Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when a Jackrabbit Oak/AEM JCR query is slow, logs a traversal warning, or you're adding/changing a query and need to check or update its property/Lucene index definition so the query is answered by the index instead of in-memory filtering or sorting.
Provides comprehensive uni-app-x component and API integration guidance. Use when the user needs official uni-app-x components or APIs, wants per-component or per-API examples, or needs cross-platform compatibility details for uni-app-x.
Design or critique UI menus — pick the right menu type (dropdown, cascading, contextual, single/multi-select, search, inline) for the action set, and apply item ordering, grouping, labeling, and state best practices. Trigger when the user asks to design or review a menu, dropdown, context/right-click menu, overflow (⋮) menu, or asks how to organize actions into a menu.
Design or critique selection controls — pick the right control (checkbox, radio button, toggle switch, dropdown, slider, picker) for the choice being made, and apply labeling, alignment, and state best practices. Trigger when the user asks to design or review checkboxes, radio buttons, toggles/switches, dropdowns, sliders, range filters, or any "which control should I use" question.
Validates a compiled Robomotion flow against pspec schemas via `robomotion validate <flow-dir>`. Exits 0 on clean, 1 on error with node-by-node report on stderr; no stdout output (composes in shell pipelines). Use when the user says "validate this flow", "check the flow", "is this correct", or before running. Does NOT run the flow — for behavioral tests use testing-flow.
Manages Fabric Variable Library items, including definitions, libraryVariables and valueSets overrides. Covers which consumers can reference a variable and with what syntax -- pipelines, notebooks via notebookutils variableLibrary, Dataflow Gen2, Copy Jobs, shortcuts, UDFs and Plan items -- the active value set per workspace or deployment stage, and Git serialization for CI/CD.
Provider-independent governance workflow for verifying and correcting human- or model-generated video descriptions. Use for pre-caption critique and post-caption revision, aspect-by-aspect factual review, critique precision/recall/constructiveness, second-stage peer review, calibration, appeals, versioned triplets, provenance, and acceptance reporting; not for pixel/audio QA, accessibility captioning, model training, or creative shot direction.
MUST be used for Vue.js tasks. Strongly recommends Composition API with `<script setup>` and TypeScript as the standard approach. Covers Vue 3, SSR, Volar, vue-tsc. Load for any Vue, .vue files, Vue Router, Pinia, or Vite with Vue work. ALWAYS use Composition API unless the project explicitly requires Options API.
Basic Yakit usage guide. Use when users need to know what Yakit is, how to install it, what each area of the interface is for, the relationship between the engine and the frontend, or how to get started with Yakit from scratch. Covers the architecture overview (engine + Electron frontend + gRPC channel), the three interface modes (classic / security expert / scan), a routing table of core features (MITM / Web Fuzzer / Codec / port scan / plugins / database, etc.), engine connection and project switching, and entry points for the most common beginner questions. Enter when the user asks "how do I use Yakit / where is a certain feature / the engine won't connect".
You are "Zhongjie Ge," a professional and trustworthy home-buying advisor whom clients may call Zhongjie Ge. You excel at participating in the entire home-buying decision process from the client's perspective. Your core ability is helping clients sort out and uncover their real home-buying needs, carefully recording profiles, preferences, and constraints, and spotting important factors they have not realized through professional questioning while proactively offering neutral advice. You can search property information across multiple channels, compare the pros and cons of different listings side by side, and recommend the most suitable developments or communities based on budget, school district, commute, future family plans, and other dimensions. When clients raise property-related topics such as buying a home, viewing homes, finding homes, policy inquiries, purchase procedures, and market trends, you step in proactively, drawing on rich hands-on experience to offer systematic, practical, and sincere advice, avoiding rigid templates and mere lists of information, focusing on educating clients about the logic behind property choices, and helping them make rational home-buying decisions.
A/B and multivariate testing methodology. Design experiments, calculate sample sizes, determine statistical significance, avoid common pitfalls, and interpret results. Platform-agnostic framework applicable to landing pages, emails, ads, pricing, and product features. Use when the user asks about A/B testing, split testing, experiment design, statistical significance, or conversion experiments.
Map player input (keyboard, mouse, touch, gamepad) to game logic with the @pmndrs/viverse action/binding system. Use when building movement controls, input handling, or custom state/event actions for a Three.js game, or when controls must change across game modes (menu, play, pause, cutscene) — e.g. pointer-lock controls wrongly stay live during a menu and a button click locks the pointer.
Helps develop ad concepts from hooks or ideas for paid social campaigns. Use when the user has a hook or idea and wants to build it into a full ad concept. Triggers: "ad concept", "creative concept", "campaign idea", "ad direction", "concept brief", "creative brief", "develop this hook", "build out this idea", "paid social concept"
Auto-transcribes an existing video's spoken audio into a word-level transcript with real timing, then builds styled, on-brand, animated captions as timed text elements synced to that timing: brand fonts and colors, entry and exit animation, per-word impact styling. This is the deep brand-styled captioning skill; for plain burned-in subtitles with default styling, see add-animated-captions. Use when the user says "add captions to this video and make them match our brand", "fancy animated captions", "burn in on-brand subtitles", "caption this with per-word emphasis", or "put styled subtitles on this in our brand style".
Burn captions into an existing video so it works with the sound off - accurate, well-timed subtitles baked into the exported file. Use when the user says "add captions", "burn in subtitles", "make it watchable on mute", "add subtitles to my video", "captions for social", or "hardcode the captions".
Visual design intelligence and UI aesthetics. Integrates: chrome-devtools, ai-multimodal, media-processing. Capabilities: design analysis, visual hierarchy, color theory, typography, micro-interactions, animation, design systems, accessibility. Actions: analyze, design, create, capture, evaluate, implement UI aesthetics. Keywords: Dribbble, Behance, Mobbin, design inspiration, visual hierarchy, color palette, typography, spacing, animation, micro-interaction, design system, style guide, accessibility, WCAG, contrast ratio, golden ratio, whitespace, visual rhythm. Use when: building beautiful UIs, analyzing design inspiration, implementing visual hierarchy, adding animations/micro-interactions, creating design systems, evaluating aesthetic quality, capturing design screenshots.
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines
Explicitly enable AGI mode; use when unsure how to move a problem forward or when self-evolution is needed. Consultations and queries are read-only. A general-purpose problem-solving assistant that resolves issues through evidence loops and continuously improves its methods and capabilities through retrospectives, evaluations and iterations
Create AI-powered podcasts with text-to-speech, music, and audio editing. Tools: Kokoro TTS, DIA TTS, Chatterbox, AI music generation, media merger. Capabilities: multi-voice conversations, background music, intro/outro, full episodes. Use for: podcast production, audiobooks, voice content, audio newsletters. Triggers: podcast, ai podcast, text to speech podcast, audio content, voice over, ai audiobook, multi voice, conversation ai, notebooklm alternative, audio generation, podcast automation, ai narrator, voice content, audio newsletter, podcast maker
When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for Perplexity,' 'AI citations,' 'AI visibility,' 'zero-click search,' 'how do I show up in AI answers,' 'LLM mentions,' or 'optimize for Claude/Gemini.' Use this whenever someone wants their content to be cited or surfaced by AI assistants and AI search engines. For traditional technical and on-page SEO audits, see seo-audit. For structured data implementation, see schema.
Open and manage brokerage accounts via the Alpaca Broker API — account creation, KYC/CIP, identity & disclosures, agreements, document upload (incl. W-8BEN), account status lifecycle, and account updates/closure. Use when a developer is building onboarding, KYC, or account-management flows on Alpaca in any language.
Move cash (JNLC) and securities (JNLS) BETWEEN accounts inside your own Alpaca omnibus via the Broker API — single, batch, and reverse-batch journals, the Idempotency-Key header, journal status lifecycle including corrections, and the firm/sweep-account pattern that powers instant funding and share rewards. Use for internal account-to-account movement in any language. For deposits/withdrawals to EXTERNAL banks, use funding-transfers instead.
Preview, submit, inspect, and manage Alpaca paper-trading orders using the Alpaca CLI. Supports US equities, options, and crypto. Use this skill when you want your AI agent to take a strategy signal and execute it as a paper trade through the Alpaca command-line interface.
Research and validate an Amazon product opportunity end to end, and evaluate whether the niche around it is winnable. Assesses demand, competition, profit potential, entry barriers, review wall, differentiation room, and seasonality, and returns a go/no-go with the reasoning. Use when a user asks to research a product, find a product to sell, validate a product idea, assess an opportunity, evaluate a niche, find a profitable niche, judge whether a category is worth entering, or compare niches. Trigger phrases: "product research", "find a product to sell", "validate this product", "is this a good product", "product opportunity", "should I sell this", "niche finder", "evaluate this niche", "is this niche worth it", "good niche", "low competition niche", "should I enter". Works with zero tools. the user describes the product and what they can observe.
Build investment systems in the style of AQR Capital Management, the quantitative investment firm pioneering factor investing. Emphasizes academic rigor, transparent methodology, and systematic factor exposure. Use when building factor models, conducting asset pricing research, or designing systematic portfolios.
Use when calling the Atlassian Cloud REST API directly — Confluence Cloud v2 (pages, spaces, search) or Jira Cloud v3 (issues, JQL search, comments) — to perform operations programmatically, including writes such as creating a Confluence page. Calls REST with curl (no SDK, no pip), authenticating with a Cloud email + API token. Constructs any of the 800+ endpoints from a bundled OpenAPI spec via an endpoint index + a $ref-resolver, with per-API patterns (base URL, pagination, errors, rate limits) and the ADF / storage rich-text formats handled explicitly. Consumes caller-injected credentials (base_url, email, and a token resolved by variable name) — it does not provision or resolve them; the token value is read only by curl, never printed.
Read-only audit of one persisted skore report: `audit/NN_<stem>.py` (jupytext percent), 1:1 with `experiments/` and `journal/`. Do not execute it. Run `materialize.py` once. Never call `skore.evaluate` or `project.put`. TRIGGER when a completed run needs an audit, the user asks to audit, show, or re-audit an experiment, a re-run overwrote the same `put()` key, or they want a narrative of a past experiment without `journal/ideas/` files. STOP when `status.setup.pending` is non-empty (load `setup-ml-project`), or when there is no approved design, no report, or no agent feature: explain and send the user to setup, `evaluate-ml-pipeline`, or `model-ml-pipeline`. Also stop for raw-data exploration or sourcing a future experiment. HOW TO USE: confirm journal, experiment, smoke, and report; place the file from `templates/audit.py`; copy `templates/materialize.py` to scratch; execute once; derive G-AUDIT-FINDING; then the continue-or-close gate. Resolve skore symbols with `api get`.
Run fast, progressive experiments to map tunable parameters and their effects. Use when optimizing code, prompts, configurations, or other artifacts against a goal or benchmark, or when a long research run needs a planned hypothesis queue, focused trials, and durable findings.
Use this skill when the user asks to “pentest AWS,” “test AWS security,” “enumerate IAM,” “exploit cloud infrastructure,” “AWS privilege escalation,” “S3 bucket testing,” “metadata SSRF,” or “Lambda exploitation,” or needs guidance on Amazon Web Services security assessment.
Writes, fixes and reviews Azure DevOps wiki Markdown: Mermaid, [[_TOC_]], [[_TOSP_]], details blocks, query tables, mentions, work-item links, KaTeX, videos, code fences, and what renders in wiki vs PR vs README. Not for GitHub-only docs or work item packets.
List, upload, download, and manage files on B2C Commerce instances via WebDAV. Use this skill whenever the user needs to upload files to IMPEX directories, download exports from an instance, list remote files, create or delete directories, zip or unzip files on the server, manage file transfers to sandboxes, or browse instance file systems — even if they just say "upload a file to the instance" or "check what's in the IMPEX folder".
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.
