Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Strict design and UX rules for React 19 + Next.js 16 (App Router) + Tailwind CSS 4. Covers navigation, interaction design, accessibility, user feedback, UX patterns, and visual design. Use when designing, building, or reviewing any user-facing web feature on this stack. Trigger when the user asks to “build a settings page”, “add a dialog”, “design this form”, “review for accessibility”, “fix dark mode”, or requests any Next.js App Router / React 19 / Tailwind UI task. Also trigger when the user says the output “looks off”, “isn't accessible”, or “doesn't follow best practices”.
Automate the WeChat macOS desktop client. Uses AppleScript + cliclick to send messages, read chat history, search conversations, scroll, and more. Trigger this skill when users mention WeChat, sending someone a message, messaging a group, checking what a group is talking about, WeChat automation, or scheduling WeChat messages. Supports background mode—it automatically switches back to the previous app after operations without interrupting the user's work.
Zeyiji course management: query, create, and edit courses (including chapter/section directory management). Use when the user needs to query a course list, view course details, create a course, edit course information, or manage a course's chapter directories (add/edit/delete directories and sections).
Adopt an existing project — often one built with AI — into the learning method. Honest triage, an understanding inventory of what the learner can actually explain, a file map with no mystery boxes, and a forward plan with reclaim tasks. Use when the user already has a project they want to understand and keep building, says "I have an existing project", "AI built this and I don't understand it", or invokes /adopt-project.
Audit websites for Google AdSense application readiness and ad-serving compliance. Use when checking whether a site is likely to satisfy AdSense eligibility, site ownership, content quality, navigation, crawler access, ads.txt, privacy disclosure, Google Publisher Policies, AdSense Program policies, or when the user asks if a site can apply for AdSense, pass AdSense review, show ads, or fix AdSense rejection/site-not-ready issues.
Static visual content in 20+ formats (diagrams, infographics, comics, icons, wallpaper) via Nano Banana Pro by default, Nano Banana, and Flux, plus technical diagrams and a few essay illustrations that draw themselves as looping GIFs. USE WHEN art, illustration, diagram, flowchart, animated diagram, diagram GIF, animated essay image, animated header, infographic, header image, blog social thumbnail, generate image, mermaid, comic, icon, blog art, framework diagram, D3 chart, remove background, wallpaper. NOT FOR any request that says visualize (Visualize owns every "visualize X" and may embed Art output), YouTube/video thumbnails (the video skill), other video or animation (HyperFrames), web UI design (Webdesign)
Expert knowledge for Azure Artifact Signing development including decision making, security, configuration, and integrations & coding patterns. Use when handling cert lifecycles, RBAC for signers, DGSSv2 migration, diagnostic logs, or CI/CD signing integration, and other Azure Artifact Signing related development tasks. Not for Azure Key Vault (use azure-key-vault), Azure Artifacts (use azure-artifacts), Azure Information Protection (use azure-information-protection).
Expert knowledge for Chaos Studio development, including troubleshooting, best practices, decision-making, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when automating Chaos Studio via CLI/ARM/REST, configuring AKS agents, Private Link, CMK, or migrating to Workspaces, and for other Chaos Studio-related development tasks. Not for Azure Monitor (use azure-monitor), Azure Resiliency (use azure-resiliency), Azure Reliability (use azure-reliability), or Azure Defender For Cloud (use azure-defender-for-cloud).
Expert knowledge for Azure Health Data Services development, including troubleshooting, best practices, decision making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when using FHIR/DICOM APIs, bulk import/export, de-identification, Synapse integration, or SMART on FHIR, and for other Azure Health Data Services development tasks. Not for Azure Health Bot (use azure-health-bot), Azure Data Factory (use azure-data-factory), Azure Data Explorer (use azure-data-explorer), or Azure Synapse Analytics (use azure-synapse-analytics).
Expert knowledge for Azure IoT development, including best practices, security, configuration, integrations and coding patterns, and deployment. Use when managing Device Registry namespaces, IoT Hub DPS, certificate-based authentication, SDK device connectivity, or software updates, and for other Azure IoT development tasks. Not for Azure IoT Hub (use azure-iot-hub), Azure IoT Edge (use azure-iot-edge), Azure IoT Central (use azure-iot-central), or Azure Defender For Iot (use azure-defender-for-iot).
Expert knowledge for Azure IoT Edge development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring EFLOW devices, DPS/X.509 provisioning, gateway/nested topologies, CI/CD deployments, or IoT Edge metrics/logs, and other Azure IoT Edge related development tasks. Not for Azure IoT Hub (use azure-iot-hub), Azure IoT (use azure-iot), Azure IoT Operations (use azure-iot-operations), Azure Stack Edge (use azure-stack-edge).
Plan verification and validation campaigns for simulation codes using manufactured solutions, canonical benchmark problems, grid/time refinement, uncertainty propagation, and pass/fail acceptance criteria. Use when an agent needs to prove a solver, model, or result is trustworthy rather than only plausible.
Surface the user's unknown unknowns before work starts. Use when the user is entering an unfamiliar codebase area, an unfamiliar domain (design, video, infra), or explicitly asks for a “blindspot pass” or to find their “unknown unknowns.”
Use when building a PlayCanvas game's on-screen interface such as ready, pause, and victory overlays, menus, and live indicators like gauges, timers, or reload meters, so the interface is driven by game state, readable over the scene, and separate from the 3D hierarchy.
Plans structure for a component library with props/slots and right-sized component granularity. Run before building or adding Canvas components (new component folders, component.yml, implementation), or for plan-only / breakdown-only work, whenever UI must map to a coherent tree. Mandatory for every new Figma frame or greenfield screen—repository drafts do not replace phases A–G
Granular feedback on drafts without rewriting. Generates highlighted HTML with click-to-reveal inline comments. Use when user says "comment on this", "leave comments on", "give feedback on", or asks for feedback on a draft. Supports multiple lenses—editor feedback, POV simulation ("as brian would react"), or focused angles ("word choice only", "weak arguments"). A granular alternative to rewrites that lets users review feedback incrementally without losing their voice.
Competitive intelligence specialist focused on systematic competitor analysis, market positioning assessment, and strategic advantage identification. Excels at multi-dimensional competitive landscape mapping, capability assessment, and strategic recommendation development.
Add production-ready authorization (RBAC, ABAC, ReBAC) to Convex apps with O(1) permission checks. Use when implementing roles, permissions, access control, multi-tenancy, or relationship-based authorization in a Convex project. Inspired by Google Zanzibar / SpiceDB
Use when Codex uses the ChatCut plugin (chatcut MCP server) to add, create, hand-author, patch, or place Motion Graphic JSX assets. Covers reference browsing, direct inline JSX authoring, editable properties, asset binding, timeline placement, and composed verification.
A skill for reviewing and revising work documents that ask readers to make a decision, such as approval requests, proposals, plans and reports, from the decision-maker’s perspective. When asked to review from a decision-maker’s perspective, check before submission, make it more likely to pass, or review an approval request, proposal or plan, follow the “review and revise from a decision-maker’s perspective” procedure. Fix issues whose answers are already in the document without asking; ask up to three questions only the author can answer and incorporate the answers into the body; put items needing confirmation in a separate file outside the document. This is the basic entry point. For separate stages, use one of three modes: if asked only to check for contradictions, verify evidence or assess weak logic, use logic. If asked whether the premises are sound, whether alternatives exist or what could overturn the conclusion, use somosomo (write neither into the document; return numbered questions and YAML). After review, if asked to “apply the feedback,” follow the “apply feedback” procedure; if asked to “rework the structure” or “try a different structure,” follow the “restructure” procedure (preserve facts and requested content, change only the backbone of the argument, and present an outline for the author to choose). If asked to be “more concise” or “more thorough,” follow the corresponding procedure (set the main text length based on the depth of logic YAML; preserve facts and decision items). Do not use for requests to make Japanese natural or easier to read (that is natural-japanese’s job).
Explains DeepBook V3 on Sui: the central limit order book (CLOB) design, how a Pool is built from Book, State, and Vault, the DEEP token's role in fees, staking and governance, the three integration models, and mainnet package and pool IDs. Use when the user asks what DeepBook is or how it compares to an AMM like Uniswap, asks about DeepBook Pool internals, BigVector, or order matching, asks whether to integrate via Move package, TypeScript SDK, or read-only queries, asks about DEEP fees, staking, whitelisted pools, or voting, or needs a DeepBook mainnet package ID, pool object ID, coin type, or fee tier.
DeepBook V3 TypeScript SDK integration. Use when building trading applications, bots, or scripts that interact with DeepBook pools using the @mysten/deepbook-v3 SDK. Covers client setup, BalanceManager lifecycle, placing limit and market orders, swaps, querying order books, order management, and fee handling. For DeepBook architecture and contract addresses, see the `deepbook-overview` skill. For Move smart contract integration, see the `deepbook-move` skill.
Detect and prevent dependency confusion (public-over-private package name resolution) in npm, PyPI, and Maven by enumerating claimable internal package names with tools like `confused` and OWASP `dep-scan`, then enforcing source restrictions via `.npmrc`, `pip.conf`/`pyproject.toml`, and Maven `settings.xml`. Use when onboarding a repo to a supply-chain security program, auditing lockfiles/manifests for confusable dependencies, or after an incident that may have leaked internal package names.
Check documentation for compliance with the Elastic style guide using Vale linter output and style rules. Use when the user asks to check, lint, or review docs for voice, tone, grammar, formatting, accessibility, or word choice, or when a docs review runs. Do not use for ordinary drafting or editing.
Flag Elastic-internal jargon in documentation and suggest plain-language replacements. Use when the user asks to check or review docs for terms that external readers would not understand, or when a docs review runs. Do not trigger on ordinary drafting or editing.
Validate and assess the quality of Elastic changelog YAML files against current Elastic standards. Reports schema errors, content quality issues, systematic pattern violations, type-title alignment mismatches, missing product/surface context in titles, description verb-tense issues, and overly technical content that needs user-focused rewrites. Features repository-aware area validation. Fetches canonical guidance to stay in sync. Use when checking or reviewing changelog files before merging — pairs with docs-fix-changelog to get suggested fixes
This skill deploys frontend and full-stack projects to EdgeOne Pages (Tencent EdgeOne). It should be used when the user's primary intent is to deploy, publish, ship, host, launch, go live, or release a new version — e.g. "deploy my app", "publish this site", "push this live", "create a preview deployment", "deploy to EdgeOne", "ship to production", "上线", "发布", "发一版", "重新部署". Do NOT trigger when deployment is only mentioned as a secondary step (e.g. "write an API and deploy it" — primary intent is writing code, use edgeone-pages-dev). Do NOT trigger for post-deployment runtime errors (e.g. CORS issues, 500 errors after deploy — use edgeone-pages-dev for troubleshooting).
Daily English vocabulary teacher for school and matric-level students. Provides 35 new words daily with meanings and examples, followed by a test with multiple choice, fill-in-the-blank, and sentence-based questions. Shows detailed results with scores.
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.