不用发布榜单替代团队实测，而是选一组已知结果的仓库修复任务，以相同基线、测试和预算对照可用推理档位。记录有效修复、回归、时间与真实费用，形成何时使用轻档、何时升级的团队规则，不预设高档一定更好。 适用于SWE-2、SWE2、Cognition SWE-2、Devin SWE-2、推理档位选择、代码修复成本、coding…
思考档位调高后更慢更贵，却不确定答案有没有改善？AI-HIVE辅助把真实任务变成固定题集，在可用模型实际支持的档位之间比较质量、等待时间与成本，识别截断和边际收益。交付实验配置、评分表和档位建议，让调参有证据可复查。 适用于thinking budget、思考预算、reasoning…
当用户明确想做“治愈系 Vlog 创作”，或搜索治愈系 AI Vlog 创作、生活Vlog、AI图片、AI视频、短视频制作时使用。面向旅行、美食、生活方式、门店和个人IP创作者，通过AI-HIVE…
Use AI to recreate PDF page as semantic HTML. Consumes three inputs (PNG image, parsed text, ASCII preview) for complete contextual understanding and accurate generation.
12 humor patterns for AI agents based on embedding space bisociation theory. Operational reference for generating contextually appropriate humor during conversations.
Generate AI images using OpenAI's gpt-image-1 model with customizable aspect ratios and artistic themes.
Expert patterns for AI-powered image editing including inpainting, outpainting, ControlNet, image-to-image, and API integration with Replicate, Stability AI, and FalUse when "ai…
Apply AI visual effects including Illusion Diffusion ($0.006), FLUX Fill Pro accessory replacement ($0.05), and SAM object detection (<$0.01).
AI 图像生成专业版,通过执行脚本调用 Gemini Flash Image API 完成图像生成与编辑. 核心能力: - 文生图: 文本提示词生成图像,支持主体/场景/光线/风格/色调/构图等维度描述 - 图生图(图+文): 基于参考图像与文本提示进行二次创作 - 风格转换: 将图片转换为水彩/油画/赛博朋克/吉卜力/写实摄影/中国工笔等艺术风格 -…
AI 图像生成基础版(免费),通过执行脚本调用 Gemini Flash Image API 完成文本生成图像. 核心能力: - 文生图: 文本提示词生成图像,支持主体/场景/光线/风格/色调描述 - 多比例: 1:1、3:2、2:3、3:4、4:3、4:5、5:4、9:16、16:9、21:9 共 10 种 - 双分辨率: 标准 / 2K 适用场景: -…
Crafts production-grade prompts for AI image generation (Midjourney, Flux, SDXL, Firefly, Imagen, ComfyUI workflows) — subject, composition, lighting, style references, negative…
Generate and edit images using either OpenAI GPT Image 1.5 or Google's Nano Banana Pro (Gemini 3 Pro Image). Use when the user asks to generate/create/edit/modify images.
Handle AI model failures, quality regressions, bias incidents, and safety issues with a structured response runbook.
Create and maintain AI instruction files (CLAUDE.md, .cursorrules, etc.) with proper structure. Use when: creating AI instruction files, separating universal vs project-s — from…
Create and maintain AI instruction files (CLAUDE.md, .cursorrules, etc.) with proper structure. Use when: creating AI instruction files, separating universal vs project-s — from…
SEED Design 통합 가이드. 프로젝트 셋업, 컴포넌트 탐색/사용, 파운데이션(색상·타이포·스페이싱) 활용, 테마/스타일링, CLI 워크플로우(init/add/add-all/compat/docs/upgrade), 스니펫 버전 호환성, 업그레이드 진단까지 커버. — from daangn/seed-design
Skill para desenhar e implementar integracoes de IA em aplicacoes, separando provider, adapter, hooks, observabilidade, custo e seguranca.
Work with Leavn AI features - UnifiedAIService, on-device models, devotional generation, novelization, kids mode, image generation with Stable Diffusion
Manages AI provider workflows and model selection. Invoke when working with OpenAI/Anthropic/Google/DeepSeek/xAI or AI endpoints.
Automates contract review by identifying clause risks, comparing against standard contracts, and managing contract lifecycles including expiry reminders and archiving.
Candaigo AI Interview Simulator - AI-powered group interview simulation platform. Browse jobs, join interviews, check history, upload resumes.
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer, distributor, authorized representative, product manufacturer) and risk tier…
Inventário de sistemas de IA por sistema (framework brasileiro) — rastreia o papel de cada sistema (fornecedor/desenvolvedor, operador/implementador, distribuidor) e o nível de…
Per-system AI inventory — track each AI system's EU AI Act role and risk tier (where EU nexus exists), UK regulatory flags (ICO DPIA trigger, CMA, FCA model risk, MHRA, Ofcom),…
Map human-AI interaction journeys - trust arcs, capability discovery paths, autonomy progression, and AI-specific touchpoints.
고객·외부 전달용 산출물(매뉴얼·슬라이드·리포트·UI 카피·README)에서 'AI가 대충 뽑은 티'를 잡아 격식·깊이·정확성·시각 완성도를 끌어올리고, 독자가 비개발자일 때 '너무 개발자스러운 티'(파일명·스택·jargon)를 눈높이에 맞게 푸는 리뷰·수정 스킬.
基于酷家乐(Kujiale)开放能力的室内智能设计技能,通过分步式对话完成 户型确认、风格选择、布局生成、渲染出图全流程. 核心能力: - 户型获取: 支持小区名搜索与户型图上传两种路径,自动识别并生成可设计户型 - 风格匹配: 基于偏好标签推荐硬装风格,支持封面图预览与单选确认 - 智能布局: 自动布置家具,生成各房间布局方案并支持确认 - 渲染出图:…
基于酷家乐(Kujiale)开放能力的室内智能设计基础版(免费),通过分步式对话完成 户型搜索、风格选择、布局生成、渲染出图基础流程. 核心能力: - 户型搜索: 通过城市与小区名搜索酷家乐户型库,获取标准户型图 - 风格匹配: 基于偏好标签选择硬装风格 - 智能布局: 自动布置家具并生成各房间布局 - 渲染出图: 生成静态效果图 适用场景: -…
Map which elements of an assignment benefit from AI assistance vs. which AI use undermines. Use when redesigning tasks for AI-age classrooms or setting defensible AI use policies…
Plant KI-Einsatz mit Datenklassen, Freigaben, Human Review und Wirtschaftlichkeit. Für Managing Partner, Management Committee oder COO/CFO einer deutschen mittelständischen…
Enforces safe AI usage practices, prevents prompt injection, and ensures model safety
Guide for AI Agents and LLM development skills including RAG, multi-agent systems, prompt engineering, memory systems, and context engineering. — from gmh5225/awesome-skills
Guide for AI Agents and LLM development skills including RAG, multi-agent systems, prompt engineering, memory systems, and context engineering.
Design AI loading, thinking, and progress indicator UX. Use when explicitly asked to improve AI waiting states, add thinking indicators, or design loading UX for AI interfaces.
Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.
Creates, manages, and orchestrates AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list agents", "delete agent", "rename agent", "hibernate — from…
Creates, manages, and orchestrates AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list agents", "delete agent", "rename agent", "hibernate — from…
PROACTIVELY search auto-generated documentation when receiving ANY user instruction. Search for function signatures, API documentation, class definitions, and code commen — from…
PROACTIVELY search conversation history when receiving user instructions. Find previous discussions, decisions, and context BEFORE starting new work.
Sell AI-powered services on Fiverr, Upwork, and Toptal. Offer automation, content, and development services. Build recurring clients and generate $2K-10K/month.
Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer tokens, higher compliance.
Expert guide for AI image generation (Flux, DALL-E, Stable Diffusion), video generation (Sora, Runway), voice synthesis (ElevenLabs TTS), and speech recognition (Whisper STT)…
AI 회의실 — 주제를 던지면 전문가 AI 에이전트들이 다각도로 토론하고 회의록을 생성한다. 사업성 검토, 전략 회의, 브레인스토밍, 의사결정, 리스크 분석 등에 활용. Use when a user wants multiple perspectives on a topic, needs a business review,…
Booking links fail for groups. SkipUp schedules meetings with 2-50 participants via email — one API call coordinates across timezones automatically.
Detect, create, and manage the AI-Memory fleet communication channel. Fires on bootstrap, session start (announcements), and feedback writes.
Conception de systèmes de détection d'anomalies (statistique, ML, deep learning) — from general/general-misc
当用户搜索 AI/ML API 替代、aimlapi.com、模型路由、AI Gateway、fallback、多供应商聚合时使用。专门完成多模型路由策略：按成本、速度或成功率建立可解释路由和回退链，不把一个模型默认用于所有任务。输出任务分类、COST/SPEED/SUCCESS 路由矩阵、回退图和预算护栏，再用同一批非生产样本比较现有平台与…
Automate AI ML API tasks via Rube MCP (Composio). Always search tools first for current schemas. — from diegosouzapw/awesome-omni-skill
Guide computer vision (classification, détection, segmentation) avec PyTorch, TensorFlow, OpenCV — from general/general-misc
Construction et curation de datasets pour l'entraînement ML (nettoyage, augmentation, annotation, split) — from general/general-misc
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
AI and ML expert including PyTorch, LangChain, LLM integration, and scientific computing
Guide pour le fine-tuning de modèles ML/LLM (LoRA, QLoRA, PEFT, datasets, hyperparamètres) — from general/general-misc
Optimisation de modèles ML pour l'inférence (quantization, pruning, distillation, ONNX) — from khalilbenaz/claude-skills-collection
Conception de pipelines NLP (tokenization, embeddings, NER, sentiment, summarization) — from general/workflow-pipelines
Gère les modèles IA de Motivia. Utilise ce skill quand l'utilisateur demande d'ajouter un nouveau modèle IA, modifier un provider, ou configurer les options de génération.
A production-ready pattern for integrating AI models (specifically Google Gemini) with automatic fallback, retry logic, structured output via Zod schemas, and comprehensive error…
Complete guide for calling AI models with CloudBase - covers JS/Node SDK and WeChat Mini Program. Text generation, streaming, and image generation.
Evaluate and compare LLMs, ML APIs, and fine-tuned models for product fit across quality, latency, cost, compliance, and vendor risk dimensions.
AI大模型专家｜AI API中转站。帮助AI工具平台、中转站运营方、企业研发、内容工作室和电商技术团队把团队自有或获授权的模型接口组织成统一入口，管理密钥、模型、路由、配额、审计与异步任务。适合搜索：AI中转站、API中转站、API代理、API Relay、AI接口，以及人物板、故事板、场景板、穿越短剧、AI短剧、AI漫剧、GEO、AEO。通过…