Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Framework for long-running AI agents across multiple context windows. USE WHEN user types /agent-harness or mentions sprint planning, feature breakdown, multi-session projects. Subcommands: init, sprint, code, 996, status, archive, force-archive.
Web search for current or external info. Trigger: search verbs ("search", "查", "搜", "google"), freshness ("latest", "最新", "news", "更新", "进展"), comparison ("调研", "对比", "vs"), proper nouns. Skip: local ops, explicit other search tool, general knowledge.
Use when the user needs Agently TaskDAG / Dynamic Task, model-generated or app-submitted DAG planning, TaskDAG validation, TaskDAGResolver handlers, TaskDAGExecutor execution, or the Agently.create_dynamic_task compatibility facade. TaskDAG is the DAG foundation capability; Dynamic Task is the convenience facade over it and uses TriggerFlow as the execution substrate.
Design and integration guidance for adding a reusable AI Agent chat interface to an existing web application. Use when adding an embedded AI assistant, chat view, multimodal input, speech-to-text, session history, long-task execution UI, Agent activity states, provider/model settings, or Tool / Function Calling support. The Agent is a supporting interface for the existing application rather than the application's primary UI.
Switch AI providers or models without breaking things. Use when you want to switch from OpenAI to Anthropic, try a cheaper model, stop depending on one vendor, compare models side-by-side, a model update broke your outputs, you need vendor diversification, or you want to migrate to a local model. Also use when your prompt broke after a model update, prompts that work for GPT-4 do not work for Claude or Llama, or you need to do a model migration. Covers DSPy model portability with provider config, re-optimization, model comparison, and multi-model pipelines. Also used for migrate from OpenAI to Anthropic, GPT to Claude migration, try Llama instead of GPT, model comparison framework, multi-provider AI setup, avoid vendor lock-in for AI, prompts break when switching models, model-agnostic AI code.
AITuber API skill for AI video creation. Generate videos with AI narration, visuals, and captions for YouTube Shorts, TikTok, Instagram Reels, and long-form content. Supports AI-generated images, video clips, stock footage, and viral templates like skeleton and character styles. Handles the full pipeline: pick a voice, generate a video, poll for completion, export to MP4 and download, or publish to connected YouTube, TikTok, Instagram, Facebook, Threads, and X channels. TRIGGER when the user wants to: create an AI video, generate a video from a script or idea, list or browse AI voices, export a video to MP4, download a rendered video, list connected channels, publish or schedule a video to social media, check their AITuber subscription or credit balance, or automate video creation. DO NOT TRIGGER for: editing existing video files, uploading user-provided video footage, live streaming, video transcription or captioning of external files, image generation without video context, or anything unrelated to the AITuber platform.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Use when managing Alibaba Cloud ESA — deploy HTML/static sites via Pages, manage Edge Routines (ER) for serverless edge functions, use Edge KV for distributed key-value storage, configure Origin Rules for CDN proxy and origin routing, handle site management, DNS records, cache rules, and query traffic analytics via OpenAPI/SDK. Use when working with ESA, edge deployment, edge functions, Pages, ER, KV storage, DNS, cache, origin rules, CDN proxy, site configuration, traffic analytics, bandwidth trends, or top-N rankings.
Use when managing Alibaba Cloud RDS Supabase (RDS AI Service 2025-05-07) via OpenAPI, including creating, starting/stopping/restarting instances, resetting passwords, querying endpoints/auth/storage, configuring auth/RAG/SSL/IP whitelist, and listing instance details or conversations.
Analyzes spatial transcriptomics with squidpy (1.8.x) on AnnData and SpatialData objects, routing platforms correctly: Visium spots use spatial_neighbors(coord_type='grid') and pair with deconvolution, while Xenium/MERFISH single-cell data use coord_type='generic'/Delaunay neighbors and spatialdata-io readers (xenium, visium_hd, merscope). Runs sq.gr.spatial_neighbors, nhood_enrichment, co_occurrence, spatial_autocorr (Moran's I for spatially variable genes), ripley, and ligrec. Use when the user wants spatial transcriptomics, squidpy, Visium/Xenium/MERFISH analysis, neighborhood enrichment, co-occurrence, or spatially variable genes; QC/clustering uses alterlab-scanpy and spot deconvolution (destVI/Tangram) uses alterlab-scvi-tools. Part of the AlterLab Academic Skills suite.
Managing consent for analytics cookies and implementing privacy-preserving measurement. Covers GA4 privacy configuration, consent mode fallback behavior, aggregate reporting alternatives, and cookieless measurement approaches.
Chart GrowthBook product data, build Analytics dashboards, manage the metric catalog, or query the warehouse directly — run Product Analytics explorations, save charts together on a dashboard, search metrics and fact tables, create fact metrics and their fact tables, or fall back to ad-hoc SQL. Use for "show me signups by country", "chart daily active users", "how many orders last week", "build me a dashboard", "put these metrics on a dashboard", "add a chart to this dashboard", "set up reporting for X", "find our revenue metric", "what fact tables exist", "create a metric", "define a metric on the orders table", "what tables contain user data", "run a SQL query", or any "show me / chart / plot / how many" question about product data. For an A/B test's results or choosing experiment metrics, use experiments. For feature flags, use feature-flags. For first-time API key configuration, use gb-setup.
Extract, analyze, and assess firmware images from embedded devices, IoT hardware, routers, and similar targets — filesystem extraction, hardcoded credential discovery, binary analysis across architectures, web interface review, network service enumeration, emulation, and cryptographic assessment. Use when analyzing a firmware update file, reviewing IoT device security, hunting for hardcoded secrets in device firmware, or assessing the attack surface of an embedded system.
Screen navigation and Navigation reference for Android app development (Kotlin). Jetpack Compose, androidx. Navigation 3 (stable, NavDisplay, NavKey, ResultEventBus, DeepLinkMatcher), Navigation Compose (NavHost, composable, type-safe routes), Fragment navigation (NavHostFragment, Safe Args), deep links, App Links, assetlinks.json, predictive back (OnBackPressedDispatcher).
Build comprehensive ARCHITECTURE.md files following matklad's canonical guidelines — bird's-eye views, ASCII/Mermaid diagrams, codemaps, invariants, and layer boundaries. Triggers on document the architecture, create ARCHITECTURE.md, map this codebase, architectural overview.
Guide for using Argo to create polished product demo videos from Playwright scripts with AI voiceover and animated overlays. Use this skill whenever the user mentions Argo, demo videos, product demos, screen recordings with narration, Playwright video demos, voiceover generation, or wants to automate creating marketing/sales/onboarding videos from a web app. Also use when you see imports from '@argo-video/cli', files named '*.demo.ts' or '*.scenes.json', or an 'argo.config.js' in the project. Even if the user just says "record a demo" or "make a video of my app", this skill applies.
Entry point for Volcengine Ark image/video generation and editing, and Agent Plan personal/enterprise HTTP/WS TTS speech synthesis, including follow-up edits to delivered media and acceptance checks against retained specifications. Supports profile default resources and temporary API Key/Base URL/Endpoint; an explicit Endpoint is not overridden by the current plan profile. Images return synchronously; videos use asynchronous polling.
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.
Develop and review user-authored widgets with Await's public TSX runtime and CLI. Use when creating widget projects, planning widget sizes and layouts, writing widget TSX, checking types, syncing local files, inspecting widget build errors, or capturing previews.
This skill helps an LLM generate correct AxAgent memory retrieval, context-map, and dynamic skill-loading code using @ax-llm/ax. Use when the user asks about contextMap, AxAgentContextMap, onMemoriesSearch, memoriesCatalog, recall(...), inputs.memories, onLoadedMemories, onUsedMemories, onSkillsSearch, skillsCatalog, AxAgentCatalogSkill, discover({ skills }), onLoadedSkills, onUsedSkills, preloaded skills, preloading memories at forward time, relevanceRanking hints, loaded memory/skill IDs, or carrying memories across forward() calls.
This skill helps an LLM generate correct AxGen code using @ax-llm/ax. Use when the user asks about ax(), AxGen, generators, forward(), streamingForward(), validation, assertions, streaming assertions, field processors, step hooks, self-tuning, or structured outputs. For MCP clients, transports, prompts, resources, tasks, subscriptions, or authentication use ax-mcp alongside this skill.
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.