Skills
100,696 packaged capabilities and playbooks for agents. Install any of them with one command.
All
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Virtual memory skill for paging, page tables, and TLB. Use when explaining page faults, multi-level page tables, TLB behavior, or virtual vs physical addressing. Activates on queries about virtual memory, page table, TLB, page fault, mmap paging, or x86-64 paging.
Faithfully archive public WPS/KDocs/金山文档 links, especially embedded ProcessOn .pof mind maps and canvases, as raw source data, original SVG/PNG, and Markdown. Use when a user gives a kdocs.cn or wps.processon.com link and asks to scrape, save, download, 扒下来, 归档, or 转 Markdown without logging in or saving the document to an account.
Use when you need to write or improve integration tests — including Testcontainers with @ServiceConnection, @DataJdbcTest persistence slices, TestRestTemplate or MockMvcTester for HTTP, data isolation, and container lifecycle management for Spring Boot 4.0.x. This should trigger for requests such as Review Java code for Spring Boot integration tests; Apply best practices for Spring Boot integration tests in Java code; Write @SpringBootTest integration tests with Testcontainers; Configure dynamic properties for Spring integration tests; Review Spring Boot integration test profiles. Part of Plinth Toolkit
Manage container registries including ECR, ACR, GCR, and Docker Hub. Push and pull images, configure authentication, set up repository policies, and implement image lifecycle management. Use when working with container image storage and distribution
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
Direct game art and creative vision. Turn GAME_DESIGN into ART_DIRECTION defining a recognizable visual identity, functional visual and audio feedback, and key in-game moments. Use for what should the game look like, set the art direction, define the visual style. 游戏美术与创意方向。把 GAME_DESIGN 转成 ART_DIRECTION，定义可辨识的视觉风格、服务玩法的视听反馈和关键游戏时刻。用于判断游戏应该长什么样、制定游戏美术方向等需求。
Turn roughly 5-second voiceover scripts, opinion statements, or abstract concepts into high-end editorial halftone paper-collage B-roll. Must be used when the user says "collage b-roll", "paper collage b-roll", "halftone collage", "use this script for a collage visual", "make a collage animation from this script", or "gbro-collage-broll", or wants to turn a line of script into a collage visual metaphor. Three-stage approval is mandatory: first propose only the visual metaphor; after the user confirms, generate the color collage still frame; after the still frame is confirmed again, call Gemini Omni Flash by default to generate the first-and-last-frame assembly animation. The default video model is fixed to gemini-omni-flash-preview, no longer defaulting to Veo; switch only when the user explicitly specifies another model.
Audit applications and infrastructure handling Protected Health Information against HIPAA — Security Rule (administrative, physical, technical safeguards), Privacy Rule, Breach Notification Rule, plus HITECH. Covers ePHI scoping, the 18 HIPAA identifiers, Business Associate Agreement (BAA) chain-of-liability, minimum-necessary standard, and breach notification timing. Use when the user mentions 'HIPAA,' 'HIPAA Security Rule,' 'HIPAA Privacy Rule,' 'PHI,' 'ePHI,' 'protected health information,' 'BAA,' 'business associate agreement,' 'covered entity,' 'business associate,' 'minimum necessary,' 'HIPAA breach,' 'HITECH,' 'healthcare compliance,' 'medical data,' 'patient data,' or audits any system that creates, receives, maintains, or transmits PHI.
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.
Audits and fixes both halves of being found — classic search and AI answers. Search side: rankings, site structure, page speed, titles and descriptions, and content that answers what customers search for. AI side: whether assistant crawlers can reach the site, pages render without JavaScript, an llms.txt file, schema.org data, and presence in the directories assistants read. For online stores it also runs a bulk catalog cleanup, rewriting product titles, descriptions, alt text, and SEO fields in approved batches. Works on any public website with no connector. Use this whenever the owner talks about being found online, including "nobody finds us on Google," "how do I show up in ChatGPT," "make my website AI friendly," "SEO audit," "GEO," "AEO," "AI search visibility," "my competitor ranks above me," "fix my product listings," or "I asked an AI about my industry and we weren't in the answer."
Escolher, compor e adaptar uma biblioteca de componentes React com Tailwind CSS para landing pages, marketing, navegação, formulários, dados, feedback e tipografia. Use quando uma interface React precisar de referências TSX reutilizáveis, exemplos visuais ou uma composição de página; use sempre em conjunto com a skill specsfy-specialist-ui-design, que governa hierarquia, layout, estados e coerência visual.
Detect and analyze adverse drug event signals using FDA FAERS reports, drug labels, and disproportionality statistics (PRR, ROR, IC). Generates quantitative safety signal scores (0-100) with evidence grading. Use for post-market surveillance, pharmacovigilance, drug safety assessment, regulatory submissions, and detecting rare AE signals not visible in clinical trials.
This skill should be used when the user asks to "verify code", "run verification", "check quality", "validate changes", or before creating a PR. Provides comprehensive verification including build, type check, lint, tests, security scan, and diff review.
Create and localize App Store in-app events, upload event media, and submit or recover event review submissions with asc. Use when managing in-app events, event card or details page assets, or event-specific submission errors.
Fetch A-share market intelligence from public sources such as CLS, Wallstreetcn, Jin10, Sina 7x24, Eastmoney Express, policy announcements from the CSRC, PBOC, SSE, and Ministry of Finance, and Eastmoney stock forums. Collect stock-related news, policies, and sentiment, and output structured JSON or Markdown. Trigger when users mention A-share market news, fetching news, individual stock news, policy and regulation, stock forum sentiment, CLS, Eastmoney Express, or market sentiment, or need public information about a specific stock aggregated. Also applies to casual requests such as “Check what news there is about 000001 recently.”
This skill should be used when executing Bankr requests, submitting prompts to Bankr API, polling for job status, checking job progress, using Bankr MCP tools, or understanding the submit-poll-complete workflow pattern. Provides the core asynchronous job pattern for all Bankr API operations.
This skill should be used when the user asks to "buy NFT", "purchase NFT", "OpenSea", "NFT collection", "view my NFTs", "NFT holdings", "mint NFT", "NFT listings", or any NFT-related operation. Provides guidance on browsing, purchasing, and managing NFTs.
Operate a BKD kanban board over its REST API. Use when the user wants to manage BKD projects, issue execution workflows, cron jobs, or execution capacity, including three-tier coordination with an event-driven L1, multiple cron-driven L2 workstreams, and L3 execution, multi-repo coordination across several git repos in one workspace directory (trigger phrases like "start BKD multi-repo coordination"), plus multi-subtask orchestration (trigger phrases like "use bkd to start coordination", "start BKD L1"), and the messages system that sends decisions and notifications to BKD's inbox (trigger phrases like "enable the messages system", "启用消息系统", "启用决策系统", "notify me when …", "通知我"). Requires a reachable BKD server ($BKD_URL).
Create channel-ready variants of an existing Canva campaign design. Use when users ask to resize or adapt one campaign for multiple social platforms, produce variants for each channel, turn landscape creative into vertical or square formats, create platform-specific versions, or prepare TikTok, Instagram, LinkedIn, Facebook, YouTube, Pinterest, X, or custom-dimension variations. When they ask for each channel or platform-ready variants and do not name placements or dimensions, use the default channel set in references/channel-formats.md. A named platform plus placement uses that file's lookup table. This skill creates resized copies and returns edit links; use edit-design separately when the user asks to recompose, adjust crop or safe areas, change copy, or use generative fill
Cost-conscious Claude Code mode. Cuts visible output and routes simple work to cheaper models by enforcing concise responses, smart model routing, and efficient workflow patterns. Keeps full technical accuracy. Activate with /cost-mode or "enable cost mode". Auto-triggers on mentions of budget, cost, tokens, or spending.
Maps business domains and suggests service boundaries in any codebase using DDD Strategic Design. Use when asking “what are the domains in this codebase?”, “where should I draw service boundaries?”, “identify bounded contexts,” “classify subdomains,” “DDD analysis,” or analyzing domain cohesion. Do NOT use for grouping existing components into domains (use domain-identification-grouping) or dependency analysis (use coupling-analysis).
Adds internationalization (i18n) infrastructure with translation plumbing, a scalable key strategy, formatters for dates, numbers, and currency, plural rules, and language switching. Use when implementing "internationalization", "translations", "multi-language support", or "i18n"
Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdown, actor, path, lifecycle, retention, and annotation queries. Use when the user reports an anomaly, asks “why did X change?”, asks for an explanation or walkthrough of a chart, or needs root-cause analysis for a trend, funnel, retention, stickiness, or lifecycle metric
Sandbox build executor for Sealos deploys: build a container image from source with an in-cluster Kaniko Job and push it to GHCR, for environments without a Docker daemon (Brain managed Devbox sandboxes). Use only when a managed deploy (SEALAI_DEPLOY_MODE=managed) needs an image built from project source; local interactive deploys build with docker buildx instead (see the use-sealos skill).
Search 1688 by image to find visually similar or identical products and suppliers using product images. Returns key data such as titles, prices, minimum order quantities, monthly sales, repeat purchase rates, and transaction ratings. Trigger this skill when users mention searching 1688 by image, finding suppliers or matching products on 1688, finding factories for cross-border trade, 1688 image recognition, finding suppliers or similar products by image, “image search 1688,” or “find supplier by image.” Also trigger it when users provide an image URL and want to find matching or similar supplier products on 1688, even if they do not explicitly mention image search.
Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.
Use this skill to migrate identified PostgreSQL tables to Timescale/TimescaleDB hypertables with optimal configuration and validation. Trigger when user asks to: - Migrate or convert PostgreSQL tables to hypertables - Execute hypertable migration with minimal downtime - Plan blue-green migration for large tables - Validate hypertable migration success - Configure compression after migration Prerequisites: Tables already identified as candidates (use find-hypertable-candidates first if needed) Keywords: migrate to hypertable, convert table, Timescale, TimescaleDB, blue-green migration, in-place conversion, create_hypertable, migration validation, compression setup Step-by-step migration planning including: partition column selection, chunk interval calculation, PK/constraint handling, migration execution (in-place vs blue-green), and performance validation queries
Designs, implements, and reviews professional mobile UI for React Native and Expo, with platform-aware design and review guidance for iOS and Android. Use when the task involves mobile screens, components, navigation, visual direction, design systems, accessibility, gestures, haptics, animations, typography, color, dark mode, safe areas, adaptive windows, localization, platform conventions, App Store or Play-quality polish, iOS HIG, Material Design, Expo Router, React Navigation, Reanimated, Gesture Handler, or mobile UX critique
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.