Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Conditionally audit and generate e-commerce structured data and agentic-commerce readiness for product pages — validate Product/Offer (price, priceCurrency, availability), AggregateRating/Review, faceted-navigation canonicalization and variant/ProductGroup handling, cross-check page-to-schema-to-feed consistency, and assess whether shopping agents can read the store (UCP merchant profile, catalog eligibility, ACP feed hygiene). Module M18. Feeds both the Search SEO and AI Visibility scores.
Audit a page's indexability and site health — canonical presence/validity (self vs cross-domain vs chain, canonical to redirect/404, and the genuinely lethal canonical+noindex pair where the canonical points elsewhere), robots meta and X-Robots-Tag noindex/nofollow, duplicate clusters, pagination signals, plus redirect chains/loops, 4xx/5xx and soft-404 internal links, mixed content, HTTP-to-HTTPS enforcement, user-agent content divergence (cloaking), orphan pages and click-depth — and generate self-referential canonical / noindex-removal fixes. Module M2 (covers M3 site health). Feeds the Search SEO score.
Audit mobile-friendliness of a page from the PageSnapshot — verify the viewport meta, no horizontal-scroll/fixed-width layouts, adequate tap targets, legible base font, and mobile/desktop content parity — and generate the viewport meta when missing. Module M7b. Feeds the Search SEO score.
Organic social media graphics (posts, stories, carousels, profile headers/covers) sized for Instagram, X/Twitter, LinkedIn, Facebook, Pinterest, and TikTok, with platform safe zones. Defaults to Gemini 3.1 Flash image generation; HTML/CSS for templated carousels. Use for unpaid feed content; for paid ads use ad-creative-design, for website/email banners use banner-design, for YouTube thumbnails and OG images use thumbnail-design. Trigger phrases: "create a social media post", "design an Instagram graphic", "make a Twitter image", "LinkedIn post graphic", "social media design", "Instagram story", "carousel design", "social graphic".
Entry point for evals. Use when the user asks for help with evals, does not know where to begin, or asks for something no other skill in this plugin matches. Do NOT use when a more specific skill in this plugin already matches; load that skill directly.
Stem cell, iPSC, and organoid research — pluripotency markers, differentiation protocol pathways, lineage commitment factors, and organoid model selection. Use for iPSC characterization, differentiation protocol design via developmental-pathway recapitulation, and organoid-model selection for disease modeling.
Multi-agent AI stock analysis for China A-shares. 15 specialized analysts collaborate across technical analysis, fundamental analysis, sentiment analysis, smart money flow tracking, macro economics, and game theory to deliver structured buy/sell/hold recommendations with risk assessment.
Prepare and conduct user interviews that extract truth, not validation. Use when asked to create an interview guide, prepare for user interviews, plan customer discovery, or talk to users. Built on The Mom Test and YC's Five Questions framework for startup customer development.
WAVES — Workers · Aggregate · Verify · Extend — wave-based orchestration for Cursor. Decompose a big goal into independent slices, fan them out to isolated parallel subagents via parallel Task tool calls as a bounded "wave", verify each structured handoff, then synthesize, and extend into another wave only when warranted. Invoke explicitly with /waves; bounded by design to avoid runaway token loops. For big research, analysis, audits, and codebase or data exploration where one linear pass is slow. Formerly parallel-orchestrate; also fan out, parallelize, orchestrate subagents, multi-agent.
Use for any task involving Ultralytics Platform, the ultralytics Python package, yolo CLI, YOLO model weights (.pt), dataset annotation, training, validation, prediction, tracking, export, deployment, or the detect / segment / semantic / depth / classify / pose / OBB vision tasks.
Plan and build agents, apps, or harnesses with You.com Search, Contents, Research, Finance, and other agentic resources found through the `you-discover` tool. Use when designing an integration — inference provider, BYOK local harness, agent behind MCP, SDK or direct-API app, or plugin for an existing agent — not when answering a question with web search.
Make an AI agent run on a schedule, loop, or interval — cron, heartbeats, recurring autonomous checks. Use for "run every N minutes", "schedule a task", "run on a loop", "heartbeat". Covers external clocks (Claude Code, Codex, Pi) vs Hermes' built-in scheduler
Use for Agently runtime extensions: AgentExecution plugins and final review/artifact policies, Actions and MCP, Shell/BashExecutor and PowerShell permissions, ExecutionResource lifecycle, TaskWorkspace, RecordStore, auto_func and KeyWaiter, FastAPIHelper, or optional DevTools observation.
Find sites ranking for target keywords, score every prospect with Ahrefs domain authority and page-level traffic, identify the strongest pitch angle per row ("links to competitor", "mentions brand without linking", "top-3 SERP", "resource page", "outdated content"), generate brand-voice-matched outreach emails using an outreach-type-aware template (unlinked-mention claim, competitor-link replacement, resource-page inclusion, outdated-content replacement, topical niche-edit), and propose a concrete in-article link placement as three artifacts — the verbatim source sentence, the same sentence rewritten with the link spliced in, or a fully drafted new insertion if no natural fit exists. Use when user asks to find link building opportunities, prospect link partners, recover unlinked brand mentions, replace competitor links, build a tiered outreach list, or run cold email outreach for SEO link building.
Creates and retrieves AI video and image-related assets via the Arcads external API (Seedance 2.0, Sora 2, Veo 3.1, Kling, Grok Video, Nano Banana, b-roll, scene, script/actor flows). Loads prompts from the bundled prompting guide and model library, respects HTTP Basic auth from ARCADS_API_KEY, and polls assets/videos until ready. Use when the user mentions Arcads, external-api.arcads.ai, Seedance, Sora2, Veo, Kling, Nano Banana, b-roll, UGC scripts, or generating marketing creative through Arcads.
Create or revise Architecture Decision Records by analyzing the codebase to understand current state, affected code paths, constraints from existing patterns, and trade-offs grounded in implementation reality.
HarmonyOS ArkTS application development with ArkUI declarative UI framework. Use when building HarmonyOS/OpenHarmony apps, creating ArkUI components, implementing state management with decorators (@State, @Prop, @Link), migrating from TypeScript to ArkTS, or working with HarmonyOS-specific APIs (router, http, preferences). Covers component lifecycle, layout patterns, and ArkTS language constraints.
Expert knowledge for Azure Resource Manager development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when authoring Bicep/ARM templates, using CLI/PowerShell/REST, deploying stacks/registries, moving resources, and other Azure Resource Manager-related development tasks. Not for Azure Policy (use azure-policy), Azure Resource Graph (use azure-resource-graph), Azure Portal (use azure-portal), or Azure Role-based access control (use azure-rbac).
Build the site-facing parts of an EmDash CMS project on Astro, including schema and seeds, content queries, Portable Text rendering, menus, taxonomies, widgets, and deployment configuration. Use for EmDash site and theme work; use creating-plugins instead when the task is plugin authoring alone.
Unix-composable CLI design patterns. Use when building CLI tools, designing command trees, implementing output layers, or testing CLI behavior. Covers stream separation (stdout/stderr), format flags (--json/--plain), exit codes, TTY detection, composability, and error design. Language-agnostic principles; TypeScript implementation patterns in resources/. For API design (REST, HTTP), see api-design.
Use when configuring a site for CloudCannon for any of the following. Download the JSON schemas before writing any configuration (see the top of SKILL.md). - Setting up cloudcannon.config.yml or .cloudcannon/initial-site-settings.json - Generating a baseline with the CloudCannon CLI - Adding or modifying Collections, Inputs, Structures, or Select Data - Setting up Structures for Array and Object Inputs - Configuring Collection URLs - Scheduling builds to publish future-dated content (_schedule.txt) - Configuring a site in a monorepo, or several sites in one repository - Troubleshooting missing fields or Input types
Laws of UX (Fitts, Hick, Miller, Jakob, Peak-End, Doherty), Gestalt principles, cognitive biases, mental models, attention, and memory constraints. Use when auditing cognitive load, sizing tap targets, reducing choice overload, fixing decision fatigue, or grounding a design decision in research.
Detects misplaced classes and fixes component hierarchy problems — finds code that should belong inside a component but sits at the root level. Use when asking "clean up component structure", "find orphaned classes", "fix module hierarchy", "flatten nested components", or analyzing why namespaces have misplaced code. Do NOT use for dependency analysis (use coupling-analysis) or domain grouping (use domain-identification-grouping).
Use when building features with TCA (The Composable Architecture), structuring reducers, managing state, handling effects, navigation, or testing TCA features. Covers @Reducer, Store, Effect, TestStore, reducer composition, and TCA patterns
Reviews DataHub connector implementations against 22 golden standards for compliance, code quality, silent failures, test coverage, type design, and merge readiness. Use when reviewing connector code, checking a PR, auditing a connector implementation, or verifying connector standards compliance.
Use this skill when the user wants to explore lineage, trace data dependencies, perform impact analysis, find root causes, map data pipelines, or understand how data flows between systems. Triggers on: "what feeds into X", "what depends on X", "show lineage for X", "impact analysis", "trace the pipeline", "root cause", "upstream of X", "downstream of X", or any request involving data lineage and dependency tracking.
ElevenLabs automatic dubbing - translate and dub audio/video into 29 languages while preserving speaker voice via inference.sh CLI. Capabilities: auto speaker detection, voice-preserving translation, video dubbing, audio localization. Use for: content localization, video translation, multilingual content, international distribution. Triggers: dubbing, dub video, translate audio, video translation, audio translation, localize content, elevenlabs dubbing, eleven labs dub, multilingual dub, voice translation, auto dub, language dub, content localization
Find out why the tests pass but the app is broken. Catches false greens: a green suite over a feature that does not work, a mocked API standing in for a real one, an assertion that holds no matter what the app does, a click handler wired to nothing. Use when the suite is green and the user says it is broken, when a test never fails, when coverage looks fine but bugs still ship, or before trusting a passing run you did not watch.
Use when a user wants to change an Adapty flow by editing its builder config JSON—such as adding a locale, translating a paywall or onboarding, rewriting copy, adding/removing/reordering screens, adding tabs or plan pickers, wiring quiz branching, or building an onboarding sequence. Also use after a flow is published to point a placement at it so an app can fetch it. Triggers include “edit my flow config”, “add a language to my paywall”, “translate my onboarding”, “remove a screen from the flow”, “add tabs to my paywall”, “show the user's name or coin balance on my paywall”, “build me a paywall like this”, “build me an onboarding”, a supplied Adapty flow config, and “publish my flow”, “I published my flow”, “attach my flow to a placement”, “create a placement for this flow”, “my flow does not show up in the app”, “how are my screens connected”, “show me the flow map”, and “where does this button lead”.
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.