Parcourir le registre

Toutes les entrées, par ordre alphabétique — 56 437 au total. Page 12 sur 226.

• ai-engineerBuild production-ready LLM applications, RAG systems, and intelligent agents. Use when implementing AI feature
• ai-engineer-v2ai-engineer workflow skill. Use this skill when the user needs Build production-ready LLM applications, advanc
• ai-engineeringAuthoritative source of truth on AI tooling and how to choose it - the knowledge behind building AI agents and
• ai-engineering-command-deskorchestrate AI engineering workflows from capability intent through model, prompt, tool, agent, retrieval, eva
• ai-engineering-toolkitAI Engineering Toolkit workflow skill. Use this skill when the user needs 6 production-ready AI engineering wo
• ai-engineering-updateThe write path for the ai-engineering tooling corpus - keeps it current, deduplicated, and honest about what w
• ai-entity-optimizer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。
• ai-ethics-checklistAnalyze and produce a ai ethics checklist with structured process, quality checks, and system integration
• ai-ethics-reviewConduct a structured ethical review of an AI or ML feature, model, or product. Use when preparing to deploy an
• ai-ethics-tradeoffsFramework for navigating AI safety, ethics, and capability trade-off discussions. Covers responsible scaling,
• ai-eval-ciRun AI agent and LLM evaluations in CI/CD pipelines — automated quality gates that fail the build when AI outp
• ai-eval-planDesign an evaluation plan for an LLM or AI feature before shipping it. Use when asked how to evaluate a prompt
• ai-evalsHelp users build robust infrastructure for measuring, monitoring, and iterating on AI product performance usin
• ai-evaluationSystematic evaluation (evals) for LLM and AI products. Design test cases, measure accuracy/quality, track regr
• ai-expertise-engineComprehensive AI/ML expertise covering prompt engineering, LLM architecture, AI agent design, RAG systems, fin
• ai-exponential-pm-shiftsA practical workflow guide for product teams operating under rapid model capability gains: short sprint explor
• ai-failure-pattern-collector系统性记录 AI 执行偏差、误解指令、输出质量不达标等失败案例的复盘系统——含失败数据结构、快速标记 UI、按标签/模型/提供商检索、定期 AI 聚类预警。Use when user wants to track AI
• ai-fashion-photographyOne model across 14 fashion-photography styles, from runway to streetwear to haute couture, each with the prom
• ai-feature-prdWrite a PRD for an AI-powered feature, covering the things normal PRDs miss. Use when asked to spec an AI/LLM
• ai-feature-spec-writerWrites a complete product spec for an AI-powered feature including user stories, model requirements, fallback
• ai-federated-learningImplements federated learning architecture patterns for GDPR compliance. Covers secure aggregation protocols,
• ai-film-stock-emulationOne portrait across 14 film stocks, so you can see exactly what each film's colour does, each with the prompt.
• ai-first-engineeringAI エージェントが大量の実装出力を生成するチームのためのエンジニアリング運用モデル。
• ai-firstifyAnalyze, re-engineer, or bootstrap projects to align with AI-first design principles. Use when asked to review
• ai-fluency-101Reference guide to working with your AI assistant effectively: when to use turn-by-turn chat vs handing off mu
• ai-fluency-for-buildersReference guide to applying the AI Fluency Framework (4Ds) to building software with AI, for engineers, design
• ai-fluency-for-educatorsReference guide to applying the AI Fluency Framework (4Ds: Delegation, Description, Discernment, Diligence) sp
• ai-fluency-for-nonprofitsReference guide to applying the AI Fluency Framework (4Ds) at a mission-driven nonprofit with limited staff ti
• ai-fluency-for-pk-12-educatorsReference guide to applying the AI Fluency Framework (4Ds) in a pK-12 classroom, where student data protection
• ai-fluency-for-small-businessesReference guide to applying the AI Fluency Framework (4Ds - Delegation, Description, Discernment, Diligence) a
• ai-fluency-for-studentsReference guide to applying the AI Fluency Framework (4Ds: Delegation, Description, Discernment, Diligence) sp
• ai-fluency-frameworkReference guide to the AI Fluency Framework (Dakan & Feller): the three ways people work with AI (Automation,
• ai-food-photography12 food-photography styles, from dark-and-moody to bright-and-airy to flat-lay, each with the prompt.
• ai-friendly-architecture设计 AI 友善架构，包含明确的模式、分层文档与语义边界。 Use when: 为 AI 协作规划项目结构、优化代码库以利 AI 分析、建立 AI 上下文。 Not for: 编写指令文件本身——请用 /ai-instr
• ai-friendly-web-designBuild, review, and refactor web interfaces that are easy for humans, screen readers, browser automation, Playw
• ai-game-art-pipelineProvider-neutral open-source skill for planning and producing game-runtime art assets and animation: static pr
• ai-gameplay-pack阿真的 AI 游戏实机视频提示词包工厂。基于《用 GPT Image 2 + Seedance 2.0 做 AI 游戏实机视频》工作流，给一张参考图或一段角色关键词/IP 名称，一键产出整套关键帧图片提示词 + Seed
• ai-gatewayReference for the studio/ai-gateway service — the single shared entry point every other service uses to reach
• ai-githubGitHub repo 展示层管家 — 让 repo 在 GitHub 页面上"看起来像个能用的项目"。三件套：① README 重写（mirror 参考 repo 的结构 + 填充本 repo 内容，含 badges
• ai-goodnovel用于【AI科幻】题材下的 GoodNovel 平台输出任务。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口、补充关系张力与现实调查边界，并明确要求优先强制加载并使用 `通用-输出GoodNovel版`。关键词：A
• ai-governanceAudit an existing application or guide a new build for AI governance — classifying every function as DETERMINI
• ai-governance-reviewer-carl-ditzlerUse this skill when the user wants an AI governance, legal-risk, privacy, compliance, procurement, or vendor-r
• ai-gpt-image-2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。
• ai-graphic-design-skillMaps 15 AI tools to design scenarios — Midjourney for ideation, Stable Diffusion for production, ControlNet fo
• ai-gtmGo-to-market strategy for AI products. Use when positioning AI products, handling "who is responsible when it
• ai-guardrailsOfficial Claude Skills for Trend Micro Vision One
• ai-harness-doctorAudit, canonicalize, guard, and evaluate a repository's AI harness configuration layer around AGENTS.md; trigg
• ai-higgsfield-marketplace-cards商品卡片图助手适合运营、产品、销售、software在用户提出“商品卡片够吸睛吗”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商品/店铺诊断、卖点与风险提示、运营动作建议。
• ai-higgsfield-product-photoshoot产品写真助手适合运营、产品、销售、software在用户提出“产品图有质感吗”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商品/店铺诊断、卖点与风险提示、运营动作建议。
• ai-high-end-visual-design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视觉/创意诊断、提示词或分镜方案、发布规格检查。
• ai-home-migrationStandardize user-installed AI agent content into user-confirmed long-term directories, recreate legacy entry p
• ai-hr-performance-review绩效评语助手适合运营、产品、销售、software在用户提出“绩效反馈怎么写”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运营诊断、商品/流量优化建议、执行清单。
• ai-hr-proHR 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。
• ai-humanizer-zh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。
• ai-ide-runnerRun prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from the current session — pick one IDE, fan out a
• ai-image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。
• ai-image-controls-comparedThe same handful of dials (aspect ratio, style strength, seed, reference images) mapped across every major ima
• ai-image-editingThe AI image-editing router — inpainting/object removal, background removal, upscaling, outpainting, old-photo
• ai-image-genGenerate AI images using ModelScope's Tongyi Wanxiang (通义万相) model. Use this skill whenever the user asks to g
• ai-image-gen-guide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。
• ai-image-generationGenerate AI images with FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: FLUX D
• ai-image-generatorGenerate AI images using Gemini or GPT APIs directly. Covers model selection (Gemini for scenes; GPT Image 2 f
• ai-image-promptCreate a ai image prompt with structured process, quality checks, and system integration
• ai-image-prompt-builderCrafts three structured text-to-image prompts with composition, lighting, palette, and negative constraints.
• ai-image-workflowDesign and document a ai image workflow with structured process, quality checks, and system integration
• ai-incident-response-desktriage AI production incidents involving hallucination spikes, safety failures, prompt injection, tool misuse,
• ai-industrial-brutalist-ui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视觉/创意诊断、提示词或分镜方案、发布规格检查。
• ai-infrastructure-huggingface-inferenceHugging Face Inference SDK patterns for TypeScript/Node.js — InferenceClient setup, chat completion, text gene
• ai-infrastructure-litellmLiteLLM proxy server setup, TypeScript client patterns via OpenAI SDK, model routing, fallbacks, load balancin
• ai-infrastructure-modalServerless GPU compute platform for AI model deployment — web endpoints, GPU functions, model serving, and Typ
• ai-infrastructure-ollamaLocal LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, st
• ai-infrastructure-replicateReplicate SDK patterns for TypeScript/Node.js -- client setup, predictions, streaming, webhooks, file handling
• ai-infrastructure-together-aiTogether AI SDK patterns for TypeScript — client setup, chat completions, streaming, structured output, functi
• ai-instruction-standards创建并维护 AI 指令文件（CLAUDE.md、AGENTS.md、.cursor/rules/ 等），并采用适当结构。 Use when: 创建 AI 指令文件、区分通用规则与项目特定规则、配置 AI 工具。 Not
• ai-interior-designOne living room across 14 interior-design styles, each with the prompt, from Scandinavian to japandi to maxima
• ai-internal-linking-optimizer内链优化助手适合市场营销、运营、内容创作者、software在用户提出“内链该怎么连”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。
• ai-inventoryPer-system AI inventory — track each AI system's EU AI Act role and risk tier (where EU nexus exists), UK regu
• ai-job-application-optimizer求职材料优化助手适合人力资源、manager、运营、software在用户提出“简历够匹配岗位吗”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匹配差距、简历优化建议、面试准备清单。
• ai-judgeThe neutral AI lenser that scores battle submissions when a battle is configured to use AI judging.
• ai-kpi-dashboard-designKPI 看板设计助手适合technical、产品、市场营销、software在用户提出“看板讲清 KPI 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销售策略、沟通素材、跟进计划。
• ai-launch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。
• ai-lead-magnets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。
• ai-lintRun ai-lint to check AI config file health. Use after editing CLAUDE.md, AGENTS.md, SKILL.md, or any rules fil
• ai-llmGuides the LLM lifecycle from strategy to deployment. Use when planning, comparing, fine-tuning, migrating, or
• ai-llm-agent-security当目标为 LLM 应用/Chatbot/智能客服/AI 助手/Copilot/Agent/RAG 知识库/多模态模型，或发现用户输入进入大模型提示、工具调用、知识库检索、对话记忆、文件解析，或需要测试提示词注入/越狱逃逸
• ai-llm-engineeringOperational skill hub for LLM system architecture, evaluation, deployment, and optimization (modern production
• ai-llm-inferenceLLM inference patterns for latency, batching, caching, quantization, routing, and serving stacks. Use when opt
• ai-llm-securityLLM and AI application security testing — prompt injection, jailbreak resistance, OWASP LLM Top 10 (2025), RAG
• ai-llm-security-reviewUse for AI/LLM security assessments, prompt injection, RAG security, agent/tool permissioning, model supply ch
• ai-loading-uxDesign AI loading, thinking, and progress indicator UX. Use when explicitly asked to improve AI waiting states
• ai-local-model-opsRuns local and self-hosted LLM workflows with Ollama, LM Studio, MLX, Open WebUI, llamafile, and adapters. Use
• ai-local-places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。
• ai-local-pois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。
• ai-loopRuns a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gat
• ai-market-landscapeReal-time competitive analysis of the AI market. Covers foundation models, products, pricing, moats, and strat
• ai-market-research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。
• ai-marketing-ideas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。
• ai-marketing-videosCreate AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, F
• ai-mdAI.MD v4 \u2014 The Complete AI-Native Conversion System workflow skill. Use this skill when the user needs Co
• ai-media-generator為使用者產生高品質的 AI 生圖、生影片、生音樂提示詞，並在需要時透過瀏覽器自動化實際送到目標平台。涵蓋 OiiOii、Kling 3.0/O-series、Seedance 2.0/2.5、Suno v5.5、Seed
• ai-meeting-notesCreate a ai meeting notes with structured process, quality checks, and system integration
• ai-meeting-to-tasks会议待办整理助手适合运营、产品、销售、software在用户提出“会议后该做什么”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待办拆解、决策摘要、风险和跟进清单。
• ai-minimalist-ui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视觉/创意诊断、提示词或分镜方案、发布规格检查。
• ai-mlAI/ML Workflow Bundle workflow skill. Use this skill when the user needs AI and machine learning workflow cove
• ai-ml-api-automationAutomate AI ML API tasks via Rube MCP (Composio). Always search tools first for current schemas.
• ai-ml-data-scienceML and data science workflows - EDA, feature engineering, modelling, evaluation, and production handoff. Use w
• ai-ml-developmentAI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models
• ai-ml-model-testingTesting machine learning models including accuracy validation, bias detection, drift monitoring, A/B testing,
• ai-ml-timeseriesTime-series forecasting with temporal validation, panel models, probabilistic forecasts, and TS foundation mod
• ai-ml-v2AI/ML Workflow Bundle workflow skill. Use this skill when the user needs AI and machine learning workflow cove
• ai-mlopsOperates production MLOps for ML, LLM, and agent systems. Use when designing deployment, monitoring, retrainin
• ai-model-comparisonCompare model outputs using output comparison, reasoning quality, and a judge lenser.
• ai-model-nodejsUse this skill for Node.js backend AI via @cloudbase/node-sdk (>=3.16.0) — cloud functions, CloudRun, Express,
• ai-model-privacy-auditConducts privacy auditing of AI models including training data extraction testing, membership inference attack
• ai-model-webUse this skill when a browser/Web app (React, Vue, Angular, Next, Nuxt, static sites, SPAs, dashboards, AI cha
• ai-model-wechatUse this skill for WeChat Mini Program AI via wx.cloud.extend.AI (小程序, 企业微信小程序, wx.cloud apps). Features gener
• ai-multimodalProcess and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (tra
• ai-music-and-soundThe AI music + sound-design skill for social -- original/licensed audio beds and sound design for Reels/TikTok
• ai-my-fiction用于【AI科幻】题材下的 My Fiction 平台输出任务。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口、补充关系黏性与调查驱动边界，并明确要求优先强制加载并使用 `通用-输出My Fiction版`。关键词
• ai-native-agent-skill-designAI Native 产品方法论——智能体与技能单元设计的实操 Skill。
• ai-native-audit-releaseAI Native 产品方法论——审计放行阶段的实操 Skill。
• ai-native-business-modelAI Native 商业模式设计 Skill。基于《AI确定性商业模式》方法论， 帮助用户设计以"确定性溢价"为核心的 AI 商业模式：
• ai-native-cliAgent-Friendly CLI Spec v0.1 workflow skill. Use this skill when the user needs Design spec with 98 rules for
• ai-native-cli-v2Agent-Friendly CLI Spec v0.1 workflow skill. Use this skill when the user needs Design spec with 98 rules for
• ai-native-context-engineeringAI Native 产品方法论——上下文工程的实操 Skill。
• ai-native-direction-framingAI Native 产品方法论——方向定界阶段的实操 Skill。
• ai-native-experiment-engineAI Native 产品方法论——试验展开阶段的实操 Skill。
• ai-native-knowledge-ragAI Native 产品方法论——RAG与知识系统设计的实操 Skill。
• ai-native-marketing-growthAI Native 营销与增长策略 Skill。基于《AI Native 营销与增长》方法论， 帮助用户构建以 AI 为第一性原理的增长系统：从工具思维升级为系统思维，
• ai-native-memory-systemAI Native 产品方法论——记忆系统设计的实操 Skill。
• ai-native-pm-agentAI Native 产品经理 Agent — — 五书合一的产品工作流编排器。 用户提供一个产品想法或问题线索，Agent 自动编排七个阶段：
• ai-native-productBuild AI-native products with agency-control tradeoffs, calibration loops, and eval strategies. Use when build
• ai-native-product-needsAI Native 产品需求发现 Skill。基于《AI rebuild product needs》方法论， 帮助用户在 AI Agent
• ai-native-production-opsAI Native 产品方法论——生产运行与循环回灌的实操 Skill。
• ai-native-system-buildingAI Native 产品方法论——系统构建阶段的总论 Skill。
• ai-native-uxHelp users interact with probabilistic models by designing interfaces that manage fluidity, intent, and agency
• ai-native-ux-designAI Native 产品方法论——AI Native 用户体验设计的实操 Skill。
• ai-newsFetch and curate AI news from X/Twitter list. Use when user asks for AI news, AI digest, what's happening in A
• ai-news-fetcherFetches and summarizes the latest AI news from across the internet — including tech blogs, research outlets, n
• ai-news-radarLearn what AI skills are and how to design, structure, and use them in real-world agent systems.
• ai-news-researchAll my YouTube tutorials. Everything here is free - but please follow me on YouTube if you find these helpful.
• ai-news-skillFetch the latest AI/ML news, trending open-source projects, social media discussions, and KOL (Key Opinion Lea
• ai-observabilityUse when adding Spring AI-specific model observations, token usage, latency, externally configured cost attrib
• ai-observability-langfuseLLM observability with Langfuse — OpenTelemetry-based tracing, evaluations, prompt management, datasets, and p
• ai-observability-promptfooTesting and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-g
• ai-onboarding新手引导诊断助手适合市场营销、产品、运营、software在用户提出“新用户会卡住吗”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。
• ai-operationsConfigure Harness AI-powered operations (AIDA) via MCP. Set up predictive failure analysis with ML models for
• ai-operations-manual运营手册整理助手适合运营、产品、销售、software在用户提出“流程手册清楚吗”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结构化摘要、风险/缺口清单、可执行建议。
• ai-opsGuides operational excellence for AI/ML systems in production. Use when deploying models, managing inference i
• ai-or-notJulga se uma referência foi feita por IA. Use quando o usuário colar um texto, artigo, imagem, vídeo, áudio ou
• ai-orchestration-langchainLangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured o
• ai-orchestration-llamaindexLlamaIndex.TS data framework for RAG, indexing, retrieval, query engines, chat engines, and agentic workflows
• ai-orchestration-vercel-ai-sdkVercel AI SDK patterns - providers, text generation, streaming, structured output, tool calling, chat UI hooks
• ai-output-comparatorCompares multiple AI outputs on the same task with a four-axis rubric and a willing-to-lose verdict.
• ai-output-validationValidates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Struc
• ai-output-verifierCheck AI output before you trust or use it — where it's likely wrong, what to verify, and how to catch confide
• ai-page-cro页面转化诊断助手适合市场营销、产品、运营、software在用户提出“页面为什么不转化”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CRO 优先级、AB test 假设、CTA 改稿。
• ai-paid-ads付费广告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“广告钱花值了吗”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、合规风险、素材迭代清单。
• ai-pair-programmingDesign and document a ai pair programming with structured process, quality checks, and system integration
• ai-patternsReference patterns for augmented coding with AI. Use when discussing AI coding patterns, anti-patterns, obstac
• ai-patterns-tool-use-patternsProvider-agnostic patterns for LLM function calling, tool loops, and agentic workflows
• ai-paywall-upgrade-cro付费墙优化助手适合市场营销、产品、运营、software在用户提出“付费墙能转化吗”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升级阻力诊断、权益表达改稿、实验建议。
• ai-pdfPDF 整理助手适合运营、产品、市场营销、technical在用户提出“PDF 重点是什么”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。
• ai-pentestingRun autonomous AI-driven penetration tests on web applications using tools like Shannon, PentAGI, and similar
• ai-performance性能诊断助手适合technical、产品、市场营销、software在用户提出“性能哪里拖慢了”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
• ai-persistent-memory-system跨对话积累 AI 知识、决策、踩坑历史的持久化记忆系统——对话结束自动提取摘要、append 写入 memory.md、相关片段注入下轮对话 SYSTEM_PROMPT。Use when user wants cross
• ai-pipeline-orchestrationOrchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefec
• ai-pm-atom-lesson输入一个"原子知识点"(AI 产品经理知识体系里的最小单元概念,如「文本切分」「演绎推理」「思维链 CoT」「向量化」「LLM-as-Judge」),自动展开成一份讲解思路并产出一个单文件、离线可用的交互式 HTML 原
• ai-pm-coachActivate this skill when the user wants to learn how to become a Senior AI Product Manager at big tech. This s
• ai-podcast播客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“播客内容够吸引吗”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播客脚本、角色设定、分镜和生成参数。
• ai-policy-generatorAI governance policy creation for nonprofits and enterprises with frameworks, risk assessment, ethical guideli
• ai-portrait-styles16 kinds of portrait, from corporate headshot to editorial to cinematic, each with the prompt.
• ai-post-trainingPost-training and alignment: reward modeling, RLHF/PPO, DPO/DAAs, GRPO, RLVR, RLAIF, over-optimization. Use wh
• ai-pptxPPT 诊断助手适合运营、产品、市场营销、technical在用户提出“PPT 讲清了吗”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摘要、诊断结论、行动建议和可复用交付物。
• ai-presentation-deck演示稿优化助手适合运营、产品、销售、software在用户提出“这套演示讲清了吗”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运营诊断、商品/流量优化建议、执行清单。
• ai-presentation-design-enhancer演示稿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“这套演示讲清了吗”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结构诊断、页面改进建议、讲述逻辑清单。
• ai-pretrainingBuilds a transformer/GPT and BPE tokenizer from scratch. Use when implementing autograd, self-attention, a nan
• ai-pricingAI Pricing Skill workflow skill. Use this skill when the user needs When the user wants to price an AI product
• ai-privacy-assessmentGuides the combined DPIA and AI Act conformity assessment for AI systems processing personal data. Covers EDPB
• ai-productEvery product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apar
• ai-product-canvasStructure AI and ML product decisions with the rigour of any product decision. Use when building AI-powered fe
• ai-product-managerElite AI Product Manager skill with expertise in AI product strategy, LLM product development, ML feature prio
• ai-product-marketing产品营销助手适合内容创作者、市场营销、运营、内容媒体在用户提出“卖点说清了吗”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。
• ai-product-operating-modelDesigns operating models for AI in product teams. Use when planning platform ownership, provider strategy, dat
• ai-product-photo-scene-planner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。
• ai-product-photographyOne product across 16 studio setups, surfaces and lighting, each with the prompt, so you can shoot any product
• ai-product-reviewerReviews and evaluates AI product ideas or existing AI tools across six dimensions: problem clarity, user speci
• ai-product-strategyHelp users decide where to apply AI effectively, manage the transition from deterministic to probabilistic sof
• ai-product-teardownStructured teardown of AI products (ChatGPT, Claude, Gemini, Perplexity, Copilot, etc.). Analyzes product deci
• ai-programmatic-seo程序化 SEO 助手适合市场营销、运营、内容创作者、software在用户提出“页面能批量获客吗”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页面集群规划、模板风险提示、内容生产清单。
• ai-prompt-engineeringPrompt engineering for production LLMs — structured outputs, evals, RAG, tool workflows, multimodal prompting,
• ai-prompt-engineering-safety-reviewComprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, s
• ai-prompting-patternsUse this skill when designing how an AI agent should communicate with developers — intent clarification, progr
• ai-provider-anthropic-sdkOfficial Anthropic SDK patterns for TypeScript/Node.js — client setup, Messages API, streaming, tool use, visi
• ai-provider-api-integration浏览器端直接调用多家 AI 提供商 REST API 的统一集成方案——Anthropic / OpenAI 兼容 / Gemini 三种格式的请求构建、响应解析、错误处理、API Key 浏览器端安全存储。Use wh
• ai-provider-claude-visionImage understanding and document analysis with Claude's multimodal capabilities -- image input formats, PDF pr
• ai-provider-cohere-sdkOfficial Cohere TypeScript SDK patterns -- CohereClientV2, chat, embeddings, rerank, RAG with citations, tool
• ai-provider-elevenlabsElevenLabs voice AI SDK patterns for TypeScript/Node.js -- text-to-speech, streaming, voice cloning, speech-to
• ai-provider-google-gemini-sdkOfficial TypeScript SDK for Google Gemini — client setup, text generation, multimodal input, function calling,
• ai-provider-mistral-sdkOfficial Mistral AI TypeScript SDK patterns — client setup, chat completions, streaming, function calling, str
• ai-provider-openai-sdkOfficial OpenAI SDK patterns for TypeScript/Node.js — client setup, Chat Completions, Responses API, streaming
• ai-provider-openai-whisperSpeech-to-text transcription and translation via OpenAI Audio API -- models, response formats, timestamps, pro
• ai-qa-reviewReview EXISTING test code for quality, smells, and testability issues. Detects test smells across six dimensio
• AI-QL/tuuiA desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Mode
• ai-radarAI-новости: модели, инструменты, тренды в ИИ
• ai-ragDesigns retrieval-augmented generation and search systems. Use when choosing retrieval, chunking, hybrid searc
• ai-readiness-assessmentAnalyze and produce a ai readiness assessment with structured process, quality checks, and system integration
• ai-readiness-auditScore AI readiness across strategy, data, process, systems, talent, and governance, then classify automation o
• ai-readyMake any repo AI-ready — analyzes your codebase and generates AGENTS.md, copilot-instructions.md, CI workflows
• ai-reasoning-process-visualizer暴露 AI 中间推理步骤、排除选项、不确定节点给用户介入的可视化系统——结构化 CoT prompt、推理树/时间线渲染、节点级暂停/修改/重推理。Use when user wants to see AI thinki
• ai-regression-testingDesign regression tests for AI-assisted development by targeting model blind spots such as sandbox versus prod
• ai-release-guardianAnalyze a git diff, map affected risks, select the tests that matter, detect coverage gaps on changed lines, r
• ai-release-readiness-deskassess readiness to release AI capabilities across requirements, evals, safety review, red-team status, infere
• ai-research-workflowDesign and document a ai research workflow with structured process, quality checks, and system integration
• ai-research-writing-skillEnd-to-end research paper generation, review, and revision for ML/AI/CV/NLP projects from repositories, notes,
• ai-rock-paper-scissorsAI Rock Paper Scissors - A fair turn-based battle game using commit-reveal anti-cheat. Register, create or joi
• ai-roi-auditAudit whether the organisation's AI spend actually paid — measured against baselines, not vendor math or vibes
• ai-routerRoute tasks to optimal model tiers and ensemble responses across Claude, GPT, and Gemini APIs. Grounded PR rev
• ai-rulesA collection of skills for AI agents (Kiro, Cursor, Windsurf, Claude Code, and others). Each skill is a reusab
• ai-safetyAI safety and responsible AI practices
• ai-safety-researcherExpert AI Safety Researcher with deep specialization in LLM alignment, Constitutional AI, RLHF/DPO, red-teamin
• ai-safety-review-deskreview AI capability risks including misuse, policy compliance, privacy, security, hallucination harm, data le
• ai-sales-championAI咨询/销售的对话策略助手。当用户需要准备AI方案沟通、跟业务部门聊AI落地、写AI提案、应对客户异议、做AI培训破冰时使用。触发场景："怎么跟老板聊AI"、"客户说AI不靠谱"、"准备一个AI方案汇报"、"帮我想想怎
• ai-scaling-lawsSizes models and token budgets using Kaplan/Chinchilla scaling laws. Use when reasoning about compute-optimal
• ai-science-alphafold-protein-designInterpret AlphaFold2/AF3 pLDDT/PAE scores, fetch AlphaFold DB models by UniProt ID, and rank RFdiffusion/Prote
• ai-science-diffusion-generative-modelsCode DDPM/DDIM diffusion samplers, linear/cosine noise schedules, and DDRM inverse-problem solving (denoising,
• ai-science-enformer-regulatoryPredict CAGE/DNase/ATAC/ChIP-seq tracks from raw DNA with Enformer/Borzoi, run in-silico mutagenesis (ISM), an
• ai-science-epigenomic-sequence-modelsChoose Borzoi (RNA-seq coverage, 32bp) vs Epiformer (sequence+PhyloP, chromatin accessibility) vs AlphaGenome
• ai-science-esm2-embeddingsGenerate ESM2 protein embeddings (fair-esm/transformers) and predict structure with ESMFold. Use when embeddin
• ai-science-geneformer-scgptTokenize scRNA-seq via Geneformer gene-rank or scGPT expression-bin encoding; annotate cell types, simulate in
• ai-science-genomic-llmsEmbed DNA with genomic foundation models (Nucleotide Transformer, HyenaDNA, Evo) via HuggingFace transformers;
• ai-science-llm-finetuningFine-tune LLMs (Mistral/Llama/Qwen) with LoRA/QLoRA via HuggingFace PEFT, bitsandbytes NF4, and trl SFTTrainer
• ai-science-llm-training-systemsTrack LLM fine-tuning runs with pandas/dataclasses + W&B/MLflow/TensorBoard: log per-epoch loss, run one-facto
• ai-science-splicing-modelsScore splicing variant effects with SpliceAI/Pangolin delta scores (DS_AG/DS_AL/DS_DG/DS_DL) and AlphaGenome.
• ai-science-variant-to-structure-modelsTriage variant scores for structural follow-up; pick AlphaFold2 vs AlphaFold3 vs RoseTTAFold2 and gate results
• ai-science-vision-ragColPali-style Vision RAG: embed rendered PDF pages, retrieve via ColBERT MaxSim, feed top-k pages to Qwen2-VL,
• ai-science-zero-shot-mutationScore protein point mutations zero-shot with ESM-1v/ESM-2 masked-LM log-odds, ensembled, benchmarked on Protei
• ai-scientistBuild AI agents that automate scientific research — hypothesis generation, experiment design, data analysis, a
• ai-sdkAnswer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SD
• ai-sdk-coreBackend AI functionality with Vercel AI SDK v5 - text generation, structured output with Zod, tool calling, an
• ai-sdk-documentationThis skill should be used when working with Vercel AI SDK, AI Gateway, streamText, generateText, generateObjec
• ai-sdk-uiFrontend React hooks for AI-powered chat interfaces, completions, and streaming UIs with Vercel AI SDK v5. Inc
• ai-sdrAI SDR Skill workflow skill. Use this skill when the user needs When the user wants to deploy AI sales develop
• ai-sdr-setupDeploy AI SDR agents safely and effectively — vendor selection, pilot scope, guardrails, signal routing, human
• ai-search-gaps-to-social-campaignFind the AI-search prompts and topics where a brand is invisible (or losing to competitors) in SE Ranking, the
• ai-search-geoGet recommended by AI search (ChatGPT, Perplexity, Google AI Overviews, Gemini, Claude) using GEO / AEO: audit
• ai-search-hubRun the AI Search Hub browser automation scripts for Yuanbao, LongCat, Doubao, Qwen, Gemini, Grok, and MiniMax
• ai-search-optimizationUse to get a brand and its content CITED and RECOMMENDED by AI answer engines — the GEO (Generative Engine Opt
• ai-search-visibilityControl how ChatGPT, Perplexity, and Google AI Overviews describe you when a buyer, seller, or client research
• ai-securityUse when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data p