Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
When the user wants to build or improve a sales bot's ability to clarify vague or ambiguous responses before proceeding. Also use when the user mentions "clarifying questions," "disambiguation," "unclear responses," "vague answers," or "asking for clarity."
React Testing Library best practices for writing maintainable, user-centric tests. Use when writing, reviewing, or refactoring RTL tests. Triggers on test files, testing patterns, getBy/queryBy queries, userEvent, waitFor, and component testing.
When the user wants to build or improve a sales bot's ability to request referrals at the right moment. Also use when the user mentions "referral timing," "referral requests," "introduction requests," "warm introductions," or "network expansion."
Generate, write, or run an ad-hoc query against SigNoz observability data (metrics, logs, or traces) without wrapping it in a dashboard panel or alert. Make sure to use this skill whenever the user asks "show me error rates", "query logs for timeout errors", "what's the p99 latency for the cart service", "how many requests hit the payment endpoint", "find slow traces", "errors in the last hour", "which agent runs cost the most", "LLM token usage by model", "LLM calls from agent runs with many tool calls", "why does AI Observability show no data", or otherwise asks an exploratory question that needs live observability data, even if they don't say "query" or "search" explicitly.
Thorough, file-cited technical debt audit across 9 dimensions using AST-grep (tree-sitter), grep, LSP, and language-native tooling. Produces TECH_DEBT_AUDIT.md with severity, effort estimates, and prioritized fixes. Use when asked for codebase health check, tech debt audit, architecture review, code quality assessment, or cleanup planning. Triggers: 'tech debt', 'technical debt', 'debt audit', 'code health', 'technical debt audit', 'codebase health check', 'find tech debt', 'debt analysis', 'audit code quality'.
Judge whether something actually produces value in a concrete scenario. Value is a beneficial relational property between subject and object, conditioned on the states of both sides, that only holds in a specific scenario. Typical uses: judging whether a value proposition holds, mapping a capability to a concrete use scenario, diagnosing why no one uses it or why they don't stick, clarifying how to position or state the value, assessing whether something is worth investing in, or judging whether you can borrow someone else's approach (e.g. "is this idea sound?", "does anyone actually want this?", "why did we roll it out and no one uses it?", "why do people try it once and never come back?", "can we copy what someone else did?"). When the thing being judged has a decision-maker (who pays / signs off) that is not the same as the actual end user (enterprise software, internal platforms, etc.), first state which side you're analyzing for and split the two value relationships to run separately.
When the user wants to build or improve a sales bot's ability to seamlessly connect prospects to live reps with full context passed along. Also use when the user mentions "warm handoff," "transfer to human," "live rep handoff," "context handover," or "seamless transfer."
Implement and debug React Native or Expo motion with Reanimated 4 and Gesture Handler 3: state transitions, layout, gestures, scroll, worklets, cancellation, and accessible alternatives. Use for native UI motion, not web Motion or a reason to add canvas graphics to ordinary views.
Speech-to-text (ASR). Uses Volcengine BigModel ASR for speech recognition, with two modes: Express (≤2h/100MB, fast synchronous response) and Standard (≤5h, asynchronous recognition). Supports Lark voice messages, local audio files, and audio URLs. Use this skill when receiving a voice message or audio attachment (.ogg/.mp3/.wav).
When the user wants to build or improve a sales bot's ability to detect and adapt to prospect communication preferences across SMS, email, phone, and chat. Also use when the user mentions "channel preference," "communication preference," "preferred channel," "omnichannel," or "channel switching."
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
Interactive ideation and brainstorming skill for the Elephant & Goldfish Model (EGM). Helps turn half-baked concepts into structured hypotheses via clarifying questions, review, and iterative refinement. Produces an RFC summary for human review or more detailed design with egm-draft.
Helps users search and filter open-source projects on GitHub and produces a structured recommendation report. Trigger when the user says “help me find open-source projects,” “search what’s on GitHub,” “find repositories in the XX area,” “open-source project recommendations,” “github search,” or “/github-search.”
Implement and audit privacy controls in product and infrastructure — GDPR, CCPA / CPRA, LGPD, PIPEDA. Covers data minimization, lawful basis, consent management, data subject access requests (DSARs — access, deletion, portability), data processing agreements, DPIA / TIA, breach notification timing, data classification, and the technical implementation of 'right to be forgotten' across backups, caches, analytics, and third parties. Use when the user mentions 'GDPR,' 'CCPA,' 'CPRA,' 'data privacy,' 'privacy engineering,' 'data subject access request,' 'DSAR,' 'right to deletion,' 'right to be forgotten,' 'data portability,' 'consent management,' 'cookie consent,' 'data minimization,' 'DPIA,' 'data protection impact assessment,' 'breach notification,' 'DPA,' 'data processing agreement,' 'sub-processor,' 'cross-border data transfer,' 'SCCs,' or needs to implement or review privacy controls.
Use when making a trailer, cutscene, cinematic or short film in Unreal Engine 5.8 with Sequencer: shot lists, master and shot sequences, cameras, lenses, depth of field, camera cuts, spawnables, character animation in shots, per-shot lighting, Movie Render Graph or Movie Render Queue EXR renders, "render darker than the viewport", "first frames pop", "last frame missing", ACES or OCIO to DaVinci Resolve, the 180-degree rule, Sequencer Python, or reviewing a cut.
This skill should be used when the user asks to "plan a scene", "scene structure", "sequel scene", "dialogue subtext", "deep POV", "psychic distance", "try fail", "scene cards", "exposition", "info dump", "flashback", "time skip", "story opening", "first page hook", "introduce a character", "scene outcome", "yes-but no-and", "chapter hook", or wants scene-level craft for drafting or revision. NOT for book-level pacing or act structure (use plot-structure), or drafting the prose of a scene or chapter (use chapter-writing).
This skill should be used when the user asks to “write a sequel,” “write a prequel,” “start book two,” “continue the series,” “companion novel,” “spin-off,” “link books in a series,” “carry characters into the next book,” “series continuity,” “series bible,” “pitch my series,” “series pitch,” or “multi-book pitch,” or needs to plan, pitch, or keep canon consistent across multiple Story Skills projects. NOT for a standalone book (use story-init), continuity within one book (use revision-continuity), or a query, pitch, or synopsis for a single book (use submission).
STM32 bare-metal skill for CMSIS-only MCU projects. Use when scaffolding STM32 firmware without HAL, configuring clocks/RCC, using CMSIS headers, or building with arm-none-eabi-gcc. Activates on queries about STM32 bare metal, CMSIS without HAL, STM32F4/H7 bring-up, or minimal Makefile CMake for Cortex-M.
three.js audio spatialization: AudioListener attached to camera rig, Audio and PositionalAudio sources, AudioAnalyser for FFT/time-domain data, and integration with Web Audio API contexts; AudioLoader is referenced from threejs-loaders for file decoding. Use when placing 3D sound, configuring panner parameters, or visualization; not a replacement for full game audio middleware.
Bootstrap and run a lightweight multi-agent development team. Use when starting or adopting a project, planning work, coordinating implementation and optional QA, brainstorming with distinct perspectives, or preserving context across sessions.
Anti-detection browser automation using Camoufox (Firefox fork with C++ fingerprint spoofing). Use when standard browser tools are blocked by Cloudflare, Akamai, or bot detection. Triggers include “stealth browse”, “anti-detection”, “bypass bot”, “camofox”, “blocked by Cloudflare”, scraping protected sites (X/Twitter, Amazon, Product Hunt), or when agent-browser/playwright fails with bot detection errors.
Build and deploy AI agents with Cloudbase Agent (TypeScript), a TypeScript SDK implementing the AG-UI protocol. Use when: (1) deploying agent servers with @cloudbase/agent-server, (2) using LangGraph adapter with ClientStateAnnotation, (3) using LangChain adapter with clientTools(), (4) building custom adapters that implement AbstractAgent, (5) understanding AG-UI protocol events, (6) building web UI clients with @ag-ui/client, (7) building WeChat Mini Program UIs with @cloudbase/agent-ui-miniprogram.
Create and manage agentic wallets with Cobo. Use for autonomous onchain operations via the caw CLI: token transfers, contract calls, pact creation and approval, DeFi execution (Uniswap, Aave, Jupiter), and wallet onboarding on EVM chains and Solana. Triggers on requests involving caw, MPC wallet, TSS node, agent wallet, Cobo, pact, or any crypto wallet operation for AI agents. NOT for fiat payments or bank transfers.
When the user wants to build or improve a sales bot's ability to respond appropriately when prospects bring up competitors. Also use when the user mentions "competitor mentions," "competitive response," "handling competition," "when they mention alternatives," or "competitive conversations."
Guides agents through experiment creation: reading the project's setup with experiment-setup-context, defining the hypothesis, configuring rollout and bucketing, setting up analytics and running time, and reporting which choices are guesses. Delegates rollout decisions to configuring-experiment-rollout and metric setup to configuring-experiment-analytics.\nTRIGGER when: user asks to create a new experiment or A/B test, OR when you are about to call experiment-create.\nDO NOT TRIGGER when: user is updating an existing experiment, managing lifecycle, or only browsing experiments.
Use when building an internal admin-facing AI agent in a Medusa project. These agents are operated by merchants and store operators — not customers. Covers data models, module service, agent runtime (tools, system prompt, streamText), streaming API routes (NDJSON), and admin UI chat extensions. Load for any internal agent type: store operations assistant, product audit, cohort analysis, customer service tooling for support staff, etc. Do NOT use for customer-facing agents (storefront chatbots, buyer-side assistants).
Crypto trading analysis advisor. Triggers when users ask whether a token is worth trading, if a position can be taken, or for trend analysis. Provides high-value data sources and professional trading principles. Trigger phrases include "should I trade", "can I long/short", "is it a good setup", "trade recommendation", "can I enter here", "what's the play" etc.
Use when building a web frontend with Deno — running React, Vite, Astro, SvelteKit, Next.js, Nuxt or other npm frameworks under Deno, or working with Fresh, Deno's own island-architecture framework. Covers which path to pick, Fresh 2.x routes, handlers, islands, Preact signals, Tailwind, and Fresh 1.x to 2.x migration.
Manage DingTalk to-dos. Use this skill when the user mentions “钉钉待办,” “待办任务,” “创建待办,” “新增待办,” “查看待办,” “完成待办,” “标记完成,” “删除待办,” “待办列表,” “我的待办,” “设置截止时间,” “指派待办,” “dingtalk todo,” “todo task,” or “task management.” Supports all to-do operations, including creating tasks (with description, deadline, priority, and participants), retrieving details, querying lists (filtered by completion status), updating tasks, marking them complete, and deleting them.
Instruments an existing Android project (Kotlin or Java) with the Dynatrace Mobile Agent for basic monitoring. Covers zero-to-first-event setup only: Gradle plugin, agent config, and user privacy opt-in. Do not use for advanced Dynatrace configuration beyond initial instrumentation.
Authoritative, machine-readable EDS design rules for color tokens, typography, spacing, elevation, icons, and page layout zones. USE FOR: looking up correct EDS CSS custom properties, typography variant names, spacing tokens, shadow/elevation tokens, icon usage rules, and Fusion Portal page layout conventions. This is a lookup reference consumed by other skills and agents — it has no standalone workflow. DO NOT USE FOR: React component props or usage examples (use fusion-research + mcp_fusion_search_eds), general Copilot coding tasks, or Fusion Framework API questions.
Audit third-party dependencies for known security advisories in any ecosystem — reads every lockfile, uses the native audit tool where one exists and the OSV database otherwise, and files one deduplicated issue per vulnerable package with its upgrade path. For code-level security review use om-auto-sec-report. Use for “audit dependencies,” “check for vulnerable packages,” “security advisories.”
When the user wants to build or improve a sales bot's ability to update lead scores dynamically during conversations. Also use when the user mentions "real-time scoring," "dynamic lead scoring," "propensity scoring," "live scoring," or "conversation scoring."
Provision, connect, and operate Sealos Cloud databases through sealos-cli for local development, Devbox development, and app setup. Use when the user needs a cloud database for a project, asks to create or connect PostgreSQL/MySQL/MongoDB/Redis or another Sealos database, wants DATABASE_URL or similar env vars wired into a dev environment, needs database connection details, backups, logs, public access, or wants to replace local Docker Compose databases with a managed Sealos database.
When the user wants to build or improve a sales bot's ability to monitor sentiment over time. Also use when the user mentions "sentiment trends," "tone tracking," "campaign sentiment," "aggregate sentiment," or "sentiment monitoring."
Rewrite and audit SEO page titles, title tags, MDX frontmatter titles, H1 alignment, and bulk title improvements. Use when the user mentions titles, title tags, SERP titles, metadata titles, SEO titles, CTR, truncation, or asks to improve titles across pages
Set up, repair, and build components with NativeWind v4 and Tailwind CSS v3 in Expo React Native apps. Use for an explicitly v4 project, v4 configuration failures, className interoperability, or v4 theming; not for NativeWind v5 or generic web Tailwind setup.
Comprehensive guide for implementing Syncfusion Blazor dropdown components including AutoComplete, ComboBox, DropDown List, MultiSelect Dropdown, and ListBox. Use this when building selection interfaces, data binding, filtering, cascading dropdowns, custom templates, and accessible dropdown experiences in Blazor applications. Covers all dropdown components from Syncfusion.Blazor.DropDowns package
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.