В каталоге 182 820 навыков в 14 категориях.
Designs a quality-control and curation process for AI-generated content or decisions — the shift from 'creator' to 'cura...
Evaluate AI-generated output quality using LLM-as-judge techniques, multi-dimensional rubrics, and bias mitigation. Use...
当拿到一段 AI 回答、准备直接复制去用之前使用。把回答拆成可检验的声明（链接、库名与版本、论文 DOI、命令行参数、API 名、数字、引文），按"用错了会炸多大"排序，为每条配一条最直接的核验路径；产出声明台账、核验计划和"现在可以用 /...
Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured outp...
Ensures all AI-generated output fields have proper validation. Auto-activates on "AI 輸出", "LLM", "Gemini", "GPT", "trunc...
AI出力の品質を自動検証するスキル。事実確認、論理性、一貫性、幻覚（ハルシネーション）検出、バイアス分析、安全性チェックを実施し、改善提案を提供。
Check AI output before you trust or use it — where it's likely wrong, what to verify, and how to catch confident-soundin...
AI Personal Assistant network skill for multi-agent PA coordination. Use when: contacting another PA, coordinating with...
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。
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。
ทำงานร่วมกับ AI แบบ pair programming เพื่อเพิ่ม productivity และ code quality
Pull structured data from messy text using AI. Use when parsing invoices, extracting fields from emails, scraping entiti...
Write operator-facing and public documentation plans for AI-Controlled Party mixer/Soundcraft Ui24R scene arming. Use fo...
Detects AI-generated writing patterns and suggests authentic alternatives. Auto-applies when reviewing content, editing...
Use this skill for game AI: "enemy AI", "state machine", "FSM", "patrol", "pathfinding", "NPC behavior", "chase", "flee"...
PDF 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。
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 清单。
Select and design AI pilots with clear hypotheses, success metrics, guardrails, and decision rules. Use when Codex is as...
Use when creating or evolving CI/CD pipelines: stack-aware generation for GitHub Actions and Azure Pipelines with securi...
Orchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow...
Use when changing the AI workflow, embeddings, Qdrant integration, newsletter intake, relevance scoring, summarization,...
Use when a founder needs to prepare a live roadshow or defense (路演、答辩) for a government park, OPC community, incubator a...
Use when an approved spec exists and needs to be broken into executable tasks with agent assignments. Creates the implem...
Plan a multi-phase AI feature before building it. Use when you have a PRD or project idea and need to figure out the exe...
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。
Generate multi-person talking head podcast videos from scratch using AI — character creation, TTS, avatar animation, and...
Use when creating and automating AI-powered podcasts. Generate episodes from topics, URLs, or documents with multiple AI...
AI governance policy creation for nonprofits and enterprises with frameworks, risk assessment, ethical guidelines, and c...
Chooses DPO, GRPO/RLVR, reward models, and over-optimization controls. Use when adapting a pretrained or SFT model with...
Use when documenting an incident, outage, or production failure using the structured DERP model (Detection, Escalation,...
PPT 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。
Use when creating pull requests: governed PR workflow with commit pipeline, pre-push gates, auto-generated summary, and...
Use when reviewing AI-generated, Vibe Coding, or agent-authored PRs, diffs, commits, or merge requests for fake logic, f...
Builds a GPT and BPE tokenizer from scratch. Use when implementing autograd, attention, a nanoGPT loop, muP hyperparamet...
When the user wants to price an AI product, choose a charge metric, design pricing tiers, or optimize margins. Also use...
Review an AI system's compliance with GDPR, CCPA, and sector-specific privacy regulations — covering lawful basis for AI...
Protocolo de autodiagnostico contra os 5 problemas mais comuns da IA ao programar. Detecta overengineering, codigo dupli...
Ensure the AI coding procedure ecosystem stays current and consistent when new elements are introduced. This skill provi...
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in produ...
AI product engineering covering LLM integration patterns, RAG architecture, prompt engineering, and production AI system...
Use when building AI features into a product: LLM integration, RAG pipelines, guardrails, streaming, AI UX, prompt engin...
You are an AI product engineer who has shipped LLM features to millions of users. You've debugged hallucinations at 3am,...
Every product will be AI-powered. The question is whether you'll
Place one supplied real product into a new commercial studio, material, lifestyle, or campaign-ready scene while preserv...
Structure AI and ML product decisions with the rigour of any product decision. Use when building AI-powered features, ev...
Design, specify, map, evaluate, or improve an AI assistant, LLM feature, copilot, chatbot, agent, recommendation, genera...
Transition from traditional PRDs to "Evals" (evaluations) to guide AI model behavior. Use this skill when launching new...
AI 产品经理 (LLM 应用 / 生成式 AI / Agent 产品 / Copilot 嵌入 — 跨模型评估 / 工作流设计 / 产品-工程协同) (AI Product Manager — LLM application / gene...
Specialized skill for AI product photography. Use when you need professional product shots, hero images, lifestyle photo...
Create an AI Product Strategy Pack (thesis, prioritized use cases, system plan, eval + learning plan, agentic safety pla...
Help users define AI product strategy. Use when someone is building an AI product, deciding where to apply AI in their p...
A framework to assess and integrate AI into your product strategy by mapping core customer problems to AI capabilities....
Structured teardown of AI products (ChatGPT, Claude, Gemini, Perplexity, Copilot, etc.). Analyzes product decisions, UX...
Specialized skill for AI product video generation. Use when you need product reveals, animated product shots, hero video...
Use when optimizing prompts, skill descriptions, or agent instructions for clarity, specificity, and behavioral effectiv...
Design the prompt and context for an AI feature — system prompt, how context is assembled per request, examples, output...
AI engineering skill for prompt optimization, context inference, and intelligent command routing across different models...
Prompt engineering for production LLMs — structured outputs, evals, RAG, tool workflows, multimodal prompting, and safet...
Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vu...
Test LLM-backed apps for prompt injection (direct + indirect) and its consequences: data exfil, tool/function abuse, gua...
Systematically extract hidden system prompts, core directives, and invisible context intentionally concealed within Lar...
Expert assistant for managing AI prompts, features, and configuration in the KR92 Bible Voice AI system. Use when creati...
Review one prompt for an AI feature — unclear or conflicting instructions, missing context, gaps in the output format, m...
Effective communication with the assistant: context-first prompting, phased work from requirements to design to tasks, i...
Use when a README, an MR description, release notes or a changelog is drafted or reviewed and might read as machine-writ...
Official Cohere TypeScript SDK patterns -- CohereClientV2, chat, embeddings, rerank, RAG with citations, tool use, strea...
Debug and troubleshoot AI/LLM provider integrations. Use when investigating API failures, fallback chain issues, model s...
ElevenLabs voice AI SDK patterns for TypeScript/Node.js -- text-to-speech, streaming, voice cloning, speech-to-speech, p...
Official OpenAI SDK patterns for TypeScript/Node.js — client setup, Chat Completions, Responses API, streaming, structur...
Use whenever a product calls Gemini, DeepSeek, or other LLM APIs; design a Gemini-free-first, project-aware, secure prov...
Bounded-authority AI proxy that occupies the human seat at interactive checkpoints of unattended runs: answers intake qu...
Prune agent scratch directories on macOS by moving clearly outdated `.ai/` files into `.ai/archive/YYYY-MM-DD/` and tras...
Grounding and stability protocols for AI during intense work. Anti-dissociation, integration without fading, staying on...
Review EXISTING test code for quality, smells, and testability issues. Detects test smells across six dimensions — reada...
AI Questioning Pattern (MANDATORY)
雷达Skill（AI Radar）——零API、零Key、零服务器的中文AI资讯查询。数据来自 AI News Radar 在 GitHub Pages 上公开的静态 JSON（GitHub Actions 每日自动更新），curl 即取，...
Complete RAG and search engineering skill. Covers chunking strategies, hybrid retrieval (BM25 + vector), cross-encoder r...
Patterns for RAG pipelines, vector databases, embedding strategies, context-window management, and LLM orchestration. Us...
Poison a RAG/knowledge-base pipeline so retrieved content hijacks the model (indirect prompt injection at scale) or exfi...
Assess organizational AI readiness — capabilities, gaps, adoption roadmap for strategic planning.
AI README 生成器 - 扫描代码并为项目生成 AI/人类共用的规则文档（AGENTS.md + .cursor/rules/ai-readme/）。当用户说 /ai-readme、@ai-readme、生成 AI 文档、生成项目规则...
Make any repo AI-ready — analyzes your codebase and generates AGENTS.md, copilot-instructions.md, CI workflows, issue te...
**ANALYSIS SKILL** — Analyze any repository and generate AI-ready configuration — a canonical AGENTS.md, thin per-tool p...
Installs John Papa's ai-ready skill, which makes a repository AI-ready by generating AGENTS.md, copilot-instructions.md,...
Make AI solve hard problems that need planning and multi-step thinking. Use when your AI fails on complex questions, nee...
AI-powered recommendation engine specialist using Google AI SDK for personalized content suggestions
Build AI that recommends products, articles, or content based on user preferences. Use when building product recommendat...
Plan attack tests for an AI feature — direct and indirect prompt injection, jailbreaks, system-prompt and data leakage,...
Design and operate a continuous AI red team program — covering team structure, scope definition, attack scenario librari...
Run structured AI red team exercises for jailbreak resistance, data exfiltration risk, harmful output controls, and agen...
Strip PII and sensitive data from text before processing with AI. Use when redacting personal information, GDPR complian...
AI and LLM red-teaming skill for evaluating prompt injection, jailbreak, data exfiltration, tool abuse, agent hijack, RA...
AI/LLM red-team assessment using the OWASP LLM Top 10 (2025) + OWASP AI Testing Guide (AITG v1, Nov 2025) frameworks, pl...
Turn raw talking-head footage (a camera video, a separate mic recording, and one line of notes) into a finished vertical...
Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, autom...
Regression testing strategies for AI-assisted development — sandbox-mode API testing without database dependencies, auto...
Use when preparing a release: aggregated GO/NO-GO gate checking coverage, security, tests, lint, and dependency vulnerab...