Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
What a knowledgeable local with great taste would tell you to walk to. Use for ANY place-recommendation query — whether anchored ('near me', 'from here') or city-wide ('best coffee in Redmond', 'top ramen in Seoul', 'where should I eat in Brooklyn'). The CLI accepts a city name, neighborhood, address, or lat,lng as the anchor — so even bare 'best X in <city>' queries should run through it instead of being answered from model knowledge. Trigger phrases: `best <thing> in <place>`, `top <thing> in <place>`, `where to <verb> in <place>`, `good <thing> near <place>`, `what's good in <place>`, `recommendations for <place>`, `what should I walk to from here`, `find me a kissaten`, `amazing places near me`, `is <place> still open`, `sunset photo spots near`, `sync this city for offline`, `use wanderlust-goat`, `run wanderlust-goat`.
Deploy code to Railway using "railway up". Use when user wants to push code, says "railway up", "deploy", "ship", or "push". For initial setup or creating services, use railway-new skill. For Docker images, use railway-environment skill.
RDMA verbs skill for InfiniBand and RoCE programming. Use when using libibverbs API, creating queue pairs, RDMA read/write operations, or benchmarking with perftest. Activates on queries about libibverbs, ibv_reg_mr, ibv_create_qp, RDMA, RoCE, ib_send_bw, or rdma-sys.
Design and development best practices for Claude Code skills, MCP tools, and AI agent capabilities. Use when creating skills, writing SKILL.md files, designing tool descriptions, or optimizing triggers. Triggers on "create a skill", "skill template", "write skill instructions", SKILL.md, metadata.json, progressive disclosure, trigger optimization, MCP tool design, or skill testing. Does NOT cover specific frameworks or languages (use dedicated skills).
Adapts and reviews SwiftUI apps for iPhone Duo (Xcode 27.1 / iOS 27.1 SDK) and continuously changing window sizes. Use when supporting the foldable iPhone Duo, outer or inner display, vertical bars (toolbarVerticalBehavior, axisBehavior, visibilityPriority, ToolbarOverflowMenu), sheet placement, reserved regions and the fold, ArrangementView, onHingeChange, CameraCaptureAccessory, NavigationSplitView, adaptive TabView sidebar, ViewThatFits, AnyLayout, or when replacing UIDevice / UIScreen.main / idiom / orientation layout branches.
Finding validation before writing any report — 7-Question Gate (all 7 questions), 4 pre-submission gates, always-rejected list, conditionally valid with chain table, CVSS 3.1 quick reference, severity decision guide, report title formula, 60-second pre-submit checklist. Use BEFORE writing any report. One wrong answer = kill the finding and move on. Saves N/A ratio.
Use when creating, reviewing, or styling charts, graphs, dashboards, sparklines, or any data visualization. Applies to Recharts, ECharts, Chart.js, matplotlib, Plotly, seaborn, D3.js, and SVG. Enforces Tufte principles (data-ink ratio, direct labeling, range-frame axes) plus modern screen-first standards (accessibility, responsive, dark mode)
Build MCP servers with TypeScript on Cloudflare Workers. Covers tools, resources, prompts, tasks, authentication (API keys, OAuth, Zero Trust), and Cloudflare service integrations. Prevents 20 documented errors. Use when exposing APIs to LLMs or troubleshooting export syntax errors, transport leaks, server instance reuse bugs, CORS misconfigurations, or task validation errors.
Scan Linux systems for persistence mechanisms, including crontab/systemd entries, LD_PRELOAD injection, shell profile modifications (.bashrc, .profile), and SSH authorized_keys backdoors, then correlate findings with auditd logs into an installation timeline. Use during incident response or threat hunting to detect or confirm how an adversary maintained access to a compromised Linux host.
Build 2D screen-space UI for Decentraland scenes with React-ECS: HUDs, menus, dialogs, health bars, form inputs, sliders. Use for any on-screen UI, UI editable in the Creator Hub UI Designer, or adapting existing coded UI for the editor. For 3D in-world text see advanced-rendering; for clickable 3D objects see add-interactivity.
IC-specific security patterns for canister development in Motoko and Rust. Covers access control, anonymous principal rejection, reentrancy prevention (CallerGuard pattern), async safety (saga pattern), callback trap handling, cycle drain protection, and safe upgrade patterns. Use when writing or modifying any canister that modifies state, handles tokens, makes inter-canister calls, or implements access control.
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
Agent 2 of the video editing pipeline. Finds and removes spoken mistakes — stutters, repeated words, false starts, and retakes (re-recorded lines) — from a talking-head recording. Use after cut-silences, when asked to cut mistakes, remove stutters / repeats / filler restarts, clean up flubs, or keep the best take. Works review-gated: it proposes every cut with context and a reason for approval, then renders only the approved cuts via ffmpeg. Requires a word-level transcript.
Create HTML dashboards with KPI metric cards, bar/pie/line charts, progress indicators, and data visualizations. Use when users request dashboards, metrics displays, KPI visualizations, data charts, or monitoring interfaces.
Expert blueprint for real-time strategy games including unit selection (drag box, shift-add), command systems (move, attack, gather), pathfinding (NavigationAgent2D with RVO avoidance), fog of war (SubViewport mask shader), resource economy (gather/build loop), and AI opponents (behavior trees, utility AI). Use for base-building RTS or tactical combat games. Trigger keywords: RTS, unit_selection, command_system, fog_of_war, pathfinding_RVO, resource_economy, command_queue.
Use the Jev AI decision API from an AI coding agent when a workflow needs a typed choice, score, or yes/no judgment for routing, classification, verification, context compression, or a safety gate. On first use, guide the user through language, API key, and help configuration. Do not use it for open-ended writing, deterministic rules, exact lookups, or final permission enforcement.
Kalshi daily and hourly range markets on crypto prices (BTC, ETH) and equity indices (S&P 500, Nasdaq-100) — bracket structure, Gaussian P(YES) modeling on price/vol, close-offset decision timing, longshot-sell edge with honest evidence bounds
Socratic tutor that teaches codebase understanding through questioning, challenges, and active recall. Invoke with /learn-codebase when onboarding to a new codebase or deepening understanding of existing code. Maintains a learning journal that tracks mastery and schedules reviews.
Explains how macro events such as interest rates, inflation, employment, and growth affect stock markets, styles, and sectors, helping assess short-term shocks and medium-term implications. Use to interpret macro data days, monetary policy meetings, and policy windows.
Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can edit before publishing or testing. Use when Codex needs to create a new personal plugin, add optional plugin structure, or generate or update personal or repo-root `.agents/plugins/marketplace.json` entries for plugin ordering and availability metadata.
Leader's prep on a single rep before a 1:1 - their pipeline, recent activity, what they've been working on per chat and calendar, and where they might need help. Use when the user asks "prep for my 1:1 with [rep]" (a rep you manage), "how is [rep] doing", or "what's [rep] working on".
Strategic sales leadership guidance for B2B SaaS and enterprise software companies. Covers sales strategy, team building, pipeline management, enterprise selling, discovery calls, demos, proposals, negotiations, and sales operations. Use when building sales teams, designing sales processes, improving win rates, or scaling revenue operations. Use for "sales strategy", "sales process", "pipeline review", "deal strategy", "sales hiring", "quota planning".
Build, extend or deploy a Decentraland SDK7 scene. Load it first for any scene task: when to confirm with the user (parcel changes, asset downloads, the Multiplayer Server, a scene open in the Creator Hub, Blender MCP fallback, SDK bug reports), the composite-first rule, and the index of which topic skill to load.
Run a comprehensive on-page SEO audit or optimization pass covering title tags, meta descriptions, header structure, content quality, internal links, image optimization, URL hygiene, and on-page schema. Use this skill whenever the user asks to optimize a page, audit on-page SEO, fix titles or meta tags, review header structure, check internal linking, improve a single URL's search performance, or write SEO-friendly copy. Triggers on on-page SEO, page audit, title tag, meta description, H1, header structure, internal links, image alt, URL slug, page optimization, optimize this page, SEO this page. Also triggers for any single-page review where ranking, click-through, or relevance signal quality is the goal, even if the user does not say 'SEO' explicitly.
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
Puts real design variations of one project file on the user's own localhost, behind a small card that flips them with the arrow keys, then keeps listening for their verdict. Use when the user wants design variations, alternatives, or directions to choose between; asks to try a different hero, layout, palette, section, or page; wants to design something new and compare a few takes; clicked the card (a vary, more, or done ask is queued); or wants to continue or finish a variate session. It works in an empty folder (serves a page, drafts four fresh designs) and in a real project (varies one file in place), on any stack. Not for a single change with one right answer, a refactor, or a non-visual edit: just edit the file for those
VHS terminal recording best practices from Charmbracelet (formerly charmbracelet-vhs). This skill should be used when writing, reviewing, or editing VHS tape files to create professional terminal GIFs and videos. Triggers on tasks involving .tape files, VHS configuration, terminal recording, demo creation, or CLI documentation
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components—not for simple single-file HTML/JSX artifacts.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components—not for simple single-file HTML/JSX artifacts.
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.