Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Explains Streamlit's internal architecture including backend runtime, frontend rendering, and WebSocket communication. Use when debugging cross-layer issues, understanding how features work end-to-end, planning architectural changes, or onboarding to the codebase. Covers ForwardMsg/BackMsg protocol, script rerun model, element tree, widget state management, and the delta-path rules shared by the frontend and the agent snapshot.
Design or critique UI buttons — pick the right button type for the action's importance, apply sizing/label/state best practices, and gate stylistic levers like shape, shadows, FABs, and icon-only buttons. Trigger when the user asks to design, choose, style, or review buttons, CTAs, button labels, button hierarchy, or button states.
Design or critique loading states and progress indicators — match the feedback type (spinner, text, determinate bar, skeleton, progress tracker) to the wait duration and task structure, and manage perceived performance. Trigger when the user asks to design or review loaders, spinners, loading states, skeleton screens, progress bars, progress trackers, steppers, or multi-step flow progress.
Design or critique a login / sign-up screen. Applies the always-true core (separate pages, minimal fields, inline validation, full password-reset flow) and gates context-dependent choices (social login, 2FA, "stay logged in", username vs. email) with trade-offs. Trigger when designing auth screens, sign-up forms, registration flows, or password recovery.
Design or critique a settings / preferences page — organizing many options without overwhelm, plus the save model (autosave vs. explicit Save, confirmation, revert). Applies the always-true core (only relevant settings, frequency-ordered groups, plain labels, visible current status, destructive actions last, clear save feedback) and gates context-dependent levers (autosave vs. Save button, search, advanced-settings split, sensitive-change confirmation) with trade-offs. Trigger when the user asks to design or review a settings page, preferences screen, account settings, app configuration, or a save/confirmation pattern.
Vercel KV (Redis-compatible key-value storage via Upstash). Use for Next.js caching, sessions, rate limiting, TTL data storage, or encountering KV_REST_API_URL errors, rate limit issues, JSON serialization errors. Provides strong consistency vs eventual consistency.
Use when debugging or repairing existing features from rough agent-assisted coding reports, regressions, failed prior fixes, repeated "still broken" feedback, source-only debugging stalls, unobserved runtime state, tool or automation failures, environment-specific failures, runtime artifact mismatches, security boundary surprises, or fixes that feel wrong.
Generate a model-graph.png visualization of Cube.dev semantic models — render the cube graph, show relationships between cubes, draw the fact spine, or diagram the semantic layer. Use whenever the user mentions visualizing, drawing, diagramming, or graphing the semantic model / cube model / cube relationships, even if they don't explicitly ask for a PNG. Triggers: "visualize the semantic model", "draw the cube graph", "show relationships between cubes", "generate model-graph.png", "diagram the semantic layer", "render the cube model". Accepts an optional folder argument (defaults to `cubes/`).
Vitest testing framework patterns for test setup, async testing, mocking with vi.*, snapshots, and test performance (formerly test-vitest). This skill should be used when writing or debugging Vitest tests. This skill does NOT cover TDD methodology (use test-tdd skill), API mocking with MSW (use test-msw skill), or Jest-specific APIs.
Fetches current weather conditions and forecasts for any location worldwide. Use this skill whenever the user asks about weather, temperature, rain, wind, forecast, climate conditions, or what to wear/pack for a trip. Triggers on queries like "what's the weather in X", "forecast for Y", "will it rain", "what should I pack for Z", "how hot/cold is it", "is it windy in X", or any travel-planning question where weather matters.
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
Apply XP practices including pair programming, ensemble programming, continuous integration, and sustainable pace. Use when implementing agile development practices, improving team collaboration, or adopting technical excellence practices.
Load when: the user needs any of the following — - Analyze the technicals/entry-exit points/risks of an A-share stock, or ask whether a stock can be bought/sold - Interpret Z 哥 trading systems such as 「少妇战法」「B1/B2/B3」「四块砖」「双线趋势」「麒麟会」「三波理论」 - Evaluate an investment portfolio, diagnose holdings, review trades, comment on trade statements - Answer career/life/business decision questions (requires Z 哥's 「四圈框架」「四层模型」「时代主线」 perspective) - The user explicitly says 「切换到 Z 哥」「用万千视角」「zettaranc perspective」 or a similar role-switch instruction Do NOT load when: US/HK stocks, futures, or cryptocurrency analysis; pure coding questions; chit-chat unrelated to investing, career, or life Risk level: medium-high (a disclaimer must be attached when specific investment advice is involved) Data dependency: optional. JNB mode requires a Tushare Token; websearch mode has no external dependencies. Output format: Chinese, Z 哥's tone (long setup + short conclusion, rhetorical questions answered by himself, rigid-rules style, number-crunching lines) Version: 4.1.0 | 2026-07-23 Corpus basis: 467 compiled livestreams/paid courses (~2 million characters), 13 ztalk transcripts (127k characters), 9 trading-psychology pieces (33k characters), Xueqiu columns, and online preliminary research. Data sources: fan compilations such as 知行课代表, 知行小菜鸟, 复盘专用 z, 大富翁小菜鸟, TANGOO 公众号.
Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) specialist. Optimize content and websites to appear in AI-generated answers from ChatGPT, Perplexity, Claude, Google AI Overviews, and other LLM-powered search experiences. Use when the user asks about AI search optimization, AEO, GEO, AI Overviews, appearing in AI answers, LLM citations, or optimizing for generative search.
Scaffold and operate an opt-in `Agent activity log` table that records what the agent did, decided, and got blocked on across a long-running or multi-session Airtable workflow. Use whenever a workflow skill (product-ops, sales-ops, marketing-ops, etc.) is being set up for an agent-driven motion (recurring triage, multi-step plan, automated monitoring, agentic workflow), or when the user explicitly asks for "agent activity tracking," "audit log of agent decisions," "agent memory," "track what the agent did," or similar. The pattern is opt-in (front-load the offer, frame as auditability for the user's benefit, not surveillance). Composes into workflow skills the same way `show-airtable-link` does — workflow skills point at this skill rather than re-implementing the schema inline.
Playbook for Agent-Media UGC Video — the one tool for UGC video on agent-media. Always call the single make_ugc skill: give it a `script` (any length) and optionally a person/image/character; it returns the finished captioned vertical video. Short script → one clip, long monologue → full multi-take (never trimmed), `broll_url` → narrated overlay. You never pick a sub-skill.
Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and recoverable pipeline design
Prepares sprint review and demo of deliveries for stakeholders, including the sprint's quantitative metrics. Use when the sprint has ended and it is necessary to present what was delivered, the numbers, what changed in scope, what is pending, and what decisions are needed.
A Metabase AI-governance coach, covering the *controls and rollout* side of AI: who may use Metabot, what it can see, what it costs, where the model runs, and the audit trail. Use this skill whenever the user wants to roll out AI analytics safely, control who can use Metabot or what it can see, set spend or token limits on AI, restrict Metabot's system prompt, audit AI usage, evaluate bring-your-own model or self-hosting options for AI, or prep for a security review of AI features. Trigger it even if the user just says "how do we control AI access", "can we limit what Metabot sees", "we need an AI security review", or "run the AI governance checklist" in a Metabase context. **Not this skill** if the question is about whether the underlying data is modeled, documented, and trustworthy enough for AI — Transforms, metadata, the Glossary, Metrics, the Library — that's `ai-readiness-checklist`. Rough test: this skill is about who gets to point AI at the data; that one is about whether the data is good enough.
Generate AI music and songs with ElevenLabs, Diffrythm, Tencent Song Generation via inference.sh CLI. Models: ElevenLabs Music (up to 10 min, commercial license), Diffrythm (fast song generation), Tencent Song Generation (full songs with vocals). Capabilities: text-to-music, song generation, instrumental, lyrics to song, soundtrack creation. Use for: background music, social media content, game soundtracks, podcasts, royalty-free music. Triggers: music generation, ai music, generate song, ai composer, text to music, song generator, create music with ai, suno alternative, udio alternative, ai song, ai soundtrack, generate soundtrack, ai jingle, music ai, beat generator, elevenlabs music, eleven labs music
Build RAG (Retrieval Augmented Generation) pipelines with web search and LLMs. Tools: Tavily Search, Exa Search, Exa Answer, Claude, GPT-4, Gemini via OpenRouter. Capabilities: research, fact-checking, grounded responses, knowledge retrieval. Use for: AI agents, research assistants, fact-checkers, knowledge bases. Triggers: rag, retrieval augmented generation, grounded ai, search and answer, research agent, fact checking, knowledge retrieval, ai research, search + llm, web grounded, perplexity alternative, ai with sources, citation, research pipeline
Audits AI-generated or AI-enhanced listing images against the 2026 Amazon disclosure and representation policy before submission. A 5-gate flow catches the issues that trigger suppression or a misrepresentation flag. Use when a user asks about AI image policy, AI photo rules, image suppression, or 2026 image compliance. Trigger phrases: "AI image Amazon policy", "AI generated photos listing", "image suppression AI", "Amazon AI image rules 2026". Works with zero tools.
Generate a structured negotiation script for Alibaba, Canton, or domestic suppliers. Covers 7 levers (unit price, MOQ, payment terms, lead time, packaging, QC, tariff sharing) and produces email templates per negotiation round. Use when a user asks how to negotiate with a supplier, Alibaba negotiation, MOQ negotiation, supplier email scripts, or getting better terms. Trigger phrases: "negotiate supplier", "Alibaba", "MOQ", "payment terms", "supplier script", "supplier email". Works with zero tools.
Build any physical object (a product, a tool, furniture, an instrument, a shoe, a vehicle, a piece of jewellery, kitchenware, a toy, even a fruit or a flower) as a crafted isometric "anatomy" figure made of many small convex parts, then turn it into (1) an interactive dissection page you can drag, turn and take apart, and (2) a product-reveal film (MP4, 9:16, 4:5, 1:1 or 16:9, 30 fps, motion blur, white paper look, 10 s by default, any length from 3 to 60 s). The film tumbles in, whips to macro shots of the object's details, shows one feature working, explodes into its parts and snaps back together for a hero shot. Works from a photo of the object or from just its name. Use it when someone asks for an exploded view, a teardown or dissection drawing, an anatomy figure, or a product reveal or product motion video of an object.
Build a voting/poll dApp on Midnight Network using the Kuira Android SDK — Compact smart contract with create/cast/close circuits, passkey-derived identity, embedded wallet, Compose UI, reactive ledger reads via observeLedger(), and on-device ZK proving. Use when building a poll or voting dApp targeting Android.
Best practices for Flutter animations using the built-in animation framework, covering implicit animations, explicit `AnimationController` animations, page transitions, and Material 3 motion tokens. Use when creating, modifying, or reviewing animations, transitions, motion, or animated widgets, and also for custom route transitions built with `CustomTransitionPage`, a `buildPage` override on a `GoRouteData` subclass, or a `Hero` transition, since motion between routes is animation work even when the surrounding code is `go_router`.
Framework-neutral architecture and design standards for frontend engineering in TypeScript (React, Angular, Vue, or any component framework): SOLID and clean code, clean architecture and layer boundaries, feature-first structure, the adapter/repository pattern, state tiers and data fetching, security, testing strategy, DDD tactical patterns, micro-frontends, forms. Use it when generating a component or module, refactoring frontend code, reviewing a pull request, or making an architecture decision, or when the user says "code review", "clean architecture", "SOLID", "design pattern", "DDD", "bounded context", "micro-frontend", "data fetching", "form validation", or "how should I structure this".
Acquire an authenticated session THROUGH MFA/OTP on an in-scope target and emit a reusable session artifact (Playwright storageState + Bearer) so executors can test the post-auth attack surface. Use when the highest-value authenticated classes (BOLA/IDOR/mass-assignment/injection on the real data APIs) are blocked because login is gated by SMS-OTP or TOTP MFA. Distinct from the authentication skill (which ATTACKS auth); this one legitimately authenticates and hands the session to the rest of the engagement.
Generate professional infographics with 21 layout types and 22 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", "可视化", or "高密度信息大图".
Use when spawning `Camera3d` or `Camera2d`, choosing a `Projection`, rendering to an image with the `RenderTarget` component, adding `Hdr` / `Tonemapping::Linear` / `ScreenSpaceTransmission` to a camera, wiring `FreeCamera`, `PanCamera` or the new `PanOrbitCamera` from `bevy::camera_controller`, ordering views with `Camera::order`, or setting a per-camera `AmbientLight` in Bevy 0.20.
Production-grade Bootstrap 5.3 patterns for building modern, responsive web UIs in HTML and ASP.NET Core Razor Pages/Views. Use when creating or styling web pages, layouts, navigation, forms, cards, modals, tables, or any UI component with Bootstrap 5. Covers the grid system, responsive breakpoints, utility classes, color modes (dark/light), accessibility, and integration with ASP.NET Core tag helpers and Razor syntax. Trigger on any task involving Bootstrap CSS classes, responsive HTML layouts, Razor Page UI design, or front-end styling for .NET web applications.
Use when choosing brand typefaces, pairing fonts, building a type hierarchy or modular scale, or writing typography guidelines and design tokens. Keywords - brand typography, font selection, font pairing, serif vs sans-serif, type scale, typeface licensing, web font performance, WCAG typography and readability.
Comprehensive SAP BTP command line interface (btp CLI) assistant for generating commands, automating multi-step workflows, and troubleshooting errors. Use this skill whenever the user mentions "btp", "BTP CLI", "SAP BTP command line", subaccount management via CLI, entitlement assignment via terminal, service instance creation with btp, role collection assignment from the command line, or any task involving the SAP Business Technology Platform CLI — even if they just say something like "set up my BTP subaccount" or "how do I log in to my global account from the terminal". Also trigger when the user asks about scripting or automating SAP BTP operations, parsing btp output with jq, or managing Cloud Foundry / Kyma environments through the btp CLI.
Production guidance for international BytePlus Seed Speech text-to-speech. Use for selecting TTS 1.0 versus 2.0, bidirectional or unidirectional streaming, current voices and languages, prompt/prosody controls, subtitle timing validation, billing and concurrency, authorized replicated voices, privacy, error handling, and output QA. Do not use for mainland-China Volcengine Doubao Speech endpoints.
Use this skill when no pre-built connector fits and processes need a reusable integration — a proprietary or internal API, custom auth, a shared retry policy, or an inbound webhook, subscription, or poller that starts processes. Builds custom Camunda 8 connectors as a JSON template on a protocol connector or in Java with the Connectors SDK.
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.
