Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
A world-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics. Expertise in Python (NumPy, Pandas, Scikit-learn), R, SQL, statistical methods, A/B testing, time series, and business intelligence. Includes experiment design, feature engineering, model evaluation, and stakeholder communication. Use when designing experiments, building predictive models, performing causal analysis, or driving data-driven decisions.
Find product-led and blue-ocean SEO opportunities from customer demand, query behavior, competitive gaps, search result features, communities, and proprietary product strengths. Use when researching SEO opportunities, organic growth ideas, competitive SEO gaps, programmatic SEO concepts, or when keyword tools show little volume.
Prioritize SEO initiatives as product roadmap work with impact, effort, confidence, resourcing, executive pitch, cross-functional ownership, quarterly planning, and business KPI alignment. Use when building SEO roadmaps, scoring SEO work, requesting engineering/design/content resources, annual planning, executive buy-in, or turning SEO recommendations into product-ready asks.
Use when starting work in a terminal session—opening a project or directory, connecting to a session by name, cloning a repo to work in, or running a command or coding agent somewhere other than the current shell. Sesh resolves names and directories to sessions across tmux, zoxide, config, and tmuxinator. Use instead of `tmux new-session`, `tmux new-window`, `tmux attach`, or `tmux send-keys`.
Acquire, import, and analyze WeChat or QQ chat histories, including installing supported exporters, guiding required login or contact selection, converting exports, assessing relationship dynamics and risk signals, and generating a structured Chinese HTML report. Use when the user asks to export, import, or analyze WeChat/QQ chats or requests relationship analysis from message history.
This skill should be used when the user asks to “search for exposed devices on the internet,” “perform Shodan reconnaissance,” “find vulnerable services using Shodan,” “scan IP ranges with Shodan,” or “discover IoT devices and open ports.” It provides comprehensive guidance for using Shodan's search engine, CLI, and API for penetration testing reconnaissance.
Use Shopware CLI for Shopware project, extension, and account workflows — create and install new projects (project create, project dev install), validate projects or extensions (with --only/--exclude and --format json, junit, github, gitlab for CI), develop, build, upgrade, and troubleshoot. Also use when contributing to shopware/shopware-cli and reasoning about the CLI's user-facing behavior.
Professional short-drama scriptwriting skill. For short-drama topic selection, story outlines, character design, episode lists, single-episode scripts, self-checks and export; suited to Chinese short-drama scenarios such as urban romance, domineering CEO, sweet romance, rebirth and suspense.
Explain the current topic, a status, or a concept as one designed diagram made with the diagram-design skill. Use when the user asks to see it as a diagram or with diagram-design. For a quick view in plain text, use show-me; for a report or decision page to read later, use show-me-artifact.
Use when the user explicitly asks for simple English, plain English, or for text a non-native English speaker can read easily — rewrites docs, READMEs, issues, comments, or UI text into plain words and translation-friendly grammar, still native-sounding. Prose the user signs in their own voice goes to write-like-me instead
Audit claude-skills repository documentation with systematic 9-phase review: standards compliance, official docs verification via Context7/WebFetch, code examples accuracy, cross-file consistency, and version drift detection. Auto-fixes unambiguous issues with severity classification. Use when: investigating skill issues, major package updates detected (e.g., v1.x → v2.x), skill not verified >90 days, before marketplace submission, or troubleshooting outdated API patterns, contradictory examples, broken links, version drift.
Before installing or using a skill, check its independent benchmark report on SkillTester.ai. Auto-trigger this skill whenever the user shows a third-party skill install command or install plan, especially `npx skills add <repo-or-url> --skill <skill-name>`, `skills add ...`, repo URL plus `--skill`, direct `SKILL.md` URLs, or `Check this skill <skill_url>`. Parse the install command, resolve the target SKILL.md, query SkillTester.ai by skill name, and return the benchmark result when the description is either an exact match or a high-overlap near match that likely represents a newer skill revision.
Use this skill whenever the user wants to create PowerPoint presentations with animations, transitions, and precise element control from JSON — or reverse-engineer an existing .pptx into structured JSON. SlideJ is a CLI that generates .pptx from JSON and parses .pptx back to JSON, enabling a full round-trip workflow. Trigger when: user wants animated slides, mentions 'slidej', needs to convert a .pptx to JSON for reading or editing, wants element-level animation control (fadeIn, flyIn, zoom, spin, wipe, etc.), or needs a programmatic slide generation pipeline. Also trigger when the user uploads a .pptx and wants to understand its structure, modify it, or recreate it with changes.
MUST be used whenever a user asks for social media content, Instagram Reels, TikTok ideas, or a content calendar for a local or small business. This skill discovers trending content across TikTok and Google Trends, then generates a personalized weekly content plan with Reel concepts, captions, and hashtags for small businesses. It remembers the user's business profile across sessions so returning users don't need to re-enter their details. Do not answer social media planning questions without this tool.
Solid bindings for TanStack Router: RouterProvider, useRouter, useRouterState, useMatch, useMatches, useLocation, useSearch, useParams, useNavigate, useLoaderData, useLoaderDeps, useRouteContext, useBlocker, useCanGoBack, Link, Navigate, Outlet, CatchBoundary, ErrorComponent. Solid-specific patterns with Accessor<T> returns, createSignal/createMemo/createEffect, Show/Switch/Match/Dynamic, and @solidjs/meta for head management.
Show SonarQube quality gate status for a project — pass/fail and each condition (metric key, threshold, actual value), plus worst-offender breakdowns. Project key optional — resolved from `sonar-project.properties` or the MCP integration default.
Use when starting a SpacetimeDB project, installing the CLI, logging in, understanding architecture, or following quickstarts for TypeScript, React, Angular, Vue, Svelte, Next.js, Nuxt, Remix, TanStack, Browser, Node.js, Bun, Deno, Rust, C#, or C++. Triggers on: install SpacetimeDB, quickstart, getting started, architecture, state mirroring, FAQ, new app.
Use when following, adapting, or debugging complete SpacetimeDB tutorials, including the chat app tutorial, Unity Blackhol.io tutorial, Unreal Blackhol.io tutorial, multiplayer examples, and game tutorial code. Triggers on: tutorial, chat app, Unity tutorial, Unreal tutorial, Blackhol.io, multiplayer example, game tutorial.
Choose the planning form for new work and plan it before execution. Use this skill to decide whether the work is taskless, chat-only, a task file, a task file with subtasks, or multiple task files / backlog items, and to create the needed plan for non-trivial implementation work or investigation work that needs its own task.
When the user wants to analyze procurement spend, identify savings opportunities, or classify expenditures. Also use when the user mentions "spend analytics," "spend visibility," "spend cube," "category analysis," "Pareto analysis," "tail spend," "maverick spend," "spend classification," or "savings opportunity." For executing sourcing strategies, see strategic-sourcing. For supplier evaluation, see supplier-selection.
Generate professional sponsorship pitches and media kits for brands. Creates compelling proposals highlighting channel value, audience demographics, and collaboration ideas. Use when seeking sponsorships, responding to brand inquiries, or creating media kits.
Index coverage and N+1 review aids for SQLite/D1 schemas with a sqlc catalog. Surfaces unused indexes (with FK CASCADE awareness so cascade-load-bearing indexes are not flagged), queries that scan tables without index help, and `for`-loops calling generated SQL fns.
Search and download stock photos from Pexels, Unsplash, and Pixabay for projects, landing pages, UI mockups, and content. Use when users explicitly ask to find stock photos, need a hero/profile/content image, or want to download a selected stock image.
Based on the story content described by the user, polish the storyline and split it into a storyboard script, then batch-generate storyboard illustrations in a consistent style. Offers 8 visual style choices and recommends the best style based on story type. Calls the Gemini API to generate images and saves them to the Obsidian image directory. Trigger words: "分镜故事", "故事板", "做个分镜", "创建故事板", "storyboard", "画个故事".
A strategic thinking partner for Claude Code that separates deciding from building. Challenges assumptions, compares approaches, and hands execution a ready-to-run prompt in a fresh session. Handles skill routing, context handoff, and memory management. Use when: "plan my project", "advise on architecture", "what should I build next", "help me think through", "explore", "brainstorm", "how should I approach", "what's the right tool", "which skill do I use", "route this task", "hand off context", "manage my session". Triggers on: /strategic-partner, /advisor, /sp
Use when the user wants to build or think through a strategy via guided conversation — for a company, product, team, career, or initiative. Triggers on "help me figure out our direction", "what should we focus on", strategic planning, competitive positioning, go-to-market strategy. Also catches indirect requests like prioritization struggles or "we have too many priorities". Does NOT review existing strategy documents (use strategy-review) or brainstorm project features (use brainstorm-beagle).
Guides Stripe integration decisions across development and test environment planning (separate sandboxes vs the shared test mode sandbox), API selection (Checkout Sessions vs PaymentIntents), Connect platform setup (Accounts v2, controller properties), billing/subscriptions, tax and registrations (Stripe Tax, automatic_tax, product tax codes), Treasury financial accounts, integration options (Checkout, Payment Element), migrating from deprecated Stripe APIs, and security best practices (API key management, API key permissions, webhooks, OAuth). Use when planning, building, modifying, testing, or reviewing any Stripe integration, including choosing a development environment, accepting payments, building marketplaces, integrating Stripe, processing payments, setting up subscriptions, collecting sales tax, VAT, or GST, creating connected accounts, or implementing secure key handling.
Remove the discourse-level (structural) signs of AI writing that survive surface editing: stated lessons and moral-of-the-story closers, tidy single-track arcs, embodied-emotion performance ("chest tightened"), vague allusions instead of named references, unbroken linear structure, and shape convergence across pieces. Grounded in the StoryScope study (Russell et al. 2026): narrative structure alone detects AI text at 93.2% F1, and professional stylistic rewriting moved detection only 1.6 points. Use as the SECOND pass after the humanizer skill (which handles words and phrasing) whenever writing or revising LinkedIn posts, course lessons, blog posts, essays, newsletters, or emails that must read as human. Triggers: "humanize", "de-slop", "AI tells", "make this sound human", "structural pass", "deep humanize".
SupSub CLI authentication management — login / logout / check login status. Login uses OAuth browser device authorization; the CLI does not support API Key login. Matches 「supsub 登录」「supsub 登出」「查看我在 supsub 的登录状态」「我现在 supsub 用的是哪个账号」「supsub auth login / logout / status」. Before calling other supsub subcommands, if you are unsure of the credential status, run `supsub auth status` with this skill first.
SupSub subscription management — list / add / remove subscription sources (WeChat official accounts MP, websites WEBSITE, Twitter X), browse the article list of a subscribed source (with paging), and mark an entire source as read. Matches 「列出我的订阅」「我订阅了哪些」「取消订阅某个号」「订阅某个公众号 / 网站」「看某个订阅里有哪些文章」「某公众号最近的未读文章」「添加 / 删除订阅源」「看更早的文章 / 翻页」「这个号我读完了 / 整源标记已读」. ⚠️ Read status only has a **whole-source** level (`mark-read --all`, irreversible): articles have no 「详情 / 阅读」 step, so marking a single article as read is not supported. ⚠️ Also matches browsing phrasing that **refers to your own subscription source by its subject name**: 「看一下最近 X 的内容」「X 最近有什么」「X 更新了吗」「读读 X」 — for such requests, first run `supsub sub list` to check whether X is a subscribed source name (contains match, case-insensitive); if it matches, use `sub contents` to fetch that source's content and **do not** treat it as a site-wide keyword search; if it does not match, switch directly to supsub-search to perform a site-wide search (**do not ask the user whether to search**). ⚠️ In this skill, `--type X` refers specifically to Twitter platform accounts; in colloquial user phrasings such as 「订阅 X」 or 「X 公众号」, the letter X is usually just a placeholder for a specific account and does not mean `--type X`. ⚠️ Verb discrimination: this skill only recognizes 「订阅 / 订阅了」; when the user says 「关注 / 关注了 / 我关注了哪些 / 我的关注点」, route to supsub-focus (focus points), not this skill. ⚠️ Not for searching article keywords across subscriptions (route to supsub-search), nor for 「发现一个新的公众号」 (route to supsub-mp).
CLI tools for Svelte 5 documentation lookup and code analysis. MUST be used whenever creating, editing or analyzing any Svelte component (`.svelte`) or Svelte module (`.svelte.ts`/`.svelte.js`). If possible, this skill should be executed within the `svelte-file-editor` subagent for optimal results.
SVG illustration generation tool for books and articles, focused on professional technical illustrations such as architecture diagrams, flowcharts, and hierarchy diagrams. Use this skill when the user needs to generate illustrations for book chapters or formal articles, create architecture diagrams/flowcharts/hierarchy diagrams, or mentions "章节配图", "书籍插图", "架构图", "流程图".
Create flexible, responsive card layouts with headers, images, action buttons, and custom styling. Use when building UI containers for displaying content, product cards, service offerings, or dashboard components. Customize with CSS styling, add headers, images, and action buttons as needed.
Systematic step-by-step debugging process for bugs, test failures, and unexpected behavior. Use when a test fails, something isn't working as expected, user says "this is broken", "why isn't X working", "help me debug", or when you encounter any error before proposing a fix.
Production-tested setup for Tailwind CSS v4 with shadcn/ui, Vite, and React. Use when: initializing React projects with Tailwind v4, setting up shadcn/ui, implementing dark mode, debugging CSS variable issues, fixing theme switching, migrating from Tailwind v3, or encountering color/theming problems. Covers: @theme inline pattern, CSS variable architecture, dark mode with ThemeProvider, component composition, vite.config setup, common v4 gotchas, and production-tested patterns. Keywords: Tailwind v4, shadcn/ui, @tailwindcss/vite, @theme inline, dark mode, CSS variables, hsl() wrapper, components.json, React theming, theme switching, colors not working, variables broken, theme not applying, @plugin directive, typography plugin, forms plugin, prose class, @tailwindcss/typography, @tailwindcss/forms
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.