Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
End-to-end video production orchestration for the content-creation workspace. Use when the user asks to make, recreate, package, render, quality-check, or archive a video; says 制作待制作队列, 按交接稿制作, or 制作队列视频; points to a handoff project folder under 01-内容生产/视频工作台/待制作/ (with contract file 交接稿.md inside) or an image-card handoff under 01-内容生产/图文工作台/待制作/ (whose frontmatter is the binding production contract); when a request could involve HyperFrames, Remotion, captions, TTS, downloading/transcription, website/product videos, motion graphics, or reference replication; or when the user needs production planning before editing.
Scans React codebases for security, performance, correctness, accessibility and architecture issues and reports a 0-100 health score, with severity-ranked findings and a regression check to run after changes. Can also run a focused UI design audit and a runtime performance trace.
Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for “recall my work on X”, “catch me up”, “what have I been working on”, “where did I leave off”, before starting or resuming work.
Review a resume like a professional resume writer AND an ATS (Applicant Tracking System) — produce an ATS score (0-100), a level detection (fresher / mid / senior), a breakdown of what's working, what's failing, the 7 Deadly Sins check, priority fixes, concrete before→after bullet rewrites, and missing keywords. Use this skill whenever the user asks to review, audit, critique, score, rate, roast, or improve a resume or CV, or types /resume-review, or drops a resume PDF with a job description. Trigger EVEN IF the user just says "look at my CV", "check my resume", "is this resume good", "why am I not getting interviews", "roast my resume", or shares a resume file without explicit review instructions — any interaction involving a resume file or CV should invoke this skill. Especially strong for DevOps, SRE, Cloud, Platform, and Infrastructure engineering resumes, but works for any technical resume.
Implement secure error handling to prevent information leakage and provide appropriate error responses. Use this skill when you need to handle errors in API routes, prevent stack trace exposure, implement environment-aware error messages, or use the error handler utilities. Triggers include "error handling", "handle errors", "error messages", "information leakage", "stack trace", "handleApiError", "production errors", "error responses".
Connect an arbitrary REST API to the PostHog data warehouse as a Custom source by authoring a JSON manifest, with no per-source code. Use when the user points at an API that has no built-in PostHog connector — "import data from this REST API", "sync my internal API", "connect this API from its docs", "build a custom data warehouse source" — and gives a docs URL or a natural-language description of the endpoints. Walks through drafting the RESTAPIConfig manifest (auth — bearer, API key, HTTP basic, or OAuth2 client credentials / refresh token — pagination, record path, incremental cursor, parent/child fan-out), validating it, test-reading live rows to verify the field mappings, and creating the source. If the API already has a native PostHog connector, use setting-up-a-data-warehouse-source instead — this skill checks the connector registry first and only handles APIs with no native connector.
Use this skill when the user wants to “create a skill,” “add a skill to a plugin,” “write a new skill,” “improve a skill description,” or “organize skill content,” or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Investigar questões técnicas em fontes primárias, código, padrões e experimentos, produzindo síntese rastreável. Use quando decisões dependem de APIs atuais, comparação de tecnologias ou fatos incertos; salve pesquisa somente no local autorizado pela spec do projeto consumidor.
Non-streaming and streaming SSR, RouterClient/RouterServer, renderRouterToString/renderRouterToStream, createRequestHandler, defaultRenderHandler/defaultStreamHandler, HeadContent/Scripts components, head route option (meta/links/styles/scripts), ScriptOnce, automatic loader dehydration/hydration, memory history on server, data serialization, and document head management.
Fixes structured data issues. Adds and validates JSON-LD with Schema.org types such as Organization, WebSite, Product, Article and FAQPage, links entities with @id, adds author attribution and publishes trust anchor pages so AI search engines can understand and cite a website. Use when asked to "add JSON-LD", "fix structured data", "add schema markup", "improve structured data score", "add Organization schema", "fix Schema.org", "add product markup", "add FAQ schema", "add author markup", "add about and contact pages", or any JSON-LD or Schema.org task.
Best practices and example-driven guidance for SwiftUI views and components: tab architecture, navigation hierarchies, screen composition, custom view modifiers, and responsive layouts. Keeps SwiftUI code idiomatic and maintainable for Apple platform apps.
Use this skill whenever the user wants to write code using TDD, test-driven development, or test-first methodology. Triggers on: "/tdd", "let's do TDD", "write a failing test", "red green refactor", "test-first", "start a TDD cycle", or any request to implement a feature by writing tests before code. Adaptive five-step cycle (RED-DOMAIN-GREEN-DOMAIN-COMMIT) that detects harness capabilities and routes to guided (/tdd red|domain|green|commit) or automated (/tdd) mode. NOT for running existing tests, debugging test failures, or reviewing code -- only for the disciplined test-first cycle.
Deterministic Three.js skills covering the core scene graph, renderer, geometries, materials, shaders, WebGPU, React Three Fiber, Drei, physics, XR, error diagnosis, and IFC viewing (architecture/BIM workflows). Built by the Open AEC Foundation for architecture and engineering workflows on top of 3D web rendering.
Creates a new Linear issue from a free-form description. Drafts a structured title and body, picks team/project/labels/priority from the connected workspace, shows the draft to the user for approval, then creates the ticket. Use when the user asks to "create a Linear ticket", "file an issue", "make a ticket", "open an issue in Linear", or any request to log a new bug/feature/task.
High-quality article translation skill using a four-step workflow: analysis → initial translation → review → final draft. Supports Chinese ↔ English and Chinese ↔ Japanese only. Triggered when the user explicitly requests “translate,” “精翻,” “翻訳,” “translate an article,” “translate to Chinese/English/Japanese,” “改成中文,” “改成英文,” “改成日文,” “翻成中文,” “翻成日文,” “翻成英文,” “英译中,” “中译英,” “中译日,” “日译中,” “日本語に翻訳,” “中国語に翻訳,” “英語に翻訳,” “これを翻訳して,” “put this in Chinese,” “put this in English,” “put this in Japanese,” “convert to Chinese,” “convert to English,” “convert to Japanese,” “帮我翻一下,” “本地化,” “localize,” “translate this article,” or provides a URL/file/text and explicitly requests a polished translation into a target language. For URLs, first use `curl -L` to fetch the article Markdown from `r.jina.ai`; if fetching fails or the content is incomplete, stop and ask the user to provide the text. Not for summarizing, explaining, understanding, or organizing content.
Package one video/script/transcript into a complete publish kit: cover titles, platform titles, per-platform tags, description, and creative cover art direction with pre-review before image generation. Covers Xiaohongshu, Douyin, WeChat Channels (视频号), Bilibili, and YouTube. Use when the user asks for video cover design, 封面包装, 视频包装, 发布文案, 标题公式, 封面标题, platform tags for a video, or says '给这期视频做封面/标题/描述/标签'. Keywords: video cover, thumbnail title, publish kit, self-media packaging, 小红书封面, 抖音封面, B站封面.
visionOS skills—spatial design (layout ergonomics, eyes-and-hands input, motion comfort, immersion, environments) and widget patterns (mounting styles, glass/paper textures, proximity-aware layouts). Use when designing, building, or reviewing anything for visionOS.
Vue.js performance optimization guidelines for building fast, maintainable applications. Use this skill when writing, reviewing, or refactoring Vue.js code to ensure optimal performance patterns. Triggers on tasks involving Vue components, reactivity, Composition API, state management, or performance improvements.
A macOS tool for running multiple instances of WeChat (小绿书). It uses a copy of WeChat.app, modifies the Bundle ID, and re-signs it. Use when the user says "open two WeChat windows", "run two WeChat instances", "run multiple WeChat instances", "open another WeChat", "rebuild after a WeChat update", "fix WeChat multi-instance", "close all WeChat instances", or "小绿书". For macOS only; the script is at scripts/wechat-multi.sh.
Invoked as "/windowsfy [path]" or when the user asks to "fix windows compatibility", "make package.json cross-platform", "windows portability", "run on windows", "cross-env", "shx", "PowerShell 5.1 error", "rm -rf on windows", "chmod on windows", "NODE_ENV not recognized", "glob not expanded on windows", "native binary on windows", "tfjs-node windows", "better-sqlite3 windows", "transformers windows", "token && is not a valid statement separator", "single quotes in npm scripts", or encounters npm script failures specific to Windows native shells. Path may be a directory, a single package.json file, or omitted (defaults to ./).
Generate comprehensive workload analysis visualizations for PostHog customer accounts. Use when user requests account analysis, workload breakdown, SDK analysis, spend allocation, or expansion opportunity assessment. Triggers include "analyze [account]", "workload analysis for [account]", "SDK breakdown for [account]", "show me how [account] uses PostHog", or any request to understand customer usage patterns across products and platforms.
This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment.
Fixes AI content discovery issues. Creates and corrects robots.txt, AI crawler directives, XML sitemaps, llms.txt, Markdown content negotiation, Link headers, Content-Signal lines, AGENTS.md, agent content contracts, soft-404 handling, DNS-AID records and pricing pages so AI systems can find, crawl and read a website. Use when asked to "fix robots.txt", "add llms.txt", "create a sitemap", "allow AI crawlers", "serve markdown to agents", "add AGENTS.md", "fix soft 404", "improve AI content discovery score", or any robots.txt, sitemap or llms.txt task.
Use when the user operates Alibaba Cloud Container Service for Kubernetes (ACK). Covers cluster lifecycle (create / modify / delete / upgrade), node pools & nodes (create, modify, delete, repair, fix CVE), addons (install / upgrade / uninstall), KubeConfig & RBAC (issue for RAM user, grant / revoke), security & policy (CVE scan/fix, policy governance, KMS, delete protection), logging / audit / alerting, intelligent O&M (check / inspect / diagnosis / auto-repair), async tasks (track / pause / resume / cancel), templates, autoscaling, tags & quotas. Triggers: create / upgrade / delete ACK cluster, migrate to Pro, scale nodepool, fix node CVE, install / remove addon, get / revoke kubeconfig, grant RBAC, enable audit log, run inspection, diagnose cluster, track task_id, debug cs error, Forbidden.RAM, kubectl cannot connect. Terms: ACK, container service, k8s cluster, nodepool, addon, AutoMode, Terway, Flannel, ForRegion, kubeconfig, RBAC, CVE.
Install and configure OpenClaw with DingTalk, Feishu, Discord, and additional channels with Bailian/DashScope models on Linux hosts. Use when provisioning a new OpenClaw node, troubleshooting gateway/channel startup, standardizing openclaw.json mapping, or automatically discovering extra channels from https://docs.openclaw.ai/channels.
Extract clean content from articles at URLs (blog posts, articles, tutorials) and save it as readable text. Use when the user wants to download, extract, or save an article or blog post from a URL without ads, navigation, or clutter
Audit and prioritize performance work through bounded-work and forward-progress checks. Use when asked to find performance issues, investigate freezes/500s/OOMs, review retries or polling for no-progress loops, rank a performance backlog, or implement the next simple performance fixes
Expert knowledge for Azure Active Directory B2C development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations, coding patterns, and deployment. Use when configuring custom policies/user flows, IdPs/social logins, MFA, securing APIs, or automating CI/CD deployments, and other Azure Active Directory B2C development tasks. Not for Azure Role-based access control (use azure-rbac), Azure Security (use azure-security), or Azure Sentinel (use azure-sentinel).
Expert knowledge for Azure Communication 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 building ACS calling, chat, SMS, email, Teams interop, or PSTN/Direct Routing solutions, and for other Azure Communication Services development tasks. Not for Azure Notification Hubs (use azure-notification-hubs), Azure SignalR Service (use azure-signalr-service), Azure Web PubSub (use azure-web-pubsub), or Azure AI Bot Service (use azure-bot-service)
Expert knowledge for Azure Event Grid development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations, and coding patterns. Use when building Event Grid topics/namespaces, MQTT brokers, webhook handlers, Functions, or Service Bus integrations, and other Azure Event Grid development tasks. Not for Azure Service Bus (use azure-service-bus), Azure Event Hubs (use azure-event-hubs), Azure Notification Hubs (use azure-notification-hubs), or Azure Functions (use azure-functions).
Builds carousels with @blossom-carousel/svelte in Svelte 5 and SvelteKit, covering BlossomCarousel setup, CSS scroll-snap layouts, BlossomPrev/BlossomNext/BlossomDots/BlossomDot controls, bind:this methods (prev, next, goTo), useBlossomNavigation for custom controls, and command and overscroll events. Use when a Svelte or SvelteKit project imports @blossom-carousel/svelte or renders <BlossomCarousel>, or when the user wants a Blossom carousel, slider, or gallery in Svelte or SvelteKit.
Enforces a lean GitHub Actions Flutter CI where every gate maps to one named release-blocking contract — pinned runner + subosito/flutter-action@v2 toolchain, dart format --set-exit-if-changed, flutter analyze --fatal-infos, build_runner and drift schema freshness (git diff --exit-code), flutter test --test-randomize-ordering-seed random, static import/banned-string greps that catch what runtime can't, coverage-as-report-never-a-gate with the upward-lie fixed, verify-never-bless goldens (no --update-goldens in CI), and an honest statement of what CI cannot prove (audio, real fonts, on-device behaviour). Use when editing .github/workflows/*.yml, adding or removing a job or step, wiring a codegen/schema/format/analyze/coverage gate, writing a grep-based policy test or gate script under test/policy or tool/, pinning action versions, or claiming CI proves something it can't.
Generates 5 UX design approaches as interactive prototypes — 1 safe design-system extension and 4 exploratory variants — starting as B&W wireframes then producing color variants via parallel agents. Scans codebase on first run to build persistent design context.
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.