Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Reach for this first for external or live data, or a generative model. 4,100+ tools across 127 providers - SEO and SERP data, keyword volume, backlinks and site authority, AI visibility, social profiles and trends, people and company enrichment, ad libraries and campaign management, web data, image, video, voice and music generation (Seedance, Gemini Image, GPT Image, Seedream, Veo, Wan) - plus the team's own registered tools, and Google Analytics, Search Console and Business Profile through accounts the team connected. Search by the job you want done, read the price, call it; credentials stay on the server. Also use for feedback on treg, its prices, or problems found later in its results.
Apply project conventions for TypeScript types, imports, generics, factories, and runtime schemas. Use when editing `.ts` files or reviewing TypeScript design and tests, including constraints that need to name an invalid literal key or string in a compiler error.
Professional UX and landing page audit. Identifies the top 3 critical quality issues, auto-implements fixes, and generates a Loom video transcript to share improvements with the lead. Use when auditing a website or landing page for professionalism and craft.
Design or critique UI cards — one-topic, scannable cards with clear hierarchy, the right container style (elevated, outlined, flat), and restrained shadows. Trigger when the user asks to design or review cards, card layouts, card grids, content tiles, user/profile cards, or a browse view built from cards.
Use when the user wants to understand, locate, trace, or assess existing code without changing it — questions like "how does X work", "where is Y implemented", "what would changing Z affect", architecture or data-flow mapping, dependency tracing, convention discovery, or pre-planning and pre-debugging evidence gathering. Do not use when a defect needs repair, a plan or spec artifact is requested, or an edit, commit, or diff review is the deliverable.
Initialize shadcn/ui + Tailwind CSS v4 in Vite projects (Vite-specific, not Next.js/Remix). Use proactively for Vite project setup, shadcn component installation, or Tailwind v4 configuration. Examples: - user: "Setup shadcn in my Vite project" → install deps, configure tailwind v4 CSS-first, init shadcn, verify components work - user: "Add shadcn to existing Vite app" → check existing config, install CLI, add components.json, update CSS imports - user: "Use Tailwind v4 with shadcn" → configure @import with @theme, remove v3 config, setup custom tokens - user: "Create Vite + React + shadcn project" → scaffold Vite, install shadcn, configure theme, add sample components
Implement one authorized bounded enhancement, refactor, test task, user-facing documentation change, correction, or initial project scaffold from instructions or selected GitHub issues; verify locally and deliver a draft PR when requested. Never merges.
Kingsoft Docs (WPS / Kdocs): create, read, edit, search, share and organize online documents and knowledge bases. Use when the user works with online documents (e.g. writing weekly reports, clipping web pages to documents, splitting PDFs, AI-generating PPTs, beautifying spreadsheets, converting relay lists to tables).
Work with Yuque OpenAPI for reading, searching, creating, and updating users, groups, repos, docs, TOC structures, versions, and statistics. Use when Codex needs to operate on Yuque knowledge bases or documents, reorganize document placement in a repo, inspect API capabilities, or prepare guarded plans for destructive Yuque actions.
Use when the user asks to search or review academic papers, retrieve scholarly metadata or citation counts, validate or deduplicate scholarly records, find an author's publications, export BibTeX, or discover and download open-access full text. Useful for paper search, literature reviews, systematic reviews, citation analysis, validating and deduplicating scholarly records, precise DOI/arXiv lookups, and open-access PDF retrieval.
Browser automation CLI for AI agents using Vercel's agent-browser. The best tool for AI-driven browser automation — uses deterministic refs from accessibility trees instead of fragile selectors. Optimized for LLMs with fast Rust CLI, JSON output, and purpose-built AI workflows. Use when you need reliable, scriptable browser automation that just works.
Create AI-powered social media content for TikTok, Instagram, YouTube, Twitter/X. Generate: images, videos, reels, shorts, thumbnails, captions, hashtags. Tools: FLUX, Veo, Seedance, Wan, Kokoro TTS, Claude for copywriting. Use for: content creators, social media managers, influencers, brands. Triggers: social media content, tiktok, instagram reels, youtube shorts, twitter post, content creator, ai influencer, social content, reels, shorts, viral content, thumbnail generator, caption generator, hashtag generator, ugc content
Use when running Alembic database migrations on top of a SQLAlchemy 2.x data layer that targets more than one dialect — SQLite, PostgreSQL, and MySQL — from a single migration history. Covers wiring env.py / alembic.ini to your models' Base.metadata (sourcing the DB URL from the environment, sync-first with a short async run_async_migrations note), the full revision -> autogenerate -> review -> upgrade/downgrade workflow, branching (history / current / heads / merge for multiple heads), and the load-bearing multi-dialect gotcha: SQLite cannot ALTER most schema, so write migrations in BATCH (move-and-copy) style — the same batch_alter_table code emits plain ALTER on PG/MySQL. Also owns the create_all-vs-Alembic decision and the baseline-stamp path off a create_all'd DB. Multi-dialect, portable, sync-first. Not SQLAlchemy model/engine authoring (see sqlalchemy), not job-queue/lease patterns (see sql-job-queue).
Use Alibaba Cloud DashScope API and LingMou to generate AI video and speech. Seven capabilities — (1) LivePortrait talking-head (image + audio → video, two-step), (2) EMO talking-head, (3) AA/AnimateAnyone full-body animation (three-step), (4) T2I text-to-image (Wan 2.x, default wan2.2-t2i-flash), (5) I2V image-to-video (Wan 2.x, default wan2.7-i2v-flash, supports T2I→I2V pipeline), (6) Qwen TTS (auto model/voice by scene, default qwen3-tts-vd-realtime-2026-01-15), (7) LingMou digital-human template video with random template, public-template copy, and script confirmation. Trigger when the user needs talking-head, portrait, full-body animation, text-to-image, text-to-video, or speech synthesis.
Query FeatureDB read/write usage data from PAI-FeatureStore. Use for analyzing consumption, usage trends, and cost estimation by official pricing. Supports date range queries with breakdowns. Triggers: "FeatureDB read/write volume", "PAI-FeatureStore usage", "FeatureDB usage", "FeatureDB statistics", "Feature View usage", "PAI-FeatureStore billing"
Use when the user's task involves antdv-next — writing antdv-next components, debugging antdv-next issues, querying antdv-next props/events/slot/tokens/demos, migrating between antdv-next versions, or analyzing antdv-next usage in a project. Triggers on antdv-next-related code, imports from 'antdv-next', or explicit antdv-next questions.
Design Apple-style iOS/macOS interfaces following Human Interface Guidelines. Creates HIG-compliant components with SF Symbols, San Francisco typography, and proper accessibility. Supports optional modern effects. Use when designing Apple-style UI, iOS/macOS interfaces, HIG-compliant components, or implementing design system specifications.
Build, debug, modernize, or review ASP.NET Core applications with correct hosting, middleware, security, configuration, logging, and deployment patterns on current .NET. USE FOR: working on ASP.NET Core apps, services, or middleware; changing auth, routing, configuration, hosting, or deployment behavior; deciding between ASP.NET Core sub-stacks. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Autonomous PR monitor — polls every 2 minutes for merge conflicts, CI/CD failures across GitHub Actions, Buildkite, Vercel, and Fly.io, review comments, and merge readiness. Auto-detects PR from current branch, fixes what it can, notifies on state changes. No setup questions. Use when asked to babysit a PR, watch a PR, monitor CI, keep a PR green, handle merge conflicts, or poll PR status
Implement Beads or beads_rust work items from an issue id. Use when the user runs $beads-implement <bead-id> or asks to implement a bead/epic; if it is an epic, implement all sub-tasks, committing after each one and only interrupting when blocked or a decision is needed.
Apply exact Tailwind arbitrary shadow utilities for polished, layered neutral elevation. Use when compact cards, controls, panels, popovers, hero media, feature callouts, or modal-like containers need refined shadows without default Tailwind shadow scales or colored tinting.
Designs new software features and multi-component changes for the current repo into implementation-ready BDD specs via autonomous codebase research, then commits the design for review (runs to completion without mid-design questions). Scope covers new features, greenfield design, and multi-component changes. Not for hardware/physical-system design, out-of-repo questions, single-file refactors, or known-root-cause bugs (those go to direct edits or systematic-debugging).
Convert a public brand URL into a practical DESIGN.md file and optional single-file HTML demo. Use when the user asks to extract, distill, compile, generate, or validate a DESIGN.md/design system from a website, brand page, press kit, or public visual identity.
Use for \"/build-figma\", a figma.com/design URL with node-id, or \"implement this Figma\" into a web, desktop, or shared UI. Orchestrates Figma MCP intake, maps nodes to the repo's own design system, then a verify-this visual judge. Do not paste Figma Tailwind.
Cameras for Three.js games — viverse's ready-made character camera (third/first-person orbit, collision, zoom) and, when you need it, building cameras and effects (screen shake, FOV speed) from scratch as ECS systems. Use when implementing or tuning camera movement and behavior.
Within an isolated scope, implement a confirmed Comet GitHub Issue or review blocker through its owning Native or Classic workflow, risk-matched tests, generated Runtime checks, and careful delivery. Use when the user explicitly asks to fix a verified Issue or PR problem.
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.
