Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Routes any sales, marketing, ad, or GTM objective to the right specialized skill and outputs the install command for that skill plus a ready-to-paste prompt packed with the user's context. Asks clarifying questions when the objective is ambiguous, then hands back a copy-paste-runnable next step. Covers prospecting, outbound cadences, deals, proposals, forecasting, deliverability, enrichment, intent, content, coaching, CRO, SEO, launch directories, newsletters, email/SMS/push marketing, chatbots, influencer marketing, social media, employee advocacy, media relations, reviews, data hygiene, B2B advertising, retargeting, affiliate, loyalty, digital products, memberships, webinars, checkout, and platform-specific help. Use when the user has a sales or marketing question and isn't sure which skill to use, or wants a multi-skill sequence with a batch install command. Do NOT use to solve problems directly—this skill only routes.
Generates cinematic, film-style video prompts for Seedance 2.0 (Higgsfield). Use when users want cinematic, film-like, movie-quality, Hollywood-style, dramatic, or professional film-quality AI video. Trigger keywords: cinematic, film look, movie scene, dramatic lighting, depth of field, lens flare, anamorphic, letterbox, film noir, epic, Steadicam, dolly shot, crane shot, or any cinematic video generation request. Use this skill even if the user doesn't explicitly say “cinematic” but describes a film aesthetic.
Configure the “Set Up Self Service for Employees on Slack” / “Slack for Employee Service” checklist for Employee Service (ITSM) on Slack — the employee side, covering the Slack for Employee Service org preference, Employee Slack Notifications permission-set assignment, employee portal (Digital Experience site) enablement/selection, and connecting Slack to a Preferred Digital Experience Site. Use this for: “set up Slack for Employee Service”, “assign Employee Slack Notifications permission set”, “manage user access for Slack employee service”, “select a preferred digital experience site for Slack”, “set up self service for employees on Slack”, or any request to complete the IT Service / Employee Service half of the Slack ITSM Go page checklist. DO NOT TRIGGER for the Microsoft Teams equivalents (service-itsm-teams-itservice-configure) or for turning ITSM notification preferences on or off.
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
Initialize or repair SigNoz MCP server configuration for Agent Plugins v1, Claude Code, Codex, Cursor, VS Code/GitHub Copilot, Claude Desktop, Gemini CLI, Devin CLI, Grok Build, Windsurf, Zed, Antigravity CLI, OpenCode, or another MCP client. Use this skill before any SigNoz docs, query, dashboard, alert, or view workflow when `signoz_*` tools are unavailable, or when the user says "setup SigNoz MCP", "configure SigNoz plugin", "wrong region", "change SigNoz region", "MCP auth failed", or asks to connect SigNoz Cloud or a self-hosted MCP endpoint, even if they do not mention the plugin.
A task-generation skill based on the speckit workflow. Generates actionable, dependency-ordered tasks.md from available design documents. Use it to generate detailed task lists for feature development based on design documents such as spec.md, plan.md, data-model.md, and contracts/. Triggers include “speckit tasks,” “generate tasks,” “task planning,” “feature task breakdown,” and “create tasks.md.”
Investigate, structure, and validate experiences through research, information architecture, journeys, flows, forms, onboarding, and error recovery. Use for usability, flow, discovery, content, or user validation problems; do not reduce UX to visual polish.
Use when the user is working on Spree 6 checkout: the Cart → Order split, checkout requirements and advisory steps, `Spree::Checkout::Registry` (add_requirement / register_step / base_steps), cart completion (`Spree::Carts::Complete`), `carts.complete` / `carts.add_item` workflow hooks, addresses, payment sessions, guest checkout, cart association/merge on login, or the Store API / `@spree/sdk` checkout sequence. Common phrasings include "checkout broken", "cart won't complete", "why can't this cart complete", "add a checkout step", "require a field before checkout", "require terms acceptance", "skip the delivery step", "order stuck", "double charge", "guest checkout", "cart not found after checkout", "merge carts on login", "custom checkout validation", and "block checkout if…". Covers where each customization belongs and how completion guarantees idempotency.
Use when the user is working with Spree 6 payments — payment methods and gateways (Stripe, Adyen, PayPal, Razorpay), session-based vs direct (offline) payment methods, payment sessions and payment setup sessions (saved cards), payment statuses, capture timing (checkout / on_dispatch / manual), capture and void, refunds, gateway webhooks, building a custom payment method, store credits and gift cards, and payment events. Common phrasings include "add payment gateway", "install Stripe", "custom payment method", "payment session", "client_secret", "3D Secure", "offsite redirect", "customer closed the tab", "payment webhook", "capture on shipment", "authorize only", "manual capture", "refund an order", "store credit", "gift card", "payment failed", "payment stuck", "payment.paid", "order.paid", "cash on delivery", "bank transfer", "purchase order".
Use when the user is working with Spree 6 pricing: variant prices per currency (price_in, amount_in, set_price), compare-at/sale prices, multi-currency, price lists and price rules (market, channel, volume), catalog-owned price lists for B2B/wholesale, percentage price adjustments, quantity breaks / volume pricing, scheduled sales, the pricing context and resolution order, external pricing providers, bulk price updates, and EU Omnibus price history (prior_price). Common phrasings include "set price", "variant.price", "compare at price", "sale price", "price list", "wholesale pricing", "customer-specific price", "volume discount", "tiered pricing", "quantity break", "schedule a sale", "multi-currency", "wrong price shown", "prior price", "Omnibus", "lowest price in 30 days", and "bulk update prices".
Use when the user is hardening a Spree 6 app, reviewing a PR or finding for security issues, managing secrets and API keys, configuring CORS/CSP, securing the dashboard or /jobs, handling GDPR data requests, or asking about Spree-specific risks (publishable vs secret keys, scope minimization, IDOR on carts/orders, rich-text XSS, webhook HMAC and SSRF, encrypted columns, PCI scope). Common phrasings include "Spree security", "leaked secret key", "rotate API key", "CORS", "Allowed Origins", "CSP", "XSS in product description", "IDOR", "cross-store data leak", "mass assignment", "permitted attributes", "webhook signature", "SSRF", "Active Record encryption", "GDPR", "anonymize customer", "PCI", "Mission Control password". For roles, permission keys and login strategies use spree-auth-permissions.
Build and deploy Streamlit apps natively in Snowflake. Covers snowflake.yml scaffolding, Snowpark sessions, multi-page structure, Marketplace publishing as Native Apps, and caller's rights connections (v1.53.0+). Use when building data apps on Snowflake, deploying SiS, fixing package channel errors, authentication issues, cache key bugs, or path resolution errors
Apply platform accessibility best practices to SwiftUI, UIKit, and AppKit code. Essential companion to any SwiftUI, UIKit, or AppKit skill — always use together. Use whenever writing, editing, or reviewing ANY SwiftUI views, UIKit view controllers, AppKit views/window controllers, or platform UI — even when the user doesn't mention accessibility. Also use when the user mentions VoiceOver, Voice Control, Dynamic Type, Reduce Motion, screen reader, a11y, WCAG, accessibility audit, Nutrition Labels, accessibilityLabel, UIAccessibility, NSAccessibility, assistive technologies, or Switch Control. Not for server-side Swift, non-UI packages, or CLI tools.
Use this skill when users ask how to build or customize Syncfusion PivotView pivot tables in Angular. Trigger for Angular pivot grid/OLAP, aggregation, data binding (JSON/remote), drill-down/drill-through, grouping, filtering, conditional formatting, exports (Excel/PDF/CSV), or pivot charts. Angular-only, not React/Vue/Blazor.
When a solution seems impossible and the path forward is blocked. Refuses to take no for an answer: classifies what kind of "no" you hit, then runs lateral-thinking techniques (assumption autopsy, inversion, first principles, constraint toggling, analogical transfer, and more) until the wall cracks or is proven load-bearing. Generates at least 10 angles before evaluating any. AGENTS: use this on yourself when an API doesn't support what you need, an approach has failed twice, or a "that's not possible" sentence is forming — run the fast path BEFORE reporting a dead end. Archives walls to ~/.config/makerskills/unstuck/archive/. Sits upstream of decide. Triggers on "/unstuck," "I'm stuck," "this seems impossible," "we hit a wall," "there's no way to," "they said no," "dead end," "out of options," "I've tried everything," "work around this."
Build and run iOS/macOS apps using xcodebuild and xcrun simctl directly. Use when building Xcode projects, running iOS simulators, managing devices, compiling Swift code, running UI tests, or automating iOS app interactions. Replaces XcodeBuildMCP with native CLI tools.
An all-in-one note-generation tool for Xiaohongshu content creation, based on a continuously updated collection of over 2,000 viral notes gathered daily from across the web. It searches for currently popular viral notes using user-provided keywords, then uses AI to deeply analyze their structure, opening logic, informational density, and engagement language. It extracts key drivers of reach and creative techniques, follows Xiaohongshu’s content ecosystem and sharing dynamics, and generates complete, fluent, compliant, ready-to-publish notes—lowering the barrier to creation and enabling efficient production of high-reach content. Run only in the main Agent; do not delegate to subagents. If the API returns insufficient credits (code=3210), automatically open Alipay to top up and continue the query.
Use when you need to write unit tests for Micronaut applications — Mockito-first with @ExtendWith(MockitoExtension.class), @MicronautTest with @MockBean, HttpClient @Client(/) assertions, @Property overrides, @ParameterizedTest, and *Test vs *IT naming. For framework-agnostic Java use @131-java-testing-unit-testing. This should trigger for requests such as Add or improve unit tests in a Micronaut project; Reduce unnecessary @MicronautTest usage with Mockito-first tests; Write Mockito-first unit tests for Micronaut services; Mock Micronaut bean collaborators in unit tests; Review fast Micronaut tests without application context. Part of Plinth Toolkit
Warren Buffett's thinking framework and communication style. Based on in-depth research into over 60 years of primary sources, including shareholder letters, annual meeting records, detailed interviews, and authorized biographies, it distills 6 core mental models, 8 decision-making heuristics, and a complete communication profile. Use as a thinking advisor to analyze problems, examine decisions, and provide feedback from Buffett's perspective. Use when the user mentions "用巴菲特的视角", "巴菲特会怎么看", "巴菲特模式", or "Buffett perspective". Trigger even if the user only says "帮我用巴菲特的角度想想", "如果巴菲特会怎么做", or "切换到巴菲特"
Refresh stale or drifting learnings and pattern docs in docs/solutions/ by reviewing, updating, consolidating, replacing, or deleting them against the current codebase. Use after refactors, migrations, dependency upgrades, or when a retrieved learning feels outdated or wrong. Also use when reviewing docs/solutions/ for accuracy, when a recently solved problem contradicts an existing learning, when pattern docs no longer reflect current code, or when multiple docs seem to cover the same topic and might benefit from consolidation.
Help developers integrate Chainlink VRF into smart contracts. Use for consumer contract generation with VRFConsumerBaseV2Plus, subscription setup and funding (LINK or native), keyHash and gas lane selection, coordinator address lookup and debugging VRF integrations. Trigger on any mention of VRF, verifiable randomness, on-chain random number generation, requestRandomWords, fulfillRandomWords, VRF subscription, VRF coordinator, keyHash, or provably fair randomness in a smart contract, even if the user does not say 'VRF' explicitly.
Operate Chatwoot helpdesks from the terminal — list and triage conversations, send replies and private notes, assign agents and teams, change status, set labels and priority, search contacts, inspect inboxes, and search help center articles via the `chatwoot` CLI. Use when the user wants to read, summarize, or act on Chatwoot conversations or help center content from the shell, scripts, agent workflows, or CI. Always load this skill before running `chatwoot` commands — it contains the noun/verb grammar, the output-format contract, and the safety rules that prevent customer-visible mistakes.
Customer.io CLI - use for Customer.io, Journeys, CDP Pipelines, new-account onboarding and signup, app integration, SDK setup, message design, message automation (automations, broadcasts, transactional messages), plans and billing, service account tokens, sources, destinations, identify/track events, and fly.customer.io / cdp.customer.io errors. Trigger even when the user does not name the CLI.
Pre-implementation confidence assessment (≥90% required). Use before starting any implementation to verify readiness with duplicate check, architecture compliance, official docs verification, OSS references, and root cause identification.
Guides agents through creating and safely sizing a Replay Vision scanner: choosing the scanner type (monitor/classifier/scorer/summarizer), shaping the RecordingsQuery that selects sessions, and — crucially — estimating the credits it will spend and checking the org's remaining budget before creating, so a broad scanner doesn't exhaust the budget on its first scheduled sweep. TRIGGER when: user asks to create, set up, or configure a Replay Vision scanner, OR when you are about to call vision-scanners-create, OR when widening an existing scanner's query, sampling_rate, or sampling_mode (or moving it to a pricier model) via vision-scanners-update. DO NOT TRIGGER when: only reading scanners or observations, deleting a scanner, or running an existing scanner against sessions on demand (vision-scanners-scan-session/-scan-sessions). For a one-off question about sessions you already have, use vision-scanners-inline-scan rather than creating a scanner — the skill's first section covers when that applies.
The house rules for ANY design or UI work — the verification protocol (run the gate, never claim a number), the absolute no-emoji rule, token by intent, one shared theme, the eight states, one thing leads, and output completeness. Load this FIRST whenever building, reviewing, or theming a screen, component, or token set. Installed as a plugin, this skill carries what CLAUDE.md carries in the repo.
Pre-publish QA framework for content. Brief adherence, voice consistency, fact accuracy, structure and clarity, AI-content audit, SEO and AEO compliance, internal linking and schema validation, QA at scale via sampling, the QA workflow, and the discipline that distinguishes catch-problems QA from checkbox QA. Triggers on editorial QA, content review, pre-publish review, content audit, content QA process, AI-content audit, hallucination check, content sampling, programmatic QA, voice consistency check, brief adherence check. Also triggers when a content team is shipping sloppy work, when AI-co-authored content is reaching publish unaudited, when a QA process burns reviewers out, or when a programmatic SEO set needs sampling discipline. On a voice consistency check, this skill owns checking a draft against an existing voice system at the publish gate; use `brand-voice` when the voice system itself needs defining or documenting.
Query Fintel (fintel.io) institutional market data through its REST API or official MCP server. Use this skill whenever the user mentions Fintel or asks about short interest, short interest ratio or days to cover, short squeeze data, borrow rate or cost to borrow, shares available to borrow, daily short volume, fails-to-deliver (FTD), 13F institutional owners ("who owns X"), insider buying or selling from SEC Form 3/4/5, analyst price targets, ratings and forecasts, dividend or earnings history and calendars, EOD or last prices, security lookup by ticker, CUSIP, ISIN, or FIGI, Fintel leaderboards, or their Fintel watchlists and alerts. Read-only: GET endpoints only.
Expert patterns for porting desktop games to mobile, including touch control schemes (virtual joystick, gesture detection), UI scaling for small screens, performance optimization for mobile GPUs, battery life management, and platform-specific features. Use when creating mobile ports or cross-platform mobile builds. Trigger keywords: TouchScreenButton, virtual_joystick, gesture_detector, InputEventScreenTouch, InputEventScreenDrag, mobile_optimization, battery_saving, adaptive_performance, MOBILE_ENABLED
Consultation on incorporation (transitioning from a sole proprietorship to a corporation). Supports tax comparison simulations, choosing a corporate structure, incorporation procedures, executive compensation strategies, and social insurance comparisons. Trigger: "法人成り", "会社設立", "法人化", "株式会社にしたい", "合同会社", "法人税と所得税の比較", "役員報酬", "法人成りのタイミング", "マイクロ法人", "1人法人"
Use when working on landing pages — creation, copywriting, design, optimization, or conversion rate improvement. Covers hero sections, above-the-fold content, value propositions, CTAs, landing page templates, and high-converting page structure. Applies to sales pages, lead capture pages, product pages, and marketing site pages. Use this skill for landing page copy, landing page design, landing page optimization, CTA writing, conversion rate optimization, hero section content, value proposition work, and any page builder or landing page template tasks.
Integration skill for Lovable.dev projects. Activates when working with: - Lovable.dev projects with GitHub sync - Supabase Edge Functions that need deployment - Database migrations for Lovable Cloud - Projects with supabase/ directory structure - Any mention of "Lovable", "deploy edge function", "apply migration" Provides exact Lovable prompts for backend operations that can't be done via GitHub alone.
Use when authoring or debugging Meteor publications and subscriptions (Meteor.publish, Meteor.subscribe). Triggers on publication strategies (SERVER_MERGE, NO_MERGE, NO_MERGE_NO_HISTORY), the low-level publish API (added/changed/removed), cursor authorization, reactive joins, leaked documents. Use this skill when the user asks about pub/sub or asks about reactive data fetching.
Interact with Google NotebookLM (notebook.google.com) notebooks — chat with the AI, generate artifacts (slides, audio, video, mind maps, quizzes, flashcards, infographics, reports, data tables), manage sources (add URLs, YouTube, files, text), run research (fast/deep web research), and manage notes. Use whenever the user mentions NotebookLM, a notebook.google.com URL, audio overviews, or wants to query, create content from, or manage their notebook sources — even if they don't say "NotebookLM" explicitly.
Generates OpenAPI 3.0/3.1 specifications from Express, Next.js, Fastify, Hono, or NestJS routes. Creates complete specs with schemas, examples, and documentation that can be imported into Postman or Insomnia, or used with Swagger UI. Use when users request “generate openapi,” “create swagger spec,” “openapi documentation,” or “api specification”
Podcast knowledge workflows powered by Podwise CLI: search podcasts and episodes by keyword, monitor followed shows for new releases, find popular episodes, ask questions and extract insights from transcript content, process Podwise episode URLs, YouTube videos, Xiaoyuzhou links, and local audio or video files to retrieve transcripts, summaries, chapters, Q&A, mind maps, highlights, and keywords — plus catch up on your backlog, refine your listening taste, generate weekly recaps, export episode notes to PKM tools, research topics across podcasts, debate episode ideas, and generate language learning cards. Use when the user wants to find, summarize, transcribe, or extract insights from any podcast or audio content, or manage their listening library.
Use when planning a multi-step task or working in plan mode and you need to capture the plan as a durable, resumable artifact — breaking work into phases with per-item checkboxes, completion tracking, autonomous verification, and a handoff summary so a future agent can pick up where you left off. Use when user wants to create or design a plan or mentioned "real work".
Create and edit editable draw.io / diagrams.net diagrams (.drawio XML), outputting .drawio + PNG/PDF. Three approaches: use built-in templates (five-band technical roadmap, three-column research framework, three-column phase flowchart, landscape task pipeline), write XML from scratch, or faithfully recreate a reference image. Use when the user requests a technical roadmap, full-text overview, research framework, paper flowchart, algorithm flowchart, model/system architecture diagram, method illustration, a single diagram summarizing a paper or research topic, a defense presentation figure, a drawio diagram, an editable vector redraw of a reference image, or diagram fixes (text overflow, misdirected arrows, inconsistent colors, misaligned layout). For data charts such as line charts and heatmaps, use scibox-figure instead.
Use when implementing authentication/authorization, securing user input, or preventing OWASP Top 10 vulnerabilities — including custom security implementations such as hashing passwords with bcrypt/argon2, sanitizing SQL queries with parameterized statements, configuring CORS/CSP headers, validating input with Zod, and setting up JWT tokens. Invoke for authentication, authorization, input validation, encryption, OWASP Top 10 prevention, secure session management, and security hardening. For pre-built OAuth/SSO integrations or standalone security audits, consider a more specialized skill.
Use when the user wants to extend an existing Spree 6 model or API controller without forking — add an association to Spree::Product, add a validation or scope, add a method to Spree::Cart / Spree::Order, narrow what an API v3 endpoint returns, permit an extra attribute on writes. Common phrasings include "add brand to product", "decorate Spree::X", "ProductDecorator", "OrderDecorator", "Module#prepend", "spree:model_decorator", "spree:controller_decorator", "extend an existing Spree model", "add a method to Spree::Order", "override Spree behavior", "monkey patch Spree", "customize an API controller". Provides the decorator pattern, the generators, the prepended(base) idiom, API controller decorators and the gotchas — and routes behavioral changes to workflow hooks, events or dependencies instead.
Use when deploying a Spree 6 application to production or scaling it — Docker image builds, Render/AWS/Railway/Kubernetes/VPS, required environment variables, Solid Queue (jobs in Puma vs a dedicated `bin/jobs` worker), Solid Cache, optional Sidekiq/Redis, the Mission Control `/jobs` dashboard, serving the React dashboard at `/dashboard` or from a static host, migrations on boot and `spree:upgrade`, S3/R2 storage, CDN_HOST, Meilisearch, PostgreSQL/MySQL/SQLite, and observability (spree_opentelemetry, Sentry). Common phrasings include "deploy Spree", "Spree Docker image", "spree build --production", "Render deploy", "Spree environment variables", "split the worker", "SOLID_QUEUE_IN_PUMA", "jobs not running", "/jobs dashboard locked", "dashboard 404 in production", "images point at localhost", "S3 setup", "Sidekiq instead of Solid Queue", "OpenTelemetry tracing". Spree-specific bits only — generic Rails deployment is out of scope.
Use when translating a Spree 6 store — adding a locale, translating product/category/collection content, fixing missing translations, building a multilingual storefront, syncing translations from a TMS via the Admin API, making a custom model translatable, working with Mobility, or wrangling `Spree.t` / dashboard i18next keys. Common phrasings include "add Spanish to Spree", "translate products", "Mobility", "translation tables", "RTL", "missing translation", "Spree.t", "fallback locale", "translated slugs", "translations API", "translate dashboard plugin", "X-Spree-Locale".
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.