В каталоге 182 820 навыков в 14 категориях.
Request or contribute a new AI skill that does not exist yet. Use when DSPy supports something but there is no skill for...
Automates AI briefing preparation and technology research. Use for regular updates on AI trends, tools, and models relev...
Move fast AND rigorously through the full AI/ML research loop: framing a testable hypothesis, reviewing the literature,...
Produces executive-level research — market sizing, competitor mapping, trend analysis, and strategic intelligence — grou...
Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the...
文献综述助手适合市场营销、运营、software、教育培训在用户提出“文献重点是什么”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研究摘要、对比洞察、决策建议。
研究打磨助手适合市场营销、运营、software、教育培训在用户提出“研究问题清楚吗”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研究摘要、对比洞察、决策建议。
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an...
AI research: ideas, ML papers, plots, presentations, artifacts and scoped experiments; 10 cloud modules, 98 in full loca...
End-to-end research paper generation, review, and revision for ML/AI/CV/NLP projects from repositories, notes, experimen...
Tests whether an AI opportunity is framed as automating an existing process (1st-order) or as a genuine value-chain resh...
Use when git reports merge conflicts during rebase, merge, cherry-pick, or revert operations.
AI応答を洗練・改善するスキル。粗い出力を流暢で専門的な文章に変換。構造化、明確化、詳細化、トーン調整、専門性向上、読みやすさ改善を実施。
Review design or implementation of a feature or a fix
Use when reviewing code changes (PRs, diffs, or files) with parallel specialized agents. 8-agent review with self-challe...
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition...
Get AI code review from a second model (Gemini/OpenAI) mid-session via CLI. Use when asked to review code, get a second...
Analyze and execute AI PR review feedback with fix/skip decisions. Use when a user asks to parse an AI review, apply sel...
Using multimodal LLMs (Gemini, GPT-4o-audio and similar) as a second pair of ears on a mix or radio cut: chunking and pr...
RevOps 诊断助手适合销售、市场营销、运营、software在用户提出“收入流程哪里堵”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。
Rewrite text to match a different tone, reading level, or audience using AI. Use when rewriting content in a different t...
Identifying, assessing, and mitigating risks in AI systems including bias, safety, privacy, security, and ethical concer...
AI governance and risk management for mid-2026 — ISO/IEC 23894 risk process, ISO/IEC 42001 management system, NIST AI RM...
Create AI risk registers for agentic AI, GenAI pilots, AI vendors, and AI-enabled workflows. Use when Codex is asked to...
Audit whether the organisation's AI spend actually paid — measured against baselines, not vendor math or vibes. Use when...
Builds a detailed ROI model for AI tool adoption using team size, developer costs, and workflow-specific time savings be...
Add rules or skills adapters for a new AI tool and wire config, CLI, completion, and tests.
Standards-compliant lifecycle tool for agent knowledge and capabilities: author in .ai-rulez/, generate for 52 harnesses...
Unified governance for local AI tools and developer runtimes. Use this skill to inventory installed AI models, CLIs, and...
AI Runtime分层记忆系统，支持SQL风格的事件查询、时间线管理，以及记忆的智能固化和检索，用于项目历史追踪和经验传承
外部CLI工具装备系统，支持10+个成熟CLI工具的深度整合，包括fzf、ripgrep、jq等，提供模糊搜索、代码查找、JSON处理等高级功能
AI Runtime工具装备系统，支持8个内部专业工具和10+个外部CLI工具的整合管理，提供工具发现、执行和配置功能，遵循整合优于创造的设计理念
Apply the AI SAFE² framework (Sanitize & Isolate · Audit & Inventory · Fail-Safe & Recovery · Engage & Monitor · Evolve...
Implement safety guardrails, red-teaming, and alignment evaluation for AI systems
Audit AI systems for safety, bias, and responsible deployment
Plan AI safety measures including alignment, guardrails, red teaming, and regulatory compliance (EU AI Act, NIST AI RMF)...
Use this skill when you need evidence-bounded safety policy, abuse categories, refusal/redirect behavior, privacy, escal...
销售话术准备助手适合销售、市场营销、运营、software在用户提出“销售话术怎么准备”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"、"帮我想想怎么推AI"、"业务部...
销售辅导助手适合销售、市场营销、运营、software在用户提出“话术哪里弱”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。
Sizes models and token budgets using Kaplan/Chinchilla scaling laws. Use when reasoning about compute-optimal N and D, t...
Use when designing schemas, writing migrations, optimizing queries, or managing data lifecycle across PostgreSQL, MySQL,...
Schema 标记助手适合市场营销、运营、内容创作者、software在用户提出“结构化数据对吗”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Schema 建议、FAQ 结构、上线检查清单。
SakanaAI AI-Scientist integration — automated scientific discovery via Hermes. Generate ideas, run experiments, write pa...
Score, grade, or evaluate things using AI against a rubric. Use when grading essays, scoring code reviews, rating candid...
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK function...
回答 AI SDK 相关问题并协助构建 AI 功能。适用于：(1) 询问 generateText、streamText、ToolLoopAgent、tools 等 API；(2) 构建 AI 智能体、聊天机器人或文本生成；(3) 关于 A...
Vercel AI SDK v6 patterns for streaming chat, structured outputs, agents, and tool workflows.Load when building AI-power...
Comprehensive guide to AI SDK v6 for agent development, tool definitions, multi-step agentic workflows, and result extra...
Build AI features with the first-party Laravel AI SDK (Laravel 13+); agents, embeddings, images, audio, and tool calling...
Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured outp...
Vercel AI SDK 5 patterns. Trigger: When building AI chat features - breaking changes from v4.
Vercel AI SDK 5 patterns. Trigger: When building AI features with AI SDK v5 (chat, streaming, tools/function calling, UI...
Vercel AI SDK v6 development. Use when building AI agents, chatbots, tool integrations, or streaming applications with t...
Expert guidance for building AI agents with ToolLoopAgent (AI SDK v6+). Use when creating agents, configuring stopWhen/p...
Validate ai sdk concurrency limit, including boundary cases, evidence capture, and safe failure handling.
Expert guidance for AI SDK Core: text generation, structured data, tool calling (tool/dynamicTool), MCP integration (cre...
Build backend AI with Vercel AI SDK v6 stable. Covers Output API (replaces generateObject/streamObject), speech synthesi...
Vercel AI SDK v5 for backend AI (text generation, structured output, tools, agents). Multi-provider. Use for server-side...
TRIGGER when working with ai-sdk, Laravel's official first-party AI SDK. Activate when building or editing AI agents, ch...
Query and manage local Vercel AI SDK documentation mirror (271 docs across 24 sections). Search AI SDK UI hooks, streami...
This skill should be used when working with Vercel AI SDK, AI Gateway, streamText, generateText, generateObject, streamO...
Integrate Vercel AI SDK for LLMs, Chatbots, Generative UI, and Agentic Workflows.
Integrate Vercel AI SDK applications with You.com tools (web search, AI agent, content extraction). Use when developer m...
Install the Vercel AI SDK with AI Elements components. Build a streaming chat interface with the useChat hook.
Expert guidance for building chat UIs with AI SDK React hooks. Use when: (1) Building chatbots with useChat hook, (2) Im...
Build React chat interfaces with Vercel AI SDK v6. Covers useChat/useCompletion/useObject hooks, message parts structure...
Frontend React hooks for AI-powered chat interfaces, completions, and streaming UIs with Vercel AI SDK v5.Includes useCh...
Vercel AI SDK v5 React hooks (useChat, useCompletion, useObject) for AI chat interfaces. Use for React/Next.js AI apps o...
Validate ai sdk user session scope, including boundary cases, evidence capture, and safe failure handling.
AI SDR Skill workflow skill. Use this skill when the user needs When the user wants to deploy AI sales development reps,...
When the user wants to deploy AI sales development reps, automate sales qualification, build signal-to-action routing, o...
Integrates the AI Search API (Gemini 2.5 Flash + Google grounding) to perform web-aware intelligent search and return ci...
Use for "which of our pages do ChatGPT, Perplexity or Gemini cite", "does our AI search visibility bring traffic, signup...
Find the AI-search prompts and topics where a brand is invisible (or losing to competitors) in SE Ranking, then turn tho...
Use this skill for AI search optimization, generative engine visibility, entity clarity, citation readiness. Trigger whe...
Run the AI Search Hub browser automation scripts for Yuanbao, LongCat, Doubao, Qwen, Gemini, Grok, and MiniMax. Use this...
Use to get a brand and its content CITED and RECOMMENDED by AI answer engines — the GEO (Generative Engine Optimization)...
Use when a request concerns AEO/GEO demand research, AI-answer or generative-search query-corpus research, entity or sou...
Ask the AI assistants buyers use (ChatGPT, Gemini, Perplexity and others) the questions they would ask, record whether t...
Use when the user asks whether ChatGPT, Claude, or Perplexity can find or cite them, or wants a personal GEO / AI-search...
Build AI that searches your documents and answers questions. Use when building a knowledge base, help center Q&A, chatti...
Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning e...
Use when scanning for security vulnerabilities: SAST, dependency audit, secret detection, and SBOM generation with OWASP...
This skill should be used when the user asks to "scan AI systems for security threats", "check for prompt injection vuln...
Security engineering for LLM applications and AI agents: OWASP Top 10 for LLM Applications (2025), OWASP MCP Top 10 (Bet...
Use when attacking an AI/ML system or model — prompt injection & jailbreaks (Crescendo, Skeleton Key, Best-of-N), RAG/ve...
Automatically applies when securing AI/LLM applications. Ensures prompt injection detection, PII redaction for AI contex...
Enterprise AI security - OWASP LLM Top 10, prompt injection defense, guardrails, PII protection
Harden AI/LLM deployments against prompt injection, data exfiltration, model theft, and supply chain attacks. Covers inp...
Strategy, writing, experiment organization, evidence validation, reproducible result plotting, LaTeX engineering, rebutt...
Use when reviewing or designing an AI or agent system, prompt, retrieval pipeline, model-generated output, tool call, MC...
Test AI systems: model endpoints for jailbreaks and leakage, model files for malicious pickle code, and agentic apps/MCP...
Make an LLM app disclose sensitive data it should never reveal: training-data memorization, secrets/PII in RAG context,...
When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Als...
Optimize content to get cited by AI search engines — ChatGPT, Perplexity, Google AI Overviews, Claude, Gemini, Copilot....
SEO/AEO 诊断助手适合市场营销、运营、产品、software在用户提出“这篇能被 AI 引用吗”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摘要、诊断结论、行动建议和可复用交付物。
Optimize content to rank in AI search engines (AI Overviews, Perplexity, ChatGPT) via generative engine optimization (GE...