Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Orchestrator/subagent coordination workflow for tasks that can be split into clear disjoint work. Use when the user invokes $subagents, says "use subagents", "spawn agents", "parallelize this", "delegate this", "split this across agents", or asks for coordinated multi-agent work. Prefer subagents for harder tasks, broad research, multi-file changes, independent reviews, or separable implementation lanes. Skip subagents when the task is simple, the harness does not support them, or safe disjoint work cannot be identified.
Summarizes the user's merged GitHub PRs for a timeframe into a grouped, linked shipped-work report with highlights, and offers to update a brag document. Use when the user says "what shipped?", or when asked what the user shipped (this week, last month, a quarter, since a date), for a status update, or to update a brag doc.
Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing or changing anything that lives in a Postgres database: creating or altering tables and columns (including choosing column types), schema design, migrations and declarative schema files, RLS policies and the tests that verify them, indexes, triggers, database functions, queues and scheduled jobs (pg_cron, pgmq), vector/semantic search (pgvector), and restoring dumps (pg_restore) or importing data. Also load it when diagnosing slow queries, high CPU, timeouts, EXPLAIN plans, connection exhaustion, locking, bloat, or rows visible to the wrong user or tenant. This is not just a performance guide — schema, migration, security, and SQL authoring tasks need these rules too, even for a one-column change or a single query.
SupSub WeChat official account discovery — use only when the user wants to find / discover a WeChat official account itself (usually to get its mpId and then subscribe to it). Matches "搜公众号 X", "找 X 这个公众号", "查 X 公众号", "想订阅 X 公众号但不知道 ID", "discover / find a WeChat MP account". ⚠️ Do not use to search the body/content of articles or articles by keyword — that intent (e.g. "搜一下 X 相关的内容", "找 X 相关的文章") must go through supsub-search. Also covers cancelling a running official account search task.
Cross-cutting project status dashboard. Shows active epics with progress ratios, actionable next steps, blocked items, in-progress tasks, GitHub issues, and session context. Produces rich terminal output with clickable links. Triggers on: 'project status', 'swain status', 'what's next', 'dashboard', 'overview', 'where are we', 'what should I work on', 'am I blocked', 'what needs review', 'show me priorities'.
Comprehensive guide for SymPy - Python library for symbolic mathematics. Use for symbolic expressions, calculus (derivatives, integrals, limits, series), equation solving (algebraic, differential, systems), linear algebra, simplification, matrix operations, special functions, code generation, and mathematical proofs. Essential for analytical mathematics and computer algebra.
Implements Syncfusion Flutter Calendar (SfCalendar) and Date Range Picker (SfDateRangePicker) widgets for date and scheduling UIs in Flutter apps. Use when building appointment calendars, booking systems, date range selectors, or event scheduling interfaces. This skill covers calendar views, recurring events, date navigation, localization, callbacks, and customization.
Build collapsible navigation panels with the Syncfusion TypeScript Accordion component. Use this skill when implementing vertical accordion menus, expanding/collapsing content panels, multi-step wizards, data-driven panels with dynamic content, tabbed navigation alternatives, or nested hierarchical content structures. Covers initialization, expand modes, animations, icons, templates, styling, data binding, and advanced use cases like form wizards.
Implement the Syncfusion TypeScript Image Editor control for image editing, annotation, and manipulation. Use this when the user needs to add image editing capabilities, work with filters, transformations, cropping, or drawing features in TypeScript applications. Covers setup, image operations, annotations, filters, accessibility, and customization patterns.
Build responsive ListView components with Syncfusion TypeScript. Implement this skill when working with list-based interfaces, data binding, templates, selection handling, nested lists, grouping, filtering, virtualization, and advanced features like drag-drop and paging. Covers single/multi-select, checkboxes, animations, remote data binding, custom templates, and use cases such as chat windows, contact lists, and data tables.
When building navigation hierarchies, implement Syncfusion Menu for multi-level nested items, data binding, animations, and event handling. Supports horizontal and vertical orientations, scrollable menus, accessibility, and real-time item management.
Tailwind CSS 4.x utility-first styling patterns. Use when building UI components, creating responsive layouts, implementing design systems, or customizing themes. Covers CSS-first configuration, @theme directive, and component patterns.
Configure Tavus CVI personas with custom LLMs, TTS engines, perception, and turn-taking. Use when customizing AI behavior, bringing your own LLM, configuring voice/TTS, enabling vision with Raven, or tuning conversation flow with Sparrow.
Add Anthropic Claude models (Opus, Sonnet, Haiku) to Microsoft Teams.ai applications using @youdotcom-oss/teams-anthropic. Optionally integrate You.com MCP server for web search and content extraction. - MANDATORY TRIGGERS: teams-anthropic, @youdotcom-oss/teams-anthropic, Microsoft Teams.ai, Teams AI, Anthropic Claude, Teams MCP, Teams bot - Use when: building Microsoft Teams bots with Claude, integrating Anthropic with Teams.ai, adding MCP tools to Teams applications
Wire Telegram keyboards — the mechanics. Covers inline buttons, callback routing, reply_markup, grammY attach syntax, the inlined toolkit's UI builders (inlineButton, urlButton, inlineKeyboard, menuKeyboard, confirmKeyboard, paginate), ForceReply markup, custom keyboards for typed input (RequestContact, RequestLocation, RequestUser, RequestChat, RequestManagedBot), copy_text buttons, web_app buttons. USE FOR: inline buttons, keyboard, telegram menu, bot UI, callback buttons, pagination, reply_markup, ForceReply, copy_text, web_app, callback_data, prefix routing, regex routing — even if the user doesn't say "inline" or "keyboard" explicitly. DO NOT USE FOR: microcopy / flow patterns / error UX / onboarding / anti-patterns (see telegram-bot-ux router), or the Bot API foundation (see telegram-bot-api-fundamentals). Triggers: inline buttons, keyboard, telegram menu, bot UI, callback buttons, pagination, reply_markup, ForceReply, copy_text, web_app, callback_data, prefix routing, regex routing.
Develop, debug, and manage Temporal applications across Python, TypeScript, Go, Java, .NET, Ruby, and Rust. Use when the user is building workflows, activities, workers, or background job queues with a Temporal SDK, debugging issues like non-determinism errors, stuck workflows, or activity retries, using Temporal CLI, Temporal Server, or Temporal Cloud, or working with durable execution concepts like signals, queries, heartbeats, versioning, continue-as-new, child workflows, or saga patterns. Also use when the user mentions "run a Temporal workflow from the CLI", "start a dev server", "run temporal server start-dev", "temporal workflow start", "temporal workflow execute", "temporal workflow signal", "temporal workflow query", "temporal workflow update".
Framework-neutral standards for the quality of an individual automated test in TypeScript: assert on behavior not implementation, meaningful assertions, one outcome-named scenario per test, builders over shared fixtures, test doubles that earn their place, deterministic order-independent tests, coverage read as a map of the unverified. Use it when writing tests for new or changed code, reviewing the tests in a pull request, or fixing a weak, brittle, or flaky test — or when the user says “test quality”, “unit test review”, “these tests are brittle”, “flaky test”, “over-mocking”, “testing implementation details”, “AAA”, “arrange act assert”, or “assert on behavior”.
Use when completing implementation, fixing bugs, refactoring code, or any time you need to verify the test suite passes. Also use when tests fail and you hear "pre-existing" or "not my changes" — enforces strict code ownership. Ensures MECE coverage (no overlap, no gaps) and that ALL test categories including E2E are executed.
Integrate TheSys C1 Generative UI API to stream interactive React components (forms, charts, tables) from LLM responses. Supports Vite+React, Next.js, and Cloudflare Workers with OpenAI, Anthropic Claude, and Workers AI. Use when building conversational UIs, AI assistants with rich interactions, or troubleshooting empty responses, theme application failures, streaming issues, or tool calling errors.
Generate thumbnail concepts and ideas for YouTube, TikTok, and other video platforms. Creates detailed visual briefs with composition, text, colors, and emotion suggestions. Use when planning thumbnails, improving CTR, or briefing designers.
Engineering foundation skill for writing high-quality, compile-in-one-pass, edit-safe TikZ/LaTeX figure code. Teaches the agent to use "layout by construction" (positioning/fit/chains/anchor) instead of "hand-filled absolute coordinates", with 8 hard constraints, canonical arrows, before/after examples, and a static check entry point (lint.sh). Use when: writing/reviewing TikZ or LaTeX figure code, fixing figure layout/alignment/overflow/arrow problems, tikz layout, latex figure code, tikz compilation errors, CJK Chinese figures rendering as color blocks.
Real-time trade signals with executable Buy/Sell/Hold recommendations for stocks. Use when asked about trading decisions, stock analysis, technicals, buy/sell calls, earnings plays, price targets, analyst ratings, entry/exit points, portfolio rebalancing, or any investment decision requiring actionable intelligence. Supports US + Global markets, Asia emerging markets, individual stocks, ETFs, and options strategies.
tmux for AI agents. Run dev servers and TUIs in named background sessions that agents can read, wait on, snapshot, and type into. Replaces tmux with reactive waiting instead of blind `sleep`. Projects wrap their dev script with tuistory (`"dev": "tuistory -- next dev"`) so agents get a background session and humans get auto-attached. Use tuistory when you need to: - Run background dev servers or long-lived processes - Control interactive CLIs and TUIs (type, press keys, click, wait, snapshot) - Write Playwright-style tests for terminal apps **CLI** (`tuistory`) for background sessions. **JS/TS API** (`launchTerminal`) for programmatic control and tests.
Configure TOTP authenticator apps, send OTP codes via email/SMS, manage backup codes, handle trusted devices, and implement 2FA sign-in flows using Better Auth's twoFactor plugin. Use when users need MFA, multi-factor authentication, authenticator setup, or login security with Better Auth.
Use this skill for Tailwind setup, migration, integration, and utility-first styling. Apply it when the task mentions Tailwind directives or utilities, @import "tailwindcss", @theme, plugin wiring, legacy-to-modern migration, token bridging with CSS variables, or framework-specific Tailwind build issues.
This skill should be used when the user asks about Unicode rendering, wcwidth, grapheme clusters, emoji, combining marks, East Asian width, BiDi text, box drawing, Nerd Fonts, color themes, truecolor, 256-color fallback, NO_COLOR, contrast, accessibility, screen-reader behavior, keyboard access, reduced motion, or non-TUI fallbacks. PROACTIVELY activate for: Unicode width bugs, misaligned tables, emoji layout, ANSI-aware string measurement, color accessibility, screen-reader friendly CLI design, plain output mode, ASCII fallback, and terminal theme support. Provides: text measurement rules, color/fallback policy, accessibility checklist, and failure-mode fixes.
Static performance audit for Unity projects. Triggers: /perf, /perf-audit, 'audit performance', 'optimiser performance', 'anti-pattern performance', 'frame rate', 'profiler', 'budget fps'. Analyses the project's C# code to detect performance anti-patterns (CPU, GPU, memory). Produces a report with severity, file:line locations, and concrete before/after fixes.
Guide for modifying USD ASCII (.usda) files and command-line USD workflows, including prims, properties, composition arcs, variants, transforms, usdcat, usdchecker, usdrecord, usdtree, usdzip, and usdedit. Use when editing or reviewing .usda files by hand, validating USD/USDZ assets, or working in an asset pipeline outside runtime Swift USDKit.
Use when you need to run interactive CLI tools (vim, git rebase -i, Python REPL, etc.) that require real-time input/output - provides tmux-based approach for controlling interactive sessions through detached sessions and send-keys
Generate correctly formatted UTM parameters and full tracking URLs for creator marketing campaigns. This skill should be used when building UTM links for influencers, creating tracking URLs for a creator campaign, generating UTM strings for multiple creators, setting up campaign tracking links, formatting UTM parameters for influencer partnerships, building attribution links for creator posts, creating unique tracking URLs per creator, batch generating UTM links for a roster of creators, or setting up link tracking before a campaign launch. For measuring campaign results after launch, see campaign-roi-calculator. For normalizing metrics from multiple sources, see metrics-normalization-formatter.
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.
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.
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.
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.