Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Pulls structured YouTube data — video and channel details, transcripts/captions, comments, playlists, and search — via the Crawlora API as clean JSON, with no yt-dlp or HTML scraping. Use when the user provides a YouTube URL or asks for a transcript, comments, channel/video metadata, or video search results.
Generate unified, on-brand Instagram Reel covers for Yuval (YUV.AI Neon Phoenix system) — the signature look is a giant Hebrew headline BEHIND the subject cutout + a punch line IN FRONT (depth effect), on rich black with a dim neural-net field, series-colored chip + phoenix mark. Use whenever Yuval asks for an Instagram/Reel/TikTok/YouTube cover, thumbnail, עטיפה, קאבר, תמבנייל, cover image for a video, or wants his Instagram grid to look consistent. One command per cover; background removal included in the pipeline.
Perform deep WCAG 2.1 AA compliance audits on UI code. Use this skill when the user wants an accessibility review, WCAG audit, a11y check, screen reader compatibility review, or keyboard navigation assessment. Also trigger when the user mentions 'accessibility', 'a11y', 'WCAG', 'screen reader', 'keyboard navigation', 'color contrast', 'ARIA', or asks 'is this accessible'. This goes beyond the design reviewer's basic accessibility checks to provide comprehensive WCAG criterion-by-criterion analysis
Check the Sonilo account's available services, rate limits, free-trial allowance, and usage/billing history. Use before calling a paid Sonilo tool to confirm it's available and whether free-trial runs remain, or when the user asks about their Sonilo usage, limits, or billing
Use whenever a contract or token address goes into code, config, or a transaction — a token, a router, a pool, a lending market, a bridge — including choosing which venue to route a swap through and reusing an address across chains. Has checked addresses for the major tokens, Uniswap, Aave, Compound, Chainlink, Safe, ERC-4337, ENS and Robinhood Chain.
Scaffold production-ready AI agents on Google's Agent Development Kit (ADK): ReAct-style single agents, multi-agent orchestration (Sequential/Parallel/Loop), tool wiring, evaluation, and optional Vertex AI Agent Engine deployment. Use when building, scaffolding, or deploying ADK agents on Google Cloud, or when wiring ADK tools and orchestration patterns. Trigger with "build an ADK agent", "scaffold an agent on ADK", or "deploy to Agent Engine".
Competitor ad intelligence analysis across Google, Meta, LinkedIn, TikTok, and Microsoft. Analyzes competitor ad copy, creative strategy, keyword targeting, estimated spend, and identifies competitive gaps and opportunities. Use when user says "competitor ads", "ad spy", "competitive analysis", "competitor PPC", or "ad intelligence".
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Multi-model agent orchestration using specialized agents for planning, coding, research, math/science, visual analysis, and adversarial review. Use when tasks are complex enough to benefit from different models' strengths, when you want adversarial review to catch blind spots, or when coordinating multi-step workflows across agent roles. Triggers on complex projects, multi-step tasks, architecture decisions, or when explicitly requested.
Coordinate multiple specialized Skills and Task Agents through parallel, sequential, swarm, hybrid, or iterative execution strategies. Use when orchestrating multi-worker workflows, managing dependencies, or optimizing complex task execution with quality gates.
Installs agentic guardrails into a Python repo — Claude Code hooks, a Stop gate that signs off only what pre-commit accepts, vetted public skills — and troubleshoots hooks that don't fire or block. Use for 'add Claude Code hooks', 'write an AGENTS.md', 'make this repo agent-ready', 'agent keeps bypassing checks', 'agent says done but pre-commit fails'. Not for authoring the pre-commit config.
Search, list, and resume AI agent sessions across Claude Code, Codex CLI, Gemini CLI, opencode, Hermes Agent, and Cline CLI. Use when the user asks to find a past conversation, search session history, resume a previous session, list recent agent activity, or check what was discussed in a prior session. Also use when asked to "find that conversation where I...", "resume my last codex session", "read latest convo", "read last messages", "what did I work on yesterday", "search my claude history for X", or gives an agent session id such as `ses_...`, a UUID, or a Cline id like `1782988565588_qqrxi`.
Guide for orchestrating and controlling Claude Code agent teams. Use when working with or managing multi-agent team coordination in Claude Code, including: (1) Creating and starting agent teams, (2) Controlling teammates (display modes, task assignment, delegation), (3) Best practices for parallel work, (4) Troubleshooting team issues. Covers concepts like team lead, teammates, shared task lists, and inter-agent messaging.
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.
Code review, design support, and refactoring based on DDD Aggregate design rules. Guided comprehensively by Evans Rules, Vernon's 4 Rules, and Design by Contract, it covers aggregate boundary definition, invariant verification, immutable design, ID references, eventual consistency, and domain event collaboration. Use this skill whenever any of the following applies: - New design, implementation, or refactoring of Aggregates (in any language) - Code review of existing aggregates or entity classes from a DDD perspective - Deciding aggregate boundaries ("Should A and B be in the same aggregate?" "Is this aggregate too large?") - Designing invariants and consistency boundaries within an aggregate - Deciding how aggregates collaborate (domain events, eventual consistency, Saga pattern) - Refactoring mutable aggregate code into immutable design - Detecting and fixing encapsulation violations such as public fields, direct references, and push/append Keyword examples: 集約, Aggregate, aggregate boundary, 集約ルート, AggregateRoot, エンティティ設計, DDD実装, Vernon Rules, Evans Rules, 集約の分割, 真の不変条件
Implement VADER sentiment analysis for social media text scoring. Use this skill when the user needs to analyze sentiment in tweets, reviews, or social posts, compute compound sentiment scores, or classify text polarity — even if they say 'is this positive or negative', 'sentiment of these comments', or 'social media mood analysis'.
Perform SysOM deep diagnosis on Alibaba Cloud PAI products (EAS / DLC) to identify root causes of instance-level issues. Use when users report: - EAS instance anomalies, GPU OOM (out of memory), GPU memory out-of-bounds errors - Slow first-token latency, uneven request scheduling across model service instances - OOM (Out Of Memory), insufficient memory, processes being killed - Abnormally high system load, high IO latency, network jitter, packet loss - Instance crashes, unexpected restarts, kernel oops - DLC training job hangs, communication timeouts, per-step throughput degradation - Any issue related to EAS instance health, DLC job health, or underlying compute resource performance
Search Alibaba Cloud help documentation on help.aliyun.com (cn) and www.alibabacloud.com (intl) in zh, en, tc, ja, id, pt-br and experimental fr, with ranked results, and verify OpenAPI contracts (parameters, error codes, RAM permission points) against api.aliyun.com metadata. Use when the user asks how to configure a product, looks up an error code or message, checks quota or limits, asks about billing rules, wants best practices or troubleshooting guides, confirms API parameter semantics, or reads a help document. Triggers: "Alibaba Cloud documentation", "help center", "help.aliyun.com", "product how-to guide", "error code meaning", "what does this error mean", "how to fix this error", "quota and limits", "billing rules", "RAM permission point", "API reference", "troubleshooting guide", "best practice", "read help document", "international site documentation". Do not use it to change cloud resources or to diagnose an incident when a diagnosis skill applies
Batch health inspection for Alibaba Cloud RDS MySQL instances. Supports single, multiple, or all-instance global scan with configurable time window (default 7 days, max 30). Outputs one HTML report per instance plus a summary HTML. Dimensions: instance basics, resource utilization (CPU/memory/disk/IOPS/connections), CloudMonitor alert history, top 20 space-consuming tables (DAS), slow log statistics (DAS), kernel-version / expiration checks. Cluster instances auto-detected; per-node metrics and slow logs. Triggers: RDS inspection, RDS health check, RDS MySQL inspection, Alibaba Cloud RDS inspection, batch/global/multi-instance inspection, slow log analysis, space analysis, RDS 巡检, 阿里云 RDS 巡检, 数据库巡检, 批量巡检, 慢日志分析, 表空间分析.
Deploys websites, web apps, APIs, and agents to the internet with a strict pre-deploy audit and a preview → health-check → prod flow. Handles plain HTML/CSS/JS pages and static sites (Astro, Hugo, Jekyll, Eleventy, Vite) as well as Next, Remix, Nuxt, SvelteKit, FastAPI, Flask, Express, MCP servers, Claude Agent SDK scripts, Python workers, and Dockerized projects. Routes to free static hosts — Cloudflare Pages, Netlify, GitHub Pages, Render — or to Vercel, Railway, Docker+SSH VPS, or a cloudflared tunnel, and can also run the project locally. Use when the user says "/all-deploy", "/deploy", "/despliega", "deploy this", "ship this", "push to prod", "get this online", "publish my website", "sube mi página web", "publicar mi página", "hosting gratis", "free hosting", "custom domain", "dominio propio", "run it locally", "corre esto localmente", or otherwise asks to publish a site or project to a URL.
Use when the user wants to evolve an ML model/program through population-based search rather than a single sequential refine loop — a generational evolution where parallel proposers each apply one small SEARCH/REPLACE diff to a parent, scored by a cascade-evaluated training run, and children are kept in a MAP-Elites archive across islands (with migration + checkpointing) so diverse high performers survive. A finite, bounded-parallelism re-creation of AlphaEvolve/OpenEvolve, bent for ML autoresearch. Runs to a fixed compute budget or until interrupted. Not for the sequential single-thread autoresearch loops (one change → measure → keep/revert), and not for verifying a known bug or external claim — this is parallel, diversity-preserving search over a program.
High-performance containerized web scraper (Docker + Crawlee + Playwright). Use when user mentions any of these: 爬虫, 爬取, 抓取, 采集, 数据采集, 爬数据, 抓数据, 获取数据, scrape, crawl, extract, fetch data, pull data, 亚马逊, Amazon, ASIN, BSR, Best Sellers, 畅销榜, 热销榜, 新品榜, 飙升榜, 排行榜, 选品, 竞品分析, 竞品调研, 市场调研, 品类分析, 类目分析, 产品调研, 月销量, bought in past month, 销量, 评论数, 价格对比, YouTube, 视频字幕, 转录, transcript, 网页内容, 网站数据, 页面抓取, 动态页面, TikTok, Twitter, X, 社交媒体数据, 帖子内容, 关键词搜索, 搜索结果, search results, 产品详情, 产品信息, listing数据, listing分析, top 100, top sellers, 热门产品, 爆款, 跑量款, 价格带, 评分分布, review分析, 评论分析
Inspect and compare offline AI evaluation experiments, diagnose case-level regressions, and follow scorer history across application, model, or prompt changes. Use when a user asks whether an offline run improved, why a case failed, how scores changed between runs, or how to publish externally computed offline results. Covers immutable scorer versions, comparable dataset cohorts, incomplete coverage, and selective payload reads.
Researches anime and manga titles via the Crawlora API—search, title details, characters, staff, recommendations, rankings, and airing schedules—and returns clean JSON. Use when the user wants details about an anime or manga, its cast or staff, similar titles, seasonal rankings, or what's currently airing.
Extracts highlights, annotations, and book data from Apple Books via MCP. Use when: user asks to export book highlights, extract annotations with colors, search highlights across books, create highlight summaries, or match books from a reading list against their Apple Books library. Covers efficient batch color extraction (5 calls instead of 150+), annotation-to-book matching, and markdown export patterns.
Instrument browser/web apps with the Application Insights JavaScript SDK (@microsoft/applicationinsights-web). Use for Real User Monitoring (RUM) — page views, clicks, AJAX/fetch dependencies, exceptions, custom events, and browser-side GenAI agent traces correlated to backend OpenTelemetry traces. Covers SDK Loader Script and npm setup, framework extensions (React, React Native, Angular), Click Analytics, telemetry initializers, and OTel GenAI semantic conventions for agent/tool/model spans emitted from the browser.
Advanced Product Quality Planning (APQP) — plan and track a new product launch through all 5 phases, identify deliverables per phase, run gate reviews, and ensure quality outputs are complete before Start of Production (SOP). Use when launching a new part, managing an APQP project, or auditing APQP completeness. Covers AIAG APQP 2nd edition and IATF 16949 §8.3.
Aptos blockchain and Move language expert. Covers Move programming (abilities, generics, resources), Aptos framework modules, smart contract development, token standards (Coin, Fungible Asset, Digital Asset), object model, gas optimization, and dApp integration. Triggers on Aptos, Move language, Move smart contract, Aptos blockchain, abilities, generics, resources, fungible asset, digital asset.
Use when recording an architectural decision so future maintainers know why—phrases like "ADR", "architecture decision record", "why did we pick X", "lightweight architecture documentation", "decision log", "should this be an ADR", "tribal knowledge", "we chose this two years ago and now nobody remembers why". Defines an ADR as a short, structured document capturing what was decided, why, alternatives considered, and consequences—written at the time of the decision and kept in the repo
Use when protecting a service from a degraded or failing dependency—phrases like "circuit breaker", "bulkhead", "retry policy", "exponential backoff", "fail fast", "fallback", "cascade failure", "open/closed/half-open state", "resilience4j", "Polly", "Hystrix". Defines the circuit breaker pattern and related failure-isolation tools (bulkhead, retry-with-backoff, timeout, fallback)
Use when separating read and write models — phrases like "CQRS", "Command Query Responsibility Segregation", "read model vs write model", "denormalized read side", "materialized view", "different scaling for reads and writes", "command bus", "query bus", "should we use CQRS here". Defines CQRS as keeping reads and writes on separate models, with picking criteria that resist over-application.
Use when designing a system around asynchronous events—phrases like "event-driven architecture", "EDA", "event broker", "Kafka", "publish-subscribe at scale", "event-first design", "choreography vs orchestration", "event broker vs message queue", "broker topology vs mediator topology". Defines event-driven as a macro architectural style where components emit and react to events, not direct calls
Use when persisting state as a sequence of events—phrases like "event sourcing", "event store", "append-only log of facts", "replay events to rebuild state", "audit log as source of truth", "temporal queries", "snapshot", "should we event-source this aggregate". Defines event sourcing as storing the history of what happened as the canonical state, with current state derived by replay
Use when enforcing architectural characteristics through automation — phrases like "architecture fitness function", "evolutionary architecture", "architecture tests", "ArchUnit", "dependency rules in CI", "automated architecture checks", "guardrails", "drift detection". Defines fitness functions as automated checks that verify architectural characteristics on every change, catching drift before it accumulates.
Use when picking a software architecture style or pattern for a system — phrases like "what architecture should we use", "monolith vs microservices", "should we go event-driven", "is this a CQRS situation", "do we need a saga here", "should we use hexagonal architecture", "what's the right architectural style for this problem". Diagnostic mode that routes a stated problem to the relevant architecture skill or rules patterns out.
Use when discussing layered architecture (n-tier) — phrases like "layered architecture", "n-tier", "presentation / business / persistence layers", "should we go layered", "leaky layer", "sinkhole anti-pattern", "open vs closed layers". Defines the layered style with its strict top-down dependency rule, the open/closed layer concept, and the most common failure modes.
Use when designing or reviewing a microservices architecture — phrases like "microservices", "should we split this service", "service boundaries", "bounded context per service", "API gateway", "backend for frontend", "BFF", "service mesh", "microservices vs monolith", "database per service", "data ownership". Defines microservices as independently deployable services aligned with business capabilities — and the discipline of resisting the style until the monolith proves inadequate.
Use when migrating a legacy system incrementally — phrases like "strangler fig", "strangler pattern", "incremental migration", "monolith to microservices", "rewrite without big bang", "replace legacy in place", "facade in front of the legacy system", "anticorruption layer". Defines Fowler's Strangler Fig as the migration discipline of gradually replacing legacy functionality behind a stable facade, never doing a big-bang rewrite.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.