Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Symfony UX Icons for rendering SVG icons in Twig templates. Supports 200,000+ Iconify icons (Lucide, Heroicons, Tabler, Material Design, etc.), local SVG files, and custom icon sets with aliases. Use when displaying icons, configuring icon defaults, importing or locking on-demand icons, creating icon aliases, or styling SVG icons with CSS. Code triggers: <twig:ux:icon />, ux_icon(), UX_ICONS_DEFAULT_ICON_ATTRIBUTES, icon.yaml, icons/, iconify:, lucide:, heroicons:, tabler:, mdi:, bin/console ux:icons:lock, bin/console ux:icons:import. Also trigger when the user asks "how to add an icon", "how to use Lucide/Heroicons/Tabler icons", "how to render an SVG icon in Twig", "how to lock icons for production", "how to create icon aliases", "how to style an icon", "icon not found", "icon not rendering". Do NOT trigger for interactive maps (use ux-map) or general Twig components (use twig-component).
Route viral topic discovery across platform-specific account-growth skills. Use when the user asks for 起号选题, low-follower viral references, recent viral content, cross-platform topic mining, or does not specify whether to search WeChat, X, Bilibili, or YouTube.
Single UI audit door: runs detectors as a hard gate, applies frontend/motion/refine judgment, ends with an adversarial interrogation and a score. Use on "looks AI-made", "this is slop", "too cluttered", "tá com cara de IA", "tá slop", "tá poluído", "audita essa tela", "mata essa tela", "nível vale do silício", auditing UI before a PR.
vLLM Ascend plugin for LLM inference serving on Huawei Ascend NPU. Use for offline batch inference, API server deployment, quantization inference (with msmodelslim quantized models), tensor/pipeline parallelism for distributed serving, and OpenAI-compatible API endpoints. Supports Qwen, DeepSeek, GLM, LLaMA models with Ascend-optimized kernels.
Set up debugging for vvvv gamma C# node projects -- generate VS Code launch.json and tasks.json configurations, attach debugger to running vvvv, configure Visual Studio debug profiles, and use debugging best practices. Use when setting up a debugger for vvvv, creating launch configurations, attaching to vvvv process, or troubleshooting breakpoints in C# nodes. Supports multiple launch configs for different test scenarios/patches.
Covers launching vvvv gamma from the command line or programmatically -- normal startup, opening specific .vl patches, command-line arguments, package repositories, and key filesystem paths (install directory, user data, sketches, exports, packages). Use when starting vvvv, configuring launch arguments, setting up package repositories, or finding vvvv's data directories.
Search the web from the command line using duckduckgo-cli. Use this skill whenever you need current information, latest news, recent events, fact-checking, research, documentation lookups, or any answer that may have changed since training. Trigger this even when the user doesn't say "search" — phrases like "what's the latest...", "find out...", "look up...", "is X still true?", "who is the current...", "compare prices/options", or any question about recent things should activate it.
A skill for searching WeChat Official Account articles. Uses WeChat search to retrieve article lists covering Chinese-language topics such as technology/AI, social affairs, finance, education, and careers. Search by keyword and return titles, summaries, publication times, source accounts, and links. Use when users need to find WeChat Official Account articles, compile references, or quickly get article information
Expert guidance on contributing to WendyOS: Yocto builds, agent internals, E2E testing, and system architecture. Use when developers mention: (1) building WendyOS images, (2) meta-wendyos layers or bitbake, (3) wendy-agent development or internals, (4) containerd or nerdctl on WendyOS, (5) E2E tests for wendy-agent, (6) Yocto recipes or bbappend files, (7) mDNS/Avahi service configuration, (8) device identity or UUID generation.
Safe Windows C: drive space analysis and cleanup workflow. Use when a user asks Codex to scan, diagnose, clean, free space, remove large files, identify uninstall candidates, or troubleshoot low disk space on a Windows system drive, especially C:\. Emphasizes read-only analysis first, risk classification, explicit user approval before deletion or uninstalling, privacy-preserving local-only scans, and safe handling of Windows Installer, WinSxS, AppData, ProgramData, caches, personal files, and large application data.
Run the Bitwarden workflow linter (bwwl) against one or more repos and report findings. Strictly read-only — does not modify any files. Categorizes findings as mechanical or judgment using the bitwarden-workflow-linter-rules skill. Supports single repo, multiple repos, or single file/directory scope. <example> User: Run the workflow linter on the server repo Action: Trigger workflow-audit for that repo </example> <example> User: Lint the workflows across server, clients, and android Action: Trigger workflow-audit in multi-repo mode </example>
Work with PostHog Signals scouts: scheduled agents that monitor a project and write reports into the Signals inbox. Use to assign monitoring work, schedule quality scoring, find which scout covers a surface, act on reports, reduce noise, investigate missing findings, or improve the fleet through feedback and calibration. Also covers follow-up checks that verify whether a reported problem stays fixed. Use `authoring-scouts` for edits, `exploring-scouts` for run observability, and `inbox-exploration` for report triage. Trigger on "work with my scouts", "get more out of scouts", "have a scout watch X", "tell me if Y spikes", "score X on a schedule", "measure quality of Y", "what do I do with this scout report", "calibrate/review my scout fleet".
Connect a user's own X (Twitter) dev app (BYOK) for the official X API MCP (reads) plus X v2 REST writes — post, reply, like, retweet, DM. Use when the user wants to act on X with their OWN X account or app — search, read timeline/users/news/trends/bookmarks via MCP, and post/reply/like/retweet/DM via REST. Walks through OAuth 2.0 setup in the X portal, xurl CLI registration, headless OAuth (user pastes the redirect URL back), the client-not-enrolled / Pay-per-use trap, the token-expiry auto-refresh mechanism, agent.yaml MCP wiring, and FAQ. For read-only scraping WITHOUT the user's own app, use the twitter skill.
Create a structured Obsidian vault note from a YouTube video transcript — fetches captions with timestamps, cleans the text, divides into sections, adds a TOC and per-section video links, takes the thumbnail URL directly, and commits. Use when the user shares a YouTube URL and wants a full transcript note in the vault.
Query the ZINC22 virtual compound library (CartBlanche API, billions of make-on-demand + purchasable molecules). Look up substances by ZINC ID, resolve a SMILES to its ZINC ID (exact match), inspect purchasability/catalogs, and assemble compound sets for docking. Property (MW/logP) filtering is done locally with RDKit. For bioactivity use chembl-database-bioactivity; for approved drugs use drugbank-database-access.
Zod schema validation best practices for type safety, parsing, and error handling. This skill should be used when defining z.object schemas, using z.string validations, safeParse, or z.infer. This skill does NOT cover React Hook Form integration patterns (use react-hook-form skill) or OpenAPI client generation (use orval skill).
Track SERP rankings, monitor position changes, analyze SERP features, and identify ranking opportunities using DataForSEO. Alternative to Google Search Console for ranking data. Use when user says "rankings", "SERP tracking", "position monitoring", "rank tracking", "keyword positions", or "SERP analysis".
ABP Framework domain layer patterns including entities, aggregates, repositories, domain services, and data seeding. Use when: (1) creating entities with proper base classes, (2) implementing custom repositories, (3) writing domain services, (4) seeding data.
Adapt designs for narrow, medium, wide, embedded, or print web contexts without losing usability, hierarchy, or target sizing. Use when the user mentions responsive design, breakpoints, narrow layouts, viewport changes, coarse-pointer browsers, or cross-context adaptation.
Deploy tRPC on WinterCG-compliant edge runtimes with fetchRequestHandler() from @trpc/server/adapters/fetch. Supports Cloudflare Workers, Deno Deploy, Vercel Edge Runtime, Astro, Remix, SolidStart. FetchCreateContextFnOptions provides req (Request) and resHeaders (Headers) for context creation. The endpoint option must match the URL path prefix where the handler is mounted.
Execute AdCP Media Buy Protocol operations with sales agents - discover advertising products, create and manage campaigns, sync creatives, and track delivery. Use when users want to buy advertising, create media buys, interact with ad sales agents, or test advertising APIs.
Sync columns from a synced data warehouse table onto PostHog person or group properties, so warehouse data becomes usable anywhere person and group properties already work: feature flag targeting, cohorts, insight filters and breakdowns, surveys, session replay filters, workflows, and the person profile. Use when the user wants to "add a person property from my warehouse", "enrich people with Stripe/Postgres/Salesforce data", "put ARR or plan tier on my persons", "target a feature flag by a warehouse column", "sync warehouse columns onto groups or organizations", or wants to inspect, backfill, disable, or debug an existing warehouse-backed person or group property.
Expose an AG2 `Agent` over the AG-UI protocol so a frontend (CopilotKit, custom React/Next.js, or any AG-UI client) can stream responses (text and reasoning), render tool calls, sync shared state, and track sub-task steps. Wraps the agent with `AGUIStream(agent)` and mounts it in FastAPI via `stream.dispatch(...)` or `stream.build_asgi()`. Use when the user wants a web frontend in front of an AG2 agent rather than a CLI / script.
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.