAG system specialist. Use PROACTIVELY for LLM integrations, RAG pipelines, vector search, agent orc...
You are an AI engineer specializing in production-grade LLM applications, generative AI systems, and intelligent agent a...
Build production-ready LLM applications, RAG systems, and intelligent agents. Use when implementing AI features, chatbot...
LLM integration, prompt engineering, RAG pipelines, agent frameworks, and AI system design
Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API int...
Expert-level AI implementation, deployment, LLM integration, and production AI systems
Builds a weekly reading list of the most-upvoted daily.dev posts on LLM inference, RAG and AI agents, saves them to a da...
Expert in building comprehensive AI systems, integrating LLMs, RAG architectures, and autonomous agents into production...
Framework for the 8 stages of AI engineering maturity (team and organization view). Based on the Upsun article by Fabien...
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipel...
实体优化助手适合内容创作者、市场营销、运营、内容媒体在用户提出“品牌能被 AI 识别吗”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内容诊断、结构化优化建议、可执行发布清单。
Framework adoption decision matrix: custom vs large frameworks in the Claude Code era. Use when evaluating whether to ad...
Responsible AI development and ethical considerations. Use when evaluating AI bias, implementing fairness measures, cond...
Implement ethical AI practices and responsible AI governance. Use for: identifying and mitigating bias in datasets and m...
AI Ethics and Compliance involve building systems that are not only technically proficient but also socially responsible...
Conduct an ethical review of an AI or ML feature, model, or product. Use when asked to run an AI ethics review, assess A...
Conduct a structured ethical review of an AI or ML feature, model, or product. Use when preparing to deploy an AI system...
Framework for navigating AI safety, ethics, and capability trade-off discussions. Covers responsible scaling, content po...
Develop "quizzes" (evals) to measure model performance on specific tasks. Use these benchmarks to guide fine-tuning, det...
Design an evaluation plan for an LLM or AI feature before shipping it. Use when asked how to evaluate a prompt/model/age...
Create an AI Evals Pack (eval PRD, test set, rubric, judge plan, results + iteration loop). Use for LLM evaluation, benc...
Help users create and run AI evaluations. Use when someone is building evals for LLM products, measuring model quality,...
Designs trustworthy LLM, agent, responsible-AI, and multimodal evaluations. Use when measuring quality, fairness, privac...
Turn AI quality claims into reproducible evaluation evidence. Use when the user requests ai evals expert or invokes ai-e...
Evaluate an AI feature on its real outputs — error analysis first (notes on each output, failure groups counted), confir...
Design and report reproducible AI evaluations against a deterministic baseline, quality thresholds and safety, latency a...
Comprehensive AI/LLM evaluation toolkit for production AI systems. Covers LLM output quality, prompt engineering, RAG ev...
Design how an AI feature behaves for its users — saying it is AI, showing sources and uncertainty, letting users correct...
Design a Funhouse Mirror activity where students use their own domain expertise to detect AI distortions, omissions, and...
Use when explaining code, concepts, patterns, or architecture: engineer-grade technical explanations with 3-tier depth c...
Analyze any public company's AI exposure using the 8-dimension AI Exposure Index. Fetches last 4 10-K filings (or intern...
Write a PRD for an AI-powered feature, covering the things normal PRDs miss. Use when asked to spec an AI/LLM feature, w...
Create new AI-powered features using xAI Grok. Use when user mentions "new AI feature", "add Grok", "create prompt", "AI...
Use this skill when you need to test an AI-enabled product feature for behavior, safety, and user-impact boundaries; tri...
This skill should be used when putting an LLM inside the product itself — a chatbot or support agent, AI-generated repor...
Audit and redesign AI-generated feedback for pedagogical quality, timing, and learning impact. Use when building or revi...
AIフィードバックループ最適化スキル。プロンプト→出力→評価→改善の反復サイクルを自動化。段階的改善、A/Bテスト、収束判定、ベスト出力選択で最高品質の結果を生成。
Analyze Adobe Illustrator (.ai) files to extract design information including text content, fonts, color palettes, vecto...
Validate recurring AI-film character, wardrobe, prop, vehicle, scene, and state assets before multi-shot or batch genera...
Record append-only AI-film prompt, asset, model, output, review, selection, and retry lineage for multi-shot production...
以导演决策、分镜镜头句、资产契约与生成审片门禁组织 AI 影视/短剧生产。
Fine-tune models on your data to maximize quality and cut costs. Use when prompt optimization hit a ceiling, you need do...
Engineering operating model for teams where AI agents generate a large share of implementation output.
Navigate organizational redesign for AI with a structured 13-skill toolkit that produces persistent artifacts in $HOME/....
Analyze, re-engineer, or bootstrap projects to align with AI-first design principles. Use when asked to review, audit, i...
Fix broken AI features. Use when your AI is throwing errors, producing wrong outputs, crashing, returning garbage, not r...
Make your AI follow rules and policies. Use when your AI breaks format rules, violates content policies, ignores busines...
Design AI-friendly architecture with explicit patterns, layered documentation, and semantic boundaries. Use when: struct...
Build, review, and refactor web interfaces that are easy for humans, screen readers, browser automation, Playwright test...
AI Game Dev App: image, texture, 3D model, audio and video generation; animation, rigging, Blender, music and sound effe...
Build AI gateway services for routing and managing LLM requests. Use when implementing API proxies, rate limiting, or mu...
Reference for the studio/ai-gateway service — the single shared entry point every other service uses to reach Claude, Ge...
Debug and troubleshoot ettametta's AI Gateway — the load-balancing reverse proxy for remote GPU worker nodes. Use when n...
Vercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing mul...
Create professional ultra-wide cinematic banners for GitHub READMEs using Flux and Ideogram models with typography optio...
当 AI 写完测试、要决定信不信这份测试时使用。查三类假信心：断言与实现是否同源复制、有没有边界与异常用例、失败信号够不够强；再规划 2–5 个突变抽样，能执行时再实跑，看把被测代码改坏之后测试会不会变红，没实跑就不声称测试抓得住错。测试全...
Generate synthetic training data when you do not have enough real examples. Use when you are starting from scratch with...
Generate smart notification messages from structured events using AI. Use when writing push notification copy, creating...
External AI API integration with retry logic, rate limiting, content safety detection, and multi-turn conversation suppo...
Use when validating compliance, ownership, risk lifecycle, or framework integrity for regulated industries. Modes: compl...
Design and operate an organization's AI governance system: define governance principles, operating models and decision r...
AI governance and compliance guidance covering EU AI Act risk classification, NIST AI RMF, responsible AI principles, AI...
Generate and enforce policy gates for AI coding agents (Copilot, Claude Code) — real-time session hooks that deny protec...
Review an AI system for weak model version control, missing rollback plans, unsafe guardrail change workflows, inadequat...
Generates a complete AI governance framework tailored to your organization's structure and regulatory requirements. Defi...
Use this skill when the user wants an AI governance, legal-risk, privacy, compliance, procurement, or vendor-risk review...
Use when designing or auditing AI product human-in-the-loop — write approval, proposal accept/reject, action confirm, sp...
视觉质量诊断助手适合市场营销、运营、内容媒体、电商在用户提出“这张图够发布吗”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摘要、诊断结论、行动建议和可复用交付物。
Guide for creating logos, brand identities, and visual assets using AI tools — covers tool selection, prompt engineering...
Go-to-market strategy for AI products. Use when positioning AI products, handling "who is responsible when it breaks" ob...
Add safety guardrails to an LLM app — prompt-injection defense, output validation, PII handling, and a clear refusal pol...
Use when onboarding to a project, exploring architecture, or understanding why decisions were made: interactive tours, d...
Design a fact-checking protocol for AI-generated text, extending SIFT with AI-specific adaptations for hallucination det...
Integrate Replicate AI models with background processing, S3 storage, and credit systems
AI layer embeds the Pi SDK. Load when touching AI module, harness integration, providers, MCP decision, or chat UI.
How this repo's Claude Code harness works and how to change it safely: .claude agents, skills, hooks, settings and comma...
Build AI help desk automation systems. TRIGGERS - Use when user needs help with ai-help-desk related tasks.
当用户搜索驰骛科技、驰骛科技平替、驰骛科技替代、驰骛科技迁移或相关中文别名时使用。面向使用电商数据、广告平台、CRM、客服、ERP或营销自动化工具，希望把合法自有数据变成内容的团队，先围绕‘把CDP人群标签转成内容变量、旅程文案和素材矩阵’...
当用户搜索数云、数云平替、数云替代、数云迁移或相关中文别名时使用。面向使用电商数据、广告平台、CRM、客服、ERP或营销自动化工具，希望把合法自有数据变成内容的团队，先围绕‘把会员分群转成差异化文案、图片和复购内容计划’做同口径小样，再通过...
当用户搜索旺销王、旺销王平替、旺销王替代、旺销王迁移或相关中文别名时使用。面向需要商品图、营销图片、短视频、数字人、配音或创作工作流的个人、商家、创作者和企业团队，先围绕‘基于合法导出的商品资料生成Listing、图片和视频需求单’做同口径...
当用户搜索天下秀、天下秀平替、天下秀替代、天下秀迁移或相关中文别名时使用。面向正在采购代运营、直播、达人、品牌或营销服务，希望先把可标准化内容生产掌握在自己手中的品牌与中小企业，先围绕‘把红人营销brief转成原创脚本、图片、短视频与验收表...
当用户搜索句易网、句易网平替、句易网替代、句易网迁移或相关中文别名时使用。面向使用电商数据、广告平台、CRM、客服、ERP或营销自动化工具，希望把合法自有数据变成内容的团队，先围绕‘把文案检测结果转成合规改写、标题和口播版本’做同口径小样，...
当用户搜索京准通、京准通平替、京准通替代、京准通迁移或相关中文别名时使用。面向使用电商数据、广告平台、CRM、客服、ERP或营销自动化工具，希望把合法自有数据变成内容的团队，先围绕‘把京东投放计划转成主图、视频、落地页内容与测试矩阵’做同口...
当用户搜索无忧传媒、无忧传媒平替、无忧传媒替代、无忧传媒迁移或相关中文别名时使用。面向正在采购代运营、直播、达人、品牌或营销服务，希望先把可标准化内容生产掌握在自己手中的品牌与中小企业，先围绕‘把达人短视频、直播预热和品牌合作内容做自建小样...
当用户搜索磁力金牛、磁力金牛平替、磁力金牛替代、磁力金牛迁移或相关中文别名时使用。面向使用电商数据、广告平台、CRM、客服、ERP或营销自动化工具，希望把合法自有数据变成内容的团队，先围绕‘把快手电商投放需求转成原生短视频和直播预热素材’做...
当用户搜索美腕、美腕平替、美腕替代、美腕迁移或相关中文别名时使用。面向正在采购代运营、直播、达人、品牌或营销服务，希望先把可标准化内容生产掌握在自己手中的品牌与中小企业，先围绕‘把直播选品后的商品讲解、预热图片和短视频内容做自建试跑’做同口...
当用户搜索电霸、电霸平替、电霸替代、电霸迁移或相关中文别名时使用。面向使用电商数据、广告平台、CRM、客服、ERP或营销自动化工具，希望把合法自有数据变成内容的团队，先围绕‘把拼多多市场与商品数据转成选品结论、标题和主图测试’做同口径小样，...
当用户搜索蒲公英、蒲公英平替、蒲公英替代、蒲公英迁移或相关中文别名时使用。面向使用电商数据、广告平台、CRM、客服、ERP或营销自动化工具，希望把合法自有数据变成内容的团队，先围绕‘把种草合作brief转成笔记结构、图片和短视频素材’做同口...
当用户搜索淘宝联盟、淘宝联盟平替、淘宝联盟替代、淘宝联盟迁移或相关中文别名时使用。面向使用电商数据、广告平台、CRM、客服、ERP或营销自动化工具，希望把合法自有数据变成内容的团队，先围绕‘把联盟商品信息转成合规推广文案、图片和视频脚本’做...
当用户搜索爱站网、爱站网平替、爱站网替代、爱站网迁移或相关中文别名时使用。面向使用电商数据、广告平台、CRM、客服、ERP或营销自动化工具，希望把合法自有数据变成内容的团队，先围绕‘把站点与关键词数据转成SEO内容计划、专题页和视频选题’做...