Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use this skill when running PixiJS v8 outside a standard browser: Web Workers, OffscreenCanvas, Node/SSR, or CSP-restricted contexts. Covers DOMAdapter.set, BrowserAdapter, WebWorkerAdapter, custom Adapter interface, pixi.js/unsafe-eval for strict CSP. Triggers on DOMAdapter, BrowserAdapter, WebWorkerAdapter, Web Worker, OffscreenCanvas, Node, headless, SSR, CSP, unsafe-eval, Adapter.
Run the private gathering alongside a public technical event, once a named-guest programme already exists - how the seat list is assembled when sponsors, speakers and the organizer all put names forward, how invitations and the door work without publishing a tier, and where the gathering sits against the public programme. Use whenever the user mentions a private dinner or reception at a conference, refusing a sponsor's seat request, an invite-only room without a VIP badge, or when to schedule one - even if they never say "VIP". Folding it into the general evening is the default answer. Do NOT use to decide whether a guest qualifies - use samber/dev-event-organizer-skills@event-vip-management; food is samber/dev-event-organizer-skills@event-hospitality.
SEO drift monitoring: capture baselines of SEO-critical elements, detect changes and track regressions over time. Git for SEO: baseline, diff and track changes to your on-page SEO. Use when the user says "SEO drift", "baseline", "track changes", "did anything break", "SEO regression", "compare SEO", "before and after", "monitor SEO changes" or "deployment check".
Decide how many official social occasions a technical event runs and how they sit against each other one occasion, two on separate slots, or a themed multi-activity track - plus the inclusion floor a whole slate must clear rather than each activity separately. Use whenever asked whether to run more than one social activity, whether two social activities can run in the same hours, how to publish a social track, or which activity a caregiver or a non-drinker can be in. Do NOT use for a single occasion's format, food, drink or alcohol posture - use samber/dev-event-organizer-skills@event-hospitality - third-party satellites - use samber/dev-event-organizer-skills@event-side-event-coordination - or invite-only gatherings - use samber/dev-event-organizer-skills@event-vip-social-program.
Upgrades an existing assistant-ui application and applies the migrations needed to reach the current AI SDK v7 and assistant-ui 0.15.x lines. Use when updating, bumping, or migrating @assistant-ui/react, @assistant-ui/ai-sdk, the older @assistant-ui/react-ai-sdk alias, ai, or @ai-sdk/react, or when an upgrade exposes removed hooks, scope accessor calls, provider configuration, registry paths, event names, legacy interactables, or tool registrations. Start here for an existing project, post-update type failures, package compatibility, CLI codemods, and version-specific migration order. For a first install or a new project use setup; for authoring a runtime without an upgrade use runtime.
Prepare and execute negotiations using tactical empathy, calibrated questions, and the Ackerman method. Use when the user mentions “salary negotiation”, “contract terms”, “handling objections”, “mirroring and labeling”, “difficult conversation”, “deal terms”, “BATNA”, “anchoring”, “how do I ask for a raise”, “get a better deal”, or “they wont budge on price”. Also trigger when preparing for a vendor negotiation, resolving a pricing dispute, or navigating a high-stakes conversation where both sides need to feel heard. Covers accusation audits, Black Swan discovery, and the “Thats Right” technique. For persuasion in product and marketing, see influence-psychology.
Design how a hands-on technical workshop at a developer event or conference runs, once the format decision has committed hours to it - facilitator coverage, participant prerequisites and setup, capacity ceilings, session length, materials, and what breaks when a room of laptops cannot reach the network. Use whenever the user mentions planning sessions inside a workshop day, how many helpers a conference lab needs, a workshop's prerequisites, capping workshop seats, bring-your-own-laptop versus a provisioned environment, or WiFi for a room of participant laptops. Not for product docs or quickstarts. Do NOT use to place sessions in the grid - use samber/dev-event-organizer-skills@event-schedule-design; nor for hackathon mentors - use samber/dev-event-organizer-skills@hackathon-mentoring.
Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script. TRIGGER when: the user creates, reviews, or changes .agent files or aiAuthoringBundle metadata; asks to fix AgentScript, audit an existing agent, run an AgentScript health check, a common-pitfall review, or a baseline-versus-candidate repair loop; changes a response, action, subagent, route, state flow, or Agent Spec; migrates or upgrades a legacy GenAiPlannerBundle Agentforce agent (NOT an Einstein Bot) to an aiAuthoringBundle (Agent Script) agent; previews, debugs, deploys, publishes, or tests agents; uses sf agent generate/preview/publish/test; or manages Agentforce MCP servers, tools, assets, or authentication. DO NOT TRIGGER when: Apex, Flow, Prompt Template, Experience Cloud, or general Salesforce CLI work is unrelated to Agent Script; the source is an Einstein Bot (BotDefinition/BotVersion) — use agentforce-bot-upgrade; or the primary input is a production session or trace ID rather than an agent artifact.
Builds resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions. Covers the critical replay model, step operations, wait/callback patterns, error handling with saga pattern, testing with LocalDurableTestRunner. Triggers on phrases like lambda durable functions, durable execution, workflow orchestration, state machines, retry/checkpoint patterns, long-running stateful Lambda functions, saga pattern, human-in-the-loop callbacks, reliable serverless applications, context.step, context.wait, context.invoke, context.runInChildContext, withDurableExecution, DurableContext, UnrecoverableInvocationError, durable-execution-sdk, qualified ARN invocation, and durable handler replay.
Audit Lightning Web Components for SLDS design-system compliance and produce a scored quality report. Runs the SLDS linter and analyzes CSS for theming hook usage and pairing, scoring SLDS findings across categories into an overall grade. Use when asked to "score my component's SLDS", "SLDS scorecard", "SLDS quality report", "audit SLDS compliance", "how good is my SLDS", "check SLDS quality", "rate my SLDS styling", "evaluate my component's SLDS", "is this component's SLDS ready to ship?", "look at my LWC for SLDS issues", "audit SLDS before I submit", "review my component's SLDS before code review", or any time a user wants an SLDS quality assessment or SLDS production-readiness check on an LWC. Not for fixing violations (use design-systems-slds2-migrate), building new components (use design-systems-slds-apply), or accessibility/WCAG/ARIA audits (use experience-accessibility-validate).
Use this skill when displaying animated GIFs in PixiJS v8. Covers the pixi.js/gif side-effect import, Assets.load returning a GifSource, GifSprite playback (play/stop/currentFrame/animationSpeed), autoPlay/loop options, onComplete/onLoop/onFrameChange callbacks, GifSource sharing, clone, destroy. Triggers on: GifSprite, GifSource, pixi.js/gif, animationSpeed, currentFrame, autoPlay, onComplete, onLoop, onFrameChange, constructor options, GifSpriteOptions.
Smart Money analytics on OKX: leaderboard traders, position tracking, trade records, closed-position history, aggregated consensus signals, and signal history. Use this skill when the user asks about 聪明钱, smart money, 牛人榜, leaderboard, top traders, 交易员排行, trader ranking, trader positions, trader PnL, 交易员持仓, 交易员收益, 历史平仓, closed positions, realized PnL track record, trade history, 成交记录, smart money signal, 聪明钱信号, long/short ratio, 多空比, capital flow, 资金流向, position conviction, 仓位强度, entry price distribution, smart money overview, 聪明钱总览, signal history, 信号历史, trader search, 搜索交易员, who is trading BTC, 谁在交易BTC, recommend traders, 推荐交易员, best traders, top performers.
Profile and explore a dataset to understand its shape, quality, and patterns. Use when encountering a new table or file, checking null rates and column distributions, spotting data quality issues such as duplicates or suspicious values, or deciding which dimensions and metrics to analyze.
Troubleshoots and debugs AWS Clean Rooms collaboration issues related to IAM roles, S3 bucket policies, KMS keys, Lake Formation permissions, and CloudWatch logging for custom ML model training and inference jobs. Use when a customer reports permission failures, access errors, or log publishing issues in Clean Rooms.
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons or interact with web applications. Supports remote Browserbase sessions with Browserbase Identity, verified browsers, automatic CAPTCHA solving and residential proxies — ideal for protected websites and JavaScript-heavy pages.
Run an incident response workflow — triage, communicate, and write a postmortem. Trigger with "we have an incident", "production is down", an alert that needs severity assessment, a status update mid-incident, or when writing a blameless postmortem after resolution.
Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.
Routes any task involving AWS databases — choosing, comparing, recommending, getting started with, or operating a database — to the correct service-specific skill. Supersedes general training-data knowledge with post-training service updates, corrected limitations, and decision procedures for relational (Aurora, DSQL, RDS), key-value (DynamoDB), wide-column (Keyspaces), document (DocumentDB), graph (Neptune), time-series (Timestream), and in-memory/caching (ElastiCache, MemoryDB) workloads. Activates when a user describes building an application on AWS that will store, retrieve, or manage data, even if they do not mention 'database' explicitly.
Use this skill when users need to create or configure Salesforce Custom Tabs. Trigger when users mention tabs, navigation tabs, object tabs, web tabs, Visualforce tabs, Lightning component tabs, app page tabs, or tab configuration. Also use when users want to add navigation to custom objects, create tabs for external content, or set up Lightning page tabs. Always use this skill for any custom tab work.
Design MVPs, validated learning experiments, and pivot-or-persevere decisions using Build-Measure-Learn. Use when the user mentions "MVP scope", "validated learning", "pivot or persevere", "vanity metrics", "test assumptions", "innovation accounting", "build-measure-learn", "minimum viable experiment", "should we pivot", "test a business idea cheaply", or "build the smallest version first". Also trigger when deciding what to include in a first version, measuring startup progress, or evaluating whether to change direction on a product bet. Covers innovation accounting and actionable metrics. For 5-day prototype testing, see design-sprint. For customer motivation analysis, see jobs-to-be-done.
Control the user's own Chrome browser via Playwriter extension with Playwright code snippets in a stateful local js sandbox. Use this over other Playwright MCPs to automate the browser — it connects to the user's existing Chrome instead of launching a new one. Use this cli for navigating JS-heavy websites (Instagram, Twitter, cookie/login walls, lazy-loaded UIs) instead of webfetch/curl. ALWAYS load this skill before using any playwriter commands
Check “Is this business actually problem-free?” with just one business registration number — cross-reference free public data on the business registration status from the National Tax Service, National Pension Service-registered workplaces, national tax delinquencies, Financial Services Commission corporate summaries, Public Procurement Service disqualifications, and local government licensing and operating status, presenting only the facts in a due diligence report (no scores, grades, or risk judgments).
Evaluates, configures, and migrates workloads to AWS Lambda Managed Instances (LMI). Runs Lambda Event Functions (standard Lambda) on EC2 instances in the user's account while AWS manages provisioning, patching, scaling, routing, and load balancing. Triggers when queries mention Lambda Managed Instances, LMI, capacity providers, multi-concurrent execution environments, EC2-backed Lambda, persistent Lambda instances, PerExecutionEnvironmentMaxConcurrency, CapacityProviderConfig, cold start elimination via dedicated instances, migrating Lambda Event Functions to managed instances, or cost comparison between Lambda Event Functions and LMI with Savings Plans or Reserved Instances. Also covers long-running and asynchronous workloads and the 90-minute (5400s) function timeout for asynchronous and event-source-mapping (SQS, Kinesis, DynamoDB Streams / ESM) invocations, including how to raise the function timeout up to 90 minutes / 5400s and the related duration limits.
Set up, configure, and troubleshoot Salesforce Code Analyzer for any project. Handles installation, prerequisite checks, diagnosing broken setups, creating and editing code-analyzer.yml overrides, engine-specific settings, ignore patterns, severity overrides, and CI/CD pipeline setup. TRIGGER when: user says 'set up code analyzer', 'configure code analyzer', 'install code analyzer', 'code analyzer not working', 'fix my setup', 'scan failing', 'check my setup', 'enable/disable engine', 'exclude files', 'change severity', 'set up GitHub Actions', 'set up CI/CD', 'add to pipeline', 'pipeline fail', 'update my workflow', 'quality gate', 'fail on violations', 'scan changed files only', 'add SARIF', 'code-analyzer.yml', 'ESLint config', 'increase SFGE memory', or reports errors running Code Analyzer. DO NOT TRIGGER when: user wants to run a scan (use dx-code-analyzer-run), fix violations, explain rules, create custom rules (use dx-code-analyzer-custom-rule-create), or suppress violations.
Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.
Manages shadcn-vue components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn-vue, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for “shadcn-vue init”, “create an app with --preset”, or “switch to --preset”.
Writes opening hooks and post titles for long-form articles in EN or FR — blog posts, Substack/Medium/dev.to, LinkedIn long-form, newsletters, essays. Trigger whenever the user asks for a hook, opening, lede, intro, first sentence/paragraph, opener, accroche, attaque, phrase d'accroche, or première phrase — including punching up a flat intro or draft opening — or for a post title, titre d'article, or headline. Do NOT trigger for social posts (LinkedIn feed, Twitter/X, TikTok, Bluesky), READMEs, taglines, email subjects, ad copy, landing-page headlines, press releases, SEO meta, or body rewrites. Do NOT use for end-of-article CTAs — use samber/cc-skills@copywriting-cta instead.
Build the attendee-acquisition plan for a technical event - audience segments mapped to channels, the campaign-calendar spine (a ticketed event's percent-of-ticket-sales ladder or a free event's percent-of-attendance-goal curve), campaign moments pinned to pricing and program dates fixed elsewhere, budget allocated across the channel mix, funnel targets per phase, and each channel routed to the sibling that executes it. Use whenever asked to plan how to fill an event, run a ticket-sales or registration campaign, choose promotion channels, split promotion budget, or set registration targets by date. Do NOT use for the email copy itself - use samber/dev-event-organizer-skills@event-attendee-email-sequences - or ticket prices - use samber/dev-event-organizer-skills@event-ticket-pricing.
Performs pandas DataFrame operations for data analysis, manipulation, and transformation. Use when working with pandas DataFrames, data cleaning, aggregation, merging, or time series analysis. Invoke for data manipulation tasks such as joining DataFrames on multiple keys, pivoting tables, resampling time series, handling NaN values with interpolation or forward-fill, groupby aggregations, type conversion, or performance optimization of large datasets.
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.
Apply the seven principles of ethical persuasion (reciprocity, commitment, social proof, authority, liking, scarcity, unity) to product design, copy, and sales. Use when the user mentions "social proof", "persuasive copy", "why users dont convert", "ethical persuasion", "reciprocity", "scarcity tactics", "commitment and consistency", "shared identity", "in-group", "make my copy more persuasive", "increase trust", or "get more people to say yes". Also trigger when designing testimonial sections, crafting urgency messaging, or improving trust signals on landing pages. Covers the principles, when each applies, and ethical limits. For deal negotiation tactics, see negotiation. For viral word-of-mouth, see contagious.
Image generation and editing skill for GPT Image 2. Available in 3 environments: (A) Garden local mode, which generates images directly through an OpenAI-compatible interface and saves them to disk; (B) Host-Native mode, which uses this Skill as prompt-engineering guidance and passes the rendered prompt to the host Agent’s built-in image tool; (C) Advisor mode, which becomes a high-quality prompt advisor when the host has no image tools. Includes 80+ structured templates across 18 categories, covering posters, UI, products, infographics, academic illustrations, technical architecture diagrams, comics, avatars, storyboards, film storyboards, IP merchandise, and editorial workflows.
Translates Figma designs into production-ready code with 1:1 visual fidelity. Use when implementing UI from Figma files, when user mentions "implement design", "generate code", "implement component", "build Figma design", provides Figma URLs, or asks to build components matching Figma specs. Requires Figma MCP server connection.
Apply meta-principles of software craftsmanship: DRY, orthogonality, tracer bullets, and design by contract. Use when the user mentions "best practices", "pragmatic approach", "broken windows", "tracer bullet", "software craftsmanship", "avoid technical debt", "code ownership", or "how do I become a better developer". Also trigger when evaluating build-vs-buy decisions, designing estimation approaches, or choosing between reversible and irreversible architectural decisions. Covers estimation, domain languages, and reversibility. For code-level quality, see clean-code. For refactoring techniques, see refactoring-patterns.
Use when building Next.js 14+ applications with App Router, server components, or server actions. Invoke to configure route handlers, implement middleware, set up API routes, add streaming SSR, write generateMetadata for SEO, scaffold loading.tsx/error.tsx boundaries, or deploy to Vercel. Triggers on: Next.js, Next.js 14, App Router, RSC, use server, Server Components, Server Actions, React Server Components, generateMetadata, loading.tsx, Next.js deployment, Vercel, Next.js performance.
Use this skill when adding screen reader and keyboard navigation to PixiJS v8 apps. Covers AccessibilitySystem options (enabledByDefault, debug, activateOnTab, deactivateOnMouseMove), per-container accessibility properties, shadow DOM overlay, mobile touch-hook activation. Triggers on: accessibility, a11y, screen reader, ARIA, keyboard navigation, tab order, AccessibilitySystem, accessibleTitle, accessibleHint, tabIndex, accessibleChildren.
Read whether a technical event's concept, audience and price combination actually meets demand - before launch (community baseline, CFP oversubscription, saturation mapping), mid-sale (checkpoint ladder and pace index against expected sales), and after an edition (attendee return, sponsor renewal, sellout-speed trend) - composed into a go, hold, pivot or stop call. Use whenever asked to validate demand for a conference, hackathon or a meetup-to-conference jump, judge whether ticket sales are on pace, decide whether an event should recur or scale, or diagnose why an edition underperformed. Reads signals only. Do NOT use for launch scoping - use samber/dev-event-organizer-skills@event-first-edition - or growth levers - use samber/dev-event-organizer-skills@event-growth-strategy.
Use this skill when users need to create or configure tab-based Salesforce Custom Applications with navigation, branding, and action overrides. Trigger when users mention custom apps, application metadata, app navigation, or organizing tabs into applications. Use when users want to create app containers for tabs and pages. Do NOT use when the goal is hosting a React UI bundle in the App Launcher — use experience-ui-bundle-custom-app-generate for that case.
Use this skill when the user mentions 'onchainos ws', 'ws start', 'ws poll', 'ws stop', 'ws channels', 'ws session', 'ws channel-info', 'idle-timeout', 'idle timeout', 'WebSocket channels', 'WS频道', or asks about managing WebSocket sessions/会话管理. Also use when writing a custom WebSocket script/脚本/bot for real-time on-chain data. Covers: onchainos ws CLI commands (start/poll/stop/list/channels/channel-info), session lifecycle, idle-timeout configuration, and all 9 DEX WebSocket channels (price, candle, trades, price-info, signals, tracker, meme scanning).
Design, build, or improve web and mobile interfaces using real product examples from UIZZE’s 800,000+ web and iOS screens. Use for UI design, UX design, frontend or web design, mobile app UI, responsive layouts, design systems, redesigns, visual polish, interface critique, and requests like “make this UI better.”
Create irresistible offers using the Value Equation, bonus stacking, risk-reversing guarantees, and ethical scarcity. Use when the user mentions "grand slam offer", "make my offer more compelling", "what bonuses should I add", "guarantee strategy", "offer naming", or "people say its too expensive". Also trigger when packaging a product for higher perceived value, justifying premium pricing instead of discounting, designing a money-back guarantee, or structuring tiers to maximize conversions. Covers the MAGIC naming formula and starving-crowd targeting. For product positioning, see obviously-awesome. For outbound sales, see predictable-revenue.
Analyzes smart contract codebases to identify state-changing entry points for security auditing. Detects externally callable functions that modify state, categorizes them by access level (public, admin, role-restricted, contract-only), and generates structured audit reports. Excludes view/pure/read-only functions. Use when auditing smart contracts (Solidity, Vyper, Solana/Rust, Move, TON, CosmWasm) or when asked to find entry points, audit flows, external functions, access control patterns, or privileged operations.
Decide the food, drink and social provision every population at a technical event shares - the catering service style and the dietary counts it has to carry, what a scheduled break contains, the event's alcohol posture, and whether an evening or social programme exists and in what form. Use whenever asked what format to feed a conference in, how catering should cover dietary restrictions across a whole event, what to put in a coffee break, whether to serve alcohol or run the event dry, or what to do on the evening of a conference day. Sets the shared floor only. Do NOT use for how many social occasions run - use samber/dev-event-organizer-skills@event-official-social-program - or which dietary needs the event commits to - use samber/dev-event-organizer-skills@event-accessibility-inclusion.
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.