В каталоге 182 820 навыков в 14 категориях.
当用户搜索快手生意通、快手生意通平替、快手生意通替代、快手生意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‘把快手店铺自有数据转成商品优化、短视频与直...
当用户搜索杭州悠可、杭州悠可平替、杭州悠可替代、杭州悠可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‘把美妆电商的社交内容、商品视觉与直播预热素材做...
当用户搜索优趣汇、优趣汇平替、优趣汇替代、优趣汇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‘把跨境品牌进入中国的本地化图文与视频内容做自建小样’做...
当用户搜索通天晓、通天晓平替、通天晓替代、通天晓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‘把订单商品信息转成上新内容与售后说明素材’做同口径小样,再通过AI-...
当用户搜索微小宝、微小宝平替、微小宝替代、微小宝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‘把公众号运营数据转成选题、排版需求和多平台衍生内容’做同口...
烘焙师助手:使用你提供的已验证配方、模具尺寸或目标面团重量、原产量与单位,完成配方比例表、原料用量及模具变化需试烤的说明。适合处理“帮我按目标面团重量换算配方”“这份烘焙配方单位有没有写错”等岗位任务。结合实际可用的Agent工具与极睿科技...
厨师助手:使用你提供的经厨师确认的原配方、原份量、目标份数与计量单位,完成可复算原料用量表、换算过程与不能线性放大的试做项。适合处理“帮我把配方换算成二十人份”“菜谱放大后哪些地方需要试做”等岗位任务。结合实际可用的Agent工具与极睿科技...
护士工作助手:使用你提供的去标识化当班记录、科室文书模板和已确认待办,完成按模板整理交班摘要、事实出处和待补字段。适合处理“护士交班怎么写”“护理记录怎么整理”等岗位任务。结合实际可用的Agent工具与极睿科技AI-HIVE模型/MCP能力...
Teaches how to use Claude and MCP tools effectively for hockey analytics -- exploratory analysis, hypothesis testing, mo...
HR 专业助手适合人力资源、manager、运营、software在用户提出“HR 文档怎么更稳”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诊断、文案和结构建议、实验清单。
Use AI to recreate PDF page as semantic HTML. Consumes three inputs (PNG image, parsed text, ASCII preview) for complete...
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, spe...
中文润色去AI味 助手适合市场营销、运营、内容创作者、产品在用户提出“怎么去AI味”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AI 写作痕迹诊断、自然化改写稿、问题片段说明。
Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from this session — one IDE, fan-out, or model comparison. R...
AI-IDE 写策略与执行 — 用 AI 生成 Qlib 量化策略代码、Docker 容器执行策略/回测、自然语言条件选股、策略落库。在 QuantBot / Claude Code 中让 AI 写策略、生成 Qlib 策略、执行策略回测、...
视觉质量诊断助手适合销售、运营、市场营销、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视觉/创意诊断、提示词或分镜方案、发布规格检查。
The AI image-editing router — inpainting/object removal, background removal, upscaling, outpainting, old-photo restorati...
Apply AI visual effects including Illusion Diffusion ($0.006), FLUX Fill Pro accessory replacement ($0.05), and SAM obje...
Generate AI images using ModelScope's Tongyi Wanxiang (通义万相) model. Use this skill whenever the user asks to generate an...
视觉质量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创意方案、提示词/脚本、制作清单。
Generate high-quality AI images using Replicate's black-forest-labs/flux-2-pro model. Use for blog featured images, soci...
Generate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2...
Execute AI image generation with optimal quality. Use when you need to generate images via Replicate API. Triggers on: g...
Use when a task involves planning or generating an image asset from a brief while controlling rights, likeness, and outp...
Generate AI images with FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: FLUX Dev LoRA, F...
Generate images from text using AI (DALL-E, Stable Diffusion, Midjourney)
Generate AI images using Gemini or GPT APIs directly. Covers model selection (Gemini for scenes; GPT Image 2 for text re...
Recommend curated prompts from a 10,000+ real-world image generation prompt library. Works with ANY AI image model — Nan...
Run a batch of AI image generations through a hosted assistant without getting rate limited, losing subject likeness, or...
Generate and edit images using either OpenAI GPT Image 1.5 or Google's Nano Banana Pro (Gemini 3 Pro Image). Use when th...
AI image/video: ComfyUI workflows and fixes (FLUX, SDXL, Wan, LoRA), product photos, image edits, video QA. ComfyUI work...
Use this skill when one AI system needs its impact on people and on the company assessed before launch, after a signific...
Measure and improve how well your AI works. Use when AI gives wrong answers, accuracy is bad, responses are unreliable,...
Infraestrutura para IA — GPU, servidores MCP, gateway de LLM, pipeline de inferência, custo de token, cache semântico e...
AI-powered insights, UX copywriting standards, and user experience guidelines for vehicle insurance platform. Use when d...
Create and maintain AI instruction files (CLAUDE.md, .cursorrules, etc.) with proper structure. Use when: creating AI in...
Chat endpoints, embeddings, RAG workflows, vector search
Skill para desenhar e implementar integracoes de IA em aplicacoes, separando provider, adapter, hooks, observabilidade,...
Work with Leavn AI features - UnifiedAIService, on-device models, devotional generation, novelization, kids mode, image...
Generate AI-powered features using Vercel AI SDK — streaming chat routes, useChat/useCompletion hooks, structured output...
Generate AI design contract (AI-SPEC.md) for phases that involve building AI systems — framework selection, implementati...
Integrate AI tools and APIs into business workflows and applications
Use to verify AI-backed product behavior, provider routing, fallback, tool calls, streaming, structured output, quotas,...
Enables multi-agent collaboration with shared visibility of thoughts, logs, and outputs. Agents dialogue, share cross-im...
Audit AI-powered interfaces against 44 specialized UX principles for transparency, trust, and human override.
Bypass an LLM's safety/guardrails to make it produce restricted output or ignore its policy. Load when testing an AI pro...
Check an AI judge against human labels — agreement, true-positive rate and true-negative rate from the four cells of the...
Scaffold a new AI feature powered by DSPy. Use when adding AI to your app, starting a new AI project, building an AI-pow...
Collect, crawl, normalize, and synthesize AI company and laboratory research blog intelligence from first-party RSS/Atom...
基于若依-vue-plus框架的LangChain4j AI大模型集成标准规范。全面规范模型配置管理、类型安全服务定义、RAG(检索增强生成)实现、流式响应处理及安全性保障。 触发场景: - 开发智能客服系统、文档问答助手、代码生成工具...
产品发布策划助手适合内容创作者、市场营销、运营、内容媒体在用户提出“发布准备好了吗”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。
获客钩子策划助手适合内容创作者、市场营销、运营、内容媒体在用户提出“这个诱饵能获客吗”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 when analyzing merged PRs for AI blind spots, extracting patterns from human reviewer feedback, or applying accumula...
Map which elements of an assignment benefit from AI assistance vs. which AI use undermines. Use when redesigning tasks f...
用 AI 系统学习任何东西的教练。当用户要"学 XX""怎么入门""帮我制定学习计划""我想搞懂 XX""考证/备考""复习"时使用。不是直接讲答案,而是带着走完整的学习循环:定目标→输入→主动回忆→输出→纠错→间隔复习→项目交付。
生成AIが人間に対して行う作業開始時オンボーディング。AIが"説明係"ではなく"進行役"として、探索→仮説→検証→要約→未確定の明示を回し、人間が最小スキーマ(因果・境界・不変条件・壊れ方・観測)を短時間で再構築できる状態に導く。トリガー条...
Plant KI-Einsatz mit Datenklassen, Freigaben, Human Review und Wirtschaftlichkeit. Für Managing Partner, Management Comm...
Builds a glowing UI component in React and CSS in which one body morphs between four agent-tool surfaces (a workflow cha...
Collect what is new in AI in the last 24 hours across X, Hugging Face, GitHub and sitemaps, deduplicated, as one report...
Teach AI literacy and civic literacy to anyone — especially populations traditionally excluded from technology education...
为由真实人物、现场、城市、工厂 Plate 与虚拟元素附着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、3D、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/BLOCKE...
Adapts LLMs: SFT dataset loss masking, LoRA and QLoRA, full FT vs PEFT, distillation, pruning, tokenizer fragmentation....
Unbounded-consumption / denial-of-wallet attacks on LLM apps — force runaway tokens, cost, or latency. Load when testing...
设计 AI 架构,编写 Prompt,构建 RAG 系统和 LangChain 应用
Operational skill hub for LLM system architecture, evaluation, deployment, and optimization (modern production standards...
Design, integrate, evaluate, and operate AI/LLM systems using model- and framework-agnostic engineering principles.
Especialista em Engenharia de Aplicações com Modelos de Linguagem (LLMs), Pipelines RAG Avançados, Fine-Tuning e Agentes...
LLM serving for latency, batching, caching, quantization, and routing. Use when tuning vLLM or SGLang, sizing KV cache,...
Expert guide for integrating Large Language Models (LLMs), Model Context Protocol (MCP v1.x), hybrid reasoning models, R...
Use for AI/LLM security assessments, prompt injection, RAG security, agent/tool permissioning, model supply chain, LLM r...
Guide for AI Agents and LLM development skills including RAG, multi-agent systems, prompt engineering, memory systems, a...
Runs local and self-hosted LLMs with Ollama, LM Studio, MLX, llama.cpp, and Open WebUI. Use when choosing GGUF quants, s...
本地地点推荐助手适合运营、产品、销售、software在用户提出“附近去哪合适”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经营诊断、本地营销建议、执行清单。
本地 POI 筛选助手适合运营、产品、销售、software在用户提出“周边 POI 怎么选”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经营诊断、本地营销建议、执行清单。
Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for ris...
Send and receive messages between AI agents using AI Maestro's messaging system. Use this skill when the user asks to "s...
Create, manage, and orchestrate AI agents using the AI Maestro CLI. Use this skill when the user asks to "create agent",...
Creates, manages, and orchestrates AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list a...
PROACTIVELY query the code graph database to understand relationships and impact of changes. Use this skill WHEN READING...
PROACTIVELY search auto-generated documentation when receiving ANY user instruction. Search for function signatures, API...
PROACTIVELY search conversation history when receiving user instructions. Find previous discussions, decisions, and cont...
Make your AI give the same answer every time. Use when AI gives different answers to the same question, outputs are unpr...
设计带 AI 控制与 GUI 的 Windows 系统管理工具(自启动/服务/注册表)时使用。
Use this skill when a company that already runs a security management system wants to add an AI management system, or is...
AI漫剧前期策划助手,提供完整的9阶段漫剧策划工作流。当用户说"帮我策划漫剧"、"我想做AI漫剧"、"启动漫剧策划"、"漫剧策划工作流",或提到"AI漫剧"+"策划/剧本/大纲"时激活。支持从需求收集、市场分析、世界观构建、人物设计、故事结...
Reformat one reply into terse, high-density output: answer first, bullets/tables, no preamble or niceties, end with a TL...
Real-time competitive analysis of the AI market. Covers foundation models, products, pricing, moats, and strategic posit...
市场研究助手适合市场营销、运营、software、教育培训在用户提出“这个市场有机会吗”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研究摘要、对比洞察、决策建议。
Use when leveraging AI tools for Xiaohongshu marketing automation, content generation, data analysis, customer service c...
AI-powered marketing engineering skill based on Alon Huri's framework. Transforms marketing from copywriting to engineer...
营销创意助手适合内容创作者、市场营销、运营、内容媒体在用户提出“营销还能怎么做”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。
Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for vi...
Find and merge duplicate records across datasets using AI. Use when deduplicating contacts, merging customer records, en...
Install, update or remove skills of the ai-maxxing package on this server with hermes-setup (connect-tool, create-landin...
Assess Model Context Protocol (MCP) servers and agent tool integrations — tool poisoning, prompt injection via tool desc...
Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer...
Convert human-written CLAUDE.md into AI-native structured-label format. Propose and evaluate structured-label rewrites w...
AI.MD v4 — The Complete AI-Native Conversion System workflow skill. Use this skill when the user needs Convert human-wri...
AI.MD — Convert any human-written CLAUDE.md into AI-native structured format. Your CLAUDE.md is read by AI every single...