Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when the user is building or refactoring UI in their product codebase and wants designer-quality frontend code — not just functional code. Triggers on phrases like "design better", "make this UI feel more designed", "elevate the design quality", "build this with design best practices", "follow UX heuristics", "make this feel professional", "apply design polish", "review this for craft", or any request to apply UX/UI craft heuristics to code generation or review. Pairs with `docs/design.md` when it exists — the design system file owns **style** (colors, typography, spacing tokens, components), this skill owns **craft** (hierarchy, interaction, accessibility, motion, polish). Reference `docs/design.md` tokens by name for every visual decision; apply the 50-item heuristics catalogue and the Laws of UX catalogue below for every craft decision. When `docs/design.md` is absent, fall back to the codebase's existing design conventions and recommend the **Design System** skill. When a heuristic implies a token the design system doesn't have, flag it as a New Pattern to add via the **Design System** skill — never invent a value inline. Fully standalone.
Create videos programmatically with the Remotion framework. Remotion lets you define video content using React components and supports animation, subtitles, music visualization, and more. Triggers: “make a video with code,” “programmatic video,” “React video,” “Remotion,” “remotion,” “/remotion-video.” Use cases: programmatic video (1) batch generation, (2) data-driven videos such as annual summaries, (3) music visualization, (4) automatic subtitles; tutorial videos (5) visualizing technical concepts such as CNNs and algorithms, (6) layered, progressive explanations, (7) AI-voiced tutorials; 3D videos (8) product showcases/model animation, (9) cartoon character explanations, (10) 3D data visualization, (11) logo animation.
Use when the user asks to "map what our buyers believe", "capture the objections we keep hearing", or "find the switching forces that move the beachhead"; produces a belief map of the beachhead — held beliefs and mental models, the recurring objections and their reframes, and the JTBD four forces (push of the problem, pull of the new, anxiety of switching, habit of the present) — each item sourced from interviews or win-loss notes (User-provided) and labeled Measured / User-provided / Estimated, with any unverified quote or comparative claim marked "[needs source]" and routed to the claims candidates, never adjudicated here. Not for demographic or persona profiling — use audience-mapper; not for the positioning canvas — use positioning-truth-tracer. 受众信念/异议地图/切换四力/流失语言
When the user wants to plan product distribution via marketplaces, app stores, or third-party platforms. Also use when the user mentions "distribution channels," "marketplace listing," "app store listing," "Figma plugin," "Chrome extension marketplace," "AWS Marketplace," "Shopify app," "GPTs store," "app distribution," or "third-party marketplace." For channel mix, use integrated-marketing.
Apply when implementing asynchronous payment methods (Boleto, Pix, bank redirects) or working with callback URLs in payment connector code. Covers undefined status response, callbackUrl notification, X-VTEX-signature validation, sync vs async handling, correct delayToCancel configuration for each async method, and redirect-based flows where inboundRequestsUrl does not support browser GET redirects (requires custom public routes).
Analyze and optimize React component performance issues (slow renders, re-render thrash, laggy lists, expensive computations). Use when asked to profile or improve a React component, reduce re-renders, or speed up UI updates in React apps.
Use when the user asks to “turn this idea into posts for every platform,” “write the X thread / LinkedIn post / 小红书 note,” or “spec the carousel slides”; turns one idea into N platform-native, ready-to-paste packages — post/thread, caption, Threads text, 小红书 note, and link post with first-comment placement — each adapted to the dated platform norm card (never verbatim cross-posting). Every product claim must match approved claims-ledger wording or be flagged [needs source]. Each variant is tagged {formula | hook family | CTA type | signal optimized}, with a carousel slide-spec mode (intro/content/outro slide roles, per-element character budgets, 小红书 3:4 / IG 4:5 / LinkedIn document PDF artboards, text-safe-zone and alt-text checklist). Not for creator deliverable briefs — use brief-generator; not for repurposing existing assets with paid boost — use content-amplifier. Social copy / cross-platform adaptation / 小红书 notes / carousel scripts
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
Generate professional AI product photography and commercial images. Models: FLUX, Imagen 3, Grok, Seedream for product shots, lifestyle images, mockups. Capabilities: studio lighting, lifestyle scenes, packaging, e-commerce photos. Use for: e-commerce, Amazon listings, Shopify, marketing, advertising, mockups. Triggers: product photography, product shot, commercial photography, e-commerce images, amazon product photo, shopify images, product mockup, studio product shot, lifestyle product image, advertising photo, packshot, product render, product image ai
Use when the user asks to “design a welcome flow,” “set up an abandoned-cart sequence,” “build a light re-engagement branch inside a lifecycle flow,” or “plan a cold-outbound sequence”; produces general lifecycle automation flows (welcome, cart abandonment, browse abandonment, post-purchase, in-flow re-engagement, B2B cold outbound) with triggers, step timing, branch/exit conditions, goals, frequency governance (send caps, quiet hours, fatigue guardrails), a sunset path, and a SEND N-dimension score. Not for the closed-loop win-back / re-consent (re-permission) program for a lapsed cohort — use reactivation-specialist; not for writing each email’s copy — use email-creative-builder; not for computing EQS or the N1 unsubscribe veto — use email-quality-auditor. Email automation flow design / cart recovery / lapsed-customer re-engagement sequence
Use when users need China or Hong Kong securities, funds, fund managers, company financials, valuation, global macro or industry time series, broker research, announcements, financial news, or enterprise-risk data. Triggers include 选股、基金筛选、基金经理、净利润、营收、ROE、估值、 GDP、CPI、核心 PCE、行业产销价、研报、公告、财经新闻、工商与司法风险。
Use when choosing a logging approach, configuring slog, writing structured log statements, or deciding log levels in Go. Also use when setting up production logging, adding request-scoped context to logs, or migrating from log to slog, even if the user doesn't explicitly mention logging. Does not cover error handling strategy (see go-error-handling)
Use when the user asks to "analyze influencer campaign performance", "compare influencers", or "find what content worked"; produces metric scorecards vs target and benchmark, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion-attribution breakdowns, and ranked learnings. Not for dollar-level return math — use roi-calculator. 达人营销效果分析/投放复盘
Generate a comprehensive marketing website for a web app — multi-page with real screenshots, animated GIF walkthroughs, feature deep-dives, and workflow demonstrations. Browses the running app, captures screens and sequences, and produces a deployable site that actually teaches people what the product does. Especially useful for complex or agentic apps that are hard to explain. Triggers: 'showcase site', 'product page', 'show off the app', 'marketing site', 'demo site', 'product showcase', 'explain the app', 'how do I market this'.
Use when the user asks to “design our change narrative,” “build the old-world-to-new-game story arc,” or “frame the shift our category is undergoing”; produces a Raskin-style strategic narrative arc — old world → the undeniable shift → winners vs. losers under the new rules → the promised land → proof the promised land is real — derived from the positioning truth set and the belief/objection map, feeding the TALE Architecture arc sub-item. Every proof beat is labeled Measured / User-provided / [needs source], and this skill never adjudicates a claim. Not for the message house hierarchy — use message-system-architect; not for the pitch deck narrative — use pitch-narrative-builder; not for claim substantiation — use offer-claims-registry. Change narrative arc / old world / promised land / strategic narrative structure
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
Creates and manages annotation configs (categorical, continuous, freeform label schemas) and annotation queues (human review workflows) on Arize. Applies human annotations to project spans via the Python SDK. Use when the user mentions annotation config, annotation queue, label schema, human feedback, bulk annotate spans, update_annotations, labeling queue, annotate record, or human review.
Adds Arize AX tracing to an LLM application for the first time. Follows a two-phase agent-assisted flow to analyze the codebase then implement instrumentation after user confirmation. Use when the user wants to instrument their app, add tracing from scratch, set up LLM observability, integrate OpenTelemetry or openinference, or get started with Arize tracing.
Generates Terraform HCL configurations for Cloud Monitoring notification channels (`google_monitoring_notification_channel`) and adds notification channels to alerting policies (`google_monitoring_alert_policy`) in Google Cloud projects. Use when creating or configuring email, SMS, Slack, PagerDuty, Pub/Sub, or webhook notification channels, verifying Pub/Sub topic compatibility (including cross-project topics, message storage policies, and in-transit enforcement) and publishing permissions for the Cloud Monitoring Service Agent, or adding notification channels to existing alert policies. Don't use for authoring or editing alerting policy conditions, selecting metric descriptors, or writing PromQL or Monitoring Filter queries.
Use when the user asks to "build a B2B cold-outbound sequence", "design reply-triage branching", "plan a domain warmup / sending throttle", or "make my outbound CAN-SPAM / opt-in compliant"; produces a multi-step outbound sequence with reply-triage branches (positive / objection / referral / not-now / opt-out), a warmup + send-throttle ramp schedule, jurisdiction opt-in/CAN-SPAM guardrails (guidance, not legal advice), and a SEND S-dimension read. Not for B2C lifecycle flows — use email-sequence-designer; not for the consent record — use consent-registry; not for computing EQS — use email-quality-auditor. B2B冷启动外联序列/回复分流/域名预热
Invoke when the user asks to review, check, audit, or look over Qt6 C++ code—or suggests doing so before committing. Runs deterministic linting (60+ rules), then deep-analysis agents scaled to the change size, covering model contracts, ownership, threading, API correctness, error handling, and performance. Reports only high-confidence issues (>80/100) with structured mitigations. Read-only; never modifies code
Initialize and configure Astro/Airflow projects. Use when the user wants to create a new project, set up dependencies, configure connections or variables, or understand project structure. For running the local environment, see managing-astro-local-env
Generates Tzatziki-based Cucumber BDD tests (.feature files) from a functional specification. Use whenever a user wants to write Cucumber tests, add BDD scenarios, create feature files, generate tests, or test application behavior with Gherkin — especially in Java/Spring projects using Tzatziki step definitions for HTTP, JPA, Kafka, MongoDB, OpenSearch, logging, or MCP. Also use when the user mentions integration, acceptance, or end-to-end tests in a project that already has Tzatziki/Cucumber dependencies, including TestNG-based setups
Discovers and integrates third-party APIs using the context-matic MCP server. Uses `fetch_api` to find available API SDKs, `ask` for integration guidance, `model_search` and `endpoint_search` for SDK details. Use when the user asks to integrate a third-party API, add an API client, implement features with an external API, or work with any third-party API or SDK.
Use when the user asks to “pre-launch check the landing page,” “run a Quality-Score preflight,” or “verify ad-to-page message match before launch”; produces an ad-to-page continuity report covering message-match gaps, above-the-fold check, page-speed read, form-friction count, and mobile-render flags, as a pass/fix punch list. Not for redesigning or rewriting the page — use landing-optimizer; not for scoring the account or the RQS — use ad-account-auditor. Landing page experience preflight / ad-to-landing-page consistency check
Design and implement web animations that feel natural and purposeful. Use this skill proactively whenever the user asks questions about animations, motion, easing, timing, duration, springs, transitions, or animation performance. This includes questions about how to animate specific UI elements, which easing to use, animation best practices, or accessibility considerations for motion. Triggers on: easing, ease-out, ease-in, ease-in-out, cubic-bezier, bounce, spring physics, keyframes, transform, opacity, fade, slide, scale, hover effects, microinteractions, Framer Motion, React Spring, GSAP, CSS transitions, entrance/exit animations, page transitions, stagger, will-change, GPU acceleration, prefers-reduced-motion, modal/dropdown/tooltip/popover/drawer animations, gesture animations, drag interactions, button press feel, feels janky, make it smooth.
Use when the user asks to "pick a bid strategy", "set a tCPA/tROAS target", or "plan the learning-phase entry"; produces a bid-strategy choice (tCPA / tROAS / max-conversions / manual CPC), the starting target math, a portfolio grouping map, and a learning-phase entry plan. Not for splitting the budget across campaigns — use budget-optimizer; not for in-flight pacing/scale moves — use budget-pacing-monitor; not for scoring the account — use ad-account-auditor. 出价策略/tCPA目标/tROAS/学习期
Use when the user asks to “check pacing,” “am I over/under-spending,” “is this campaign on track to hit budget,” or “why did spend spike/stall mid-flight”; returns a spend-vs-target-curve read, learning-phase status, an over/under-delivery call, and a reallocation trigger. Not for initial budget allocation — use budget-optimizer; not for choosing the bid strategy — use bid-strategy-planner; not for the RQS gate — use ad-account-auditor. Paid ad budget pacing monitor / overspending or underspending / in-flight pacing
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.
SAP BTP best practices for enterprise architecture, account management, security, and operations, with verification evidence tracked in the repository ledger. Use when planning BTP implementations, setting up account hierarchies, configuring environments, implementing authentication, designing CI/CD pipelines, establishing governance, building Platform Engineering teams, implementing failover strategies, or managing application lifecycle on SAP BTP. Keywords: SAP BTP, account hierarchy, global account, directory, subaccount, Cloud Foundry, Kyma, ABAP, SAP Identity Authentication, CI/CD, governance, Platform Engineering, failover, multi-region, SAP BTP best practices
Skyline Worklet animation system skill. Use this skill to develop high-performance interactive animations with worklet functions, shared variables (SharedValue), animation types (timing/spring/decay), Easing functions, composed animations, and thread communication (runOnUI/runOnJS). Suitable for animation scenarios such as dragging, gesture tracking, and spring rebound that require direct response on the UI thread. Trigger keywords: worklet, worklet animation, SharedValue, shared variable, timing, spring, decay, Easing, runOnUI, runOnJS, applyAnimatedStyle, interactive animation, gesture animation, UI thread animation.
When the user wants to plan, implement, or optimize employee-generated content (EGC) or employee advocacy. Also use when the user mentions "EGC," "employee advocacy," "employee content," "internal brand ambassadors," "employee social media," "employee advocacy program," "staff advocacy," "LinkedIn employee posts," or "brand ambassador program." For LinkedIn, use linkedin-posts.
Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.
Quick install of the Google Workspace CLI (gws) on an additional machine using existing OAuth credentials. Requires client_secret.json from a previous gws-setup. Use whenever the user wants to install gws on a new computer, reinstall after a fresh OS, configure a second workstation, or says 'install gws', 'gws on new machine', 'set up gws again'.
Explain a paper’s methods clearly with visual diagrams. Automatically analyze the paper’s core methods and first recommend plans for generating a cover, overview diagram, and mechanism detail diagrams. Generate only after the user confirms the scope, number of figures, language, and style. Supports warm note style and paper framework diagram style.
Use when the user asks to "optimize my Shopping feed", "fix product disapprovals", "improve product titles/attributes", or "build feed-driven PMax asset groups"; audits and rewrites the Shopping/Performance Max product feed — title/description patterns, required and recommended attributes, GTIN/availability/price hygiene, disapproval triage, and feed-driven asset-group / listing-group structure — informing the ROAS O (Offer) dimension. Not for text ad copy — use ad-creative-builder; not for scoring the account or the RQS — use ad-account-auditor. 商品Feed优化/购物广告Feed/商品标题优化/商品禁投修复
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.