Skills
100,696 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Pre-flight checklist for long-running ML training jobs covering config diff, run naming, path verification, monitoring setup, and restart-cleanup. Use when the user asks to launch, kick off, start, restart, or kill a training run, or mentions launching a multi-hour or multi-day GPU job (python train, accelerate launch, torchrun, deepspeed, sbatch, tmux training).
Write, refactor, and review Rails code using layered architecture principles from “Layered Design for Ruby on Rails Applications”. Use when writing or refactoring Rails code—models, controllers, services, jobs, mailers, policies, forms, query objects, presenters, view components, state machines, serializers, or AI/LLM features—to apply correct patterns and avoid layer violations; and when reviewing Rails code, PRs, or diffs for layer violations, fat controllers/models, anemic models, callback misuse, god objects, or specification-test failures. Triggers on “layered design”, “architecture layers”, “abstraction layer”, “specification test”, “layer violation”, “fat controller/model”, “god object”, “anemic model”, “extract service/callback/policy/concern”, “service object”, “form/policy/query/value object”, “presenter”, “view component”, “state machine”, “Active Delivery”, “callback scoring”, “Rails refactor/review”, “Rails patterns/best practices”, “archspec”, or “architecture linter/enforcement”.
When the user wants to create, plan, or optimize a lead magnet for email capture or lead generation. Also use when the user mentions "lead magnet," "gated content," "content upgrade," "downloadable," "ebook," "cheat sheet," "checklist," "template download," "opt-in," "freebie," "PDF download," "resource library," "content offer," "email capture content," "Notion template," "spreadsheet template," or "what should I give away for emails." Use this for planning what to create and how to distribute it. For interactive tools as lead magnets, see free-tool-strategy. For writing the actual content, see copywriting. For the email sequence after capture, see email-sequence.
LetsFG — Agent-native flight and hotel search and booking API. Every airline in the world plus the major booking sites (Google Flights, Skyscanner, Kiwi, Kayak, Momondo), with per-flight reliability history and instant booking. Plus real bookable hotel rates, refundable and non-refundable: the price is held on the connected card and charged only once the hotel confirms. letsfg.co
LibTV (LibLib.tv) advanced video workflow skill: one-click AI video generation, automatic download, and smart editing (with transitions, subtitles, BGM). Use when the user wants to create AI videos or short films using LibTV, especially when they need automatic video editing with transitions, subtitles, or background music.
Call hosted LLMs (OpenAI GPT, Anthropic Claude, Google Gemini, open-weights models) through the Lightning AI models API / LLM gateway - chat, streaming, multi-turn conversations, images, and model metadata; plus the teamspace model checkpoint registry. Use when the user wants to run inference through lightning.ai, compare gateway models, or manage model artifacts on the platform.
Trace relationships between semantic models and downstream reports across Fabric workspaces. Automatically invoke when the user asks to "find downstream reports", "show report lineage", "impact analysis", "what depends on this dataset", "cross-workspace lineage", "which reports are connected", "get model dependencies", or mentions model-to-report dependency tracing.
Guide for developing Lit web components in the Common UI v2 system (@commonfabric/ui). Use when creating or modifying cf- prefixed components, implementing theme integration, working with Cell abstractions, or building reactive UI components that integrate with the Common Fabric runtime.
Use for any task or question involving Livewire. Activate if user mentions Livewire, wire: directives, or Livewire-specific concepts like wire:model, wire:click, invoke this skill. Covers building new components, debugging reactivity issues, real-time form validation, loading states, migrating from Livewire 2 to 3, converting component formats (SFC/MFC/class-based), and performance optimization. Do not use for non-Livewire reactive UI (React, Vue, Alpine-only, Inertia.js) or standard Laravel forms without Livewire.
Building AI-powered NPCs that maintain personality, remember conversations, and never break characterUse when "npc dialogue, ai npc, llm npc, character dialogue, npc personality, ai character, dialogue system llm, talking npc, conversational npc, dynamic dialogue, llm, npc, dialogue, ai-characters, personality, memory, game-ai, conversational-ai, role-playing" mentioned.
When distributing traffic across multiple servers or regions, use this skill to select and configure the appropriate load balancing solution (L4/L7, cloud-managed, self-managed, or Kubernetes ingress) with proper health checks and session management.
Product validation skill of the lyt series for existing products. Use when the user already has a specific product, a candidate product list, product screenshots, 1688/competitor links, supply chain materials, a CSV/XLSX candidate product table or backend test data, and wants to judge whether a product or a batch of candidate products is worth entering the test pool. Outputs "can test / hold / not recommended", facts/inferences/assumptions, 7-dimension validation, a minimal validation plan and a data gap checklist. Only handles product validation questions related to cross-border e-commerce, TikTok Shop, e-commerce product sales, supply chain, product pools, content, advertising, influencer distribution and store operations. Triggers: /lyt-product-validation, /产品验证, /单品验证, /候选品筛选, "can this product be done" "how to filter these candidate products"
Set up, authenticate, and manage MakeThisBetter feedback from Claude Code. Use when the user runs /makethisbetter followed by setup, update, setup-auth, login, signup, list, pick, respond, archive, restore, ready, release, decline, duplicate, reopen, or any feedback management command. Also triggers on MakeThisBetter setup, updating the widget, listing pending or archived feedback, choosing feedback to fix, responding to a Reporter, preparing a committed fix for release, or releasing deployed feedback.
Guide users through creating, managing, and testing server configuration automation using Ansible. When automating server configurations, deploying applications with Ansible playbooks, managing dynamic inventories for cloud environments, or testing roles with Molecule, this skill provides idempotency patterns, secrets management with ansible-vault and HashiCorp Vault, and GitOps workflows for configuration as code.
Multi-channel demand generation, paid media optimization, SEO strategy, and partnership programs for Series A+ startups. Includes CAC calculator, channel playbooks, HubSpot integration, and international expansion tactics. Use when planning demand generation campaigns, optimizing paid media, building SEO strategies, establishing partnerships, or when user mentions demand gen, paid ads, LinkedIn ads, Google ads, CAC, acquisition, lead generation, or pipeline generation.
Generate Bluetooth Low Energy (BLE) PHY waveforms. Read BEFORE writing any BLE waveform code to avoid hallucinating API patterns. Covers bleWaveformGenerator, bleIdealReceiver, bleCTEIQSample, bleAngleEstimate, bluetoothTestWaveform for LE1M/LE2M/LE500K/LE125K. Bluetooth Toolbox R2022a+.
Local memory management for agents. Compression detection, auto-snapshots, and semantic search. Use when agents need to detect compression risk before memory loss, save context snapshots, search historical memories, or track memory usage patterns. Never lose context again.
Analyzes open Dependabot PRs for semver level, CI, breaking changes, and security fixes, then squash-merges approved patch and minor updates one at a time, or only comments @dependabot rebase; supports a dry run. Use when the user explicitly asks to merge, process, or rebase Dependabot PRs. Never infer from green CI, an approved Dependabot PR, or stale or conflicting Dependabot PRs.
Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes, algorithms, user journeys), entity relationship diagrams (database schemas), C4 architecture diagrams (system context, containers, components), state diagrams, git graphs, pie charts, gantt charts, or any other diagram type. Triggers include requests to "diagram", "visualize", "model", "map out", "show the flow", or when explaining system architecture, database design, code structure, or user/application flows.
Use Miles AI, an expert WordPress designer, through composable CLI primitives. Use when the user wants to design or build a website, get design options for content they already have, design around existing copy or a brief, convert HTML into a WordPress block theme, edit or redesign a site, export site deliverables, resume work on an existing Miles site, or update/uninstall the Miles skill. Triggers include mentions of Miles, bymiles.ai, start.bymiles.ai, "build a website", "design directions", "WordPress theme", or supplying content/briefs that need a designed site.
Create Minecraft 3D models (Java/Bedrock) — generate a vanilla-Minecraft design and three-view reference with an image model, then build, texture, and animate the model directly in Blockbench through the Blockbench MCP server. Use when the user asks to 做一个 Minecraft 模型 / 生成一格 XXX / 把设计图或三视图建成 Blockbench 模型 / 给模组或资源包添加模型, or any request where a 3D model should be created or edited in Blockbench. Assumes Blockbench MCP is installed and running; if the MCP tools are unavailable, remind the user to install and start Blockbench MCP first.
Search the ecosystem for something that already solves the task before it gets built, and write the decision — reuse, extend or build — into the spec's Reuse research section as a spec-only commit. Use only when the user explicitly asks for reuse research or accepts an offer to run it.
Automated outreach and sales pipeline — cold email sequences, partnership outreach, lead generation, and prospect management. Use when the user needs cold email campaigns, sales sequences, lead generation, partnership outreach, B2B sales, or says 'cold email', 'outreach', 'lead gen', 'find prospects', 'sales sequence', or 'partnerships'.
Provides comprehensive guidance for MongoDB database including document operations, queries, aggregation, indexes, and best practices. Use when the user asks about MongoDB, needs to work with MongoDB collections, write queries, or design MongoDB schemas.
Design and build UI motion with intent — micro-interactions, transitions, entrances, scroll and hover behavior — applying the twelve principles of animation to a brand's settled system, in custom code. Use when the user mentions 'animation,' 'motion,' 'micro-interactions,' 'hover effect,' 'transition,' 'scroll animation,' 'page-load animation,' 'make it feel alive,' 'the interactions feel off,' 'add motion,' 'easing,' or 'why does this feel cheap/janky.' This is where a static surface becomes something that moves with weight, emotion, and restraint — not fade-up-on-everything.
Use when planning, auditing, or speccing a video's motion and visual craft: shot lists, storyboards, color scripts, transitions, easing, kinetic typography, pacing, retention, or animation principles. Triggers: 'video plan', 'shot list', 'storyboard', 'color script', 'motion spec', 'fix the pacing', 'explainer/demo/brand video'. For the spoken words themselves, use script-writer-skill; for in-code UI motion, use frontend-design.
WeChat Official Account article management tool. Used to manage the publishing and updating of WeChat Official Account articles. Use cases: publishing articles to the WeChat Official Account draft box; updating existing draft content; uploading image assets to the WeChat asset library. Core features: convert documents to WeChat Official Account HTML with AI, then use Python scripts to call the WeChat API for asset upload and draft management.
Generate music using ElevenLabs Music API. Use when creating instrumental tracks, songs with lyrics, background music, jingles, or any AI-generated music composition. Supports prompt-based generation, composition plans for granular control, and detailed output with metadata.
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.