Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Create, edit, and fully analyze spreadsheets with support for formulas, formatting, data analysis, and visualization. Use when Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc.) to: (1) create new spreadsheets with formulas and formatting; (2) read or analyze data; (3) modify existing spreadsheets while preserving formulas; (4) analyze and visualize spreadsheet data; or (5) recalculate formulas
Use when uploading, annotating, building, converting, analyzing, or debugging datasets in Ultralytics Platform or local YOLO — Platform dataset management and Smart Annotation, data.yaml, YOLO label .txt formats, COCO/DOTA/mask conversion, auto-labeling, splits, validation, and errors like "no labels found" or mAP near 0. Covers detect, segment, semantic, depth, classify, pose, and OBB data.
Use when training, fine-tuning, or validating Ultralytics YOLO models in Platform, cloud GPUs, or local code — model.train(), yolo train/val, remote metric streaming, epochs, batch, imgsz, devices, augmentation, multi-GPU, resumes, results, and fixing OOM, NaN loss, low mAP, or overfitting. For hyperparameter search and systematic improvement loops, see yolo-tuning.
When the user wants to price an AI product, choose a charge metric, design pricing tiers, or optimize margins. Also use when the user mentions 'AI pricing,' 'usage-based pricing,' 'consumption pricing,' 'outcome pricing,' 'BYOK,' 'bring your own key,' 'per-seat pricing,' 'pricing tiers,' 'AI margins,' 'cost per token,' or 'pricing model.' This skill covers pricing strategy, packaging, and margin management for AI-native products. Do NOT use for technical implementation, code review, or software architecture.
Expert-level Apache Airflow orchestration, DAGs, operators, sensors, XComs, task dependencies, and scheduling. Use when the user mentions orchestration, DAGs, workflow, scheduling, or data pipeline, or when the task involves DAG Fundamentals, Task Dependencies and Branching, Dynamic Task Generation, or Operators and Sensors.
Query DTS (Data Transmission Service) task status and details across all Alibaba Cloud regions. v12.1: Enhanced reliability - Timeout increased to 10s, exponential backoff (0.2s, 0.4s) for better timeout handling. Parallel execution remains 6-8x faster than v10 (39s → 6s with --workers 16). API retry logic ensures consistent results (no count variations). Supports filtering by instance ID or job name. Automatically polls all 27 regions and 3 job types. Strictly filters for PrePaid/PostPaid tasks and outputs a full Chinese report with Region information. Tasks are grouped by type (Migration/Sync/Subscribe) and sorted by CreateTime within each group. Use this skill when: checking DTS task status, finding migration/sync tasks, verifying task counts, or filtering tasks by instance ID or job name.
Alibaba Cloud MongoDB full lifecycle management: create/query/scale/delete standalone, replica set, sharded cluster instances. Covers node management, security (whitelist/security group), public & SRV address, password reset, renewal, billing conversion, cloud disk reconfiguration, maintenance window, backup, version upgrade, HA switchover, account & tag management. Triggers: "MongoDB", "create MongoDB", "dds instance", "list instances", "MongoDB scaling", "add Mongos/Shard node", "MongoDB whitelist", "reset password", "allocate public address", "SRV address", "MongoDB renewal", "billing type conversion", "cloud disk reconfiguration", "delete MongoDB instance", "maintenance window", "restart MongoDB", "MongoDB backup", "upgrade MongoDB version", "HA switchover", "MongoDB tags", "MongoDB account"
Ark UI headless / unstyled component library. Based on Zag.js, with Chakra UI v3 as its foundation. Supports React / Solid / Vue / Svelte. asChild, RootProvider, createListCollection, createTreeCollection, Presence hideMode, useHotkey / useHotkeys, data-* selectors. Component APIs for Navigation Menu, TOC, Tour, Signature Pad, Image Cropper, Floating Panel, Angle Slider, and more.
Import local or downloaded media, or relink missing media to an existing ChatCut asset, through the hosted Claude plugin. Use the editor loopback bridge when the editor and files are on the same machine; use the upload helper for imports otherwise. Desktop MCP sessions use their own built-in import tools.
Expert knowledge for Azure Cloud Shell development, including troubleshooting, architecture and design patterns, limits and quotas, security, and deployment. Use when configuring Cloud Shell storage, session limits, private VNet access, RBAC, or private endpoints, and for other Azure Cloud Shell-related development tasks. Not for Azure Portal (use azure-portal), Azure Virtual Machines (use azure-virtual-machines), Azure Functions (use azure-functions), or Azure Kubernetes Service (AKS) (use azure-kubernetes-service).
Expert knowledge for Azure Confidential Computing development, including best practices, decision-making, architecture and design patterns, security, configuration, integrations and coding patterns, and deployment. Use when working with SGX enclaves, confidential VMs/GPUs, AKS confidential containers, Fortanix CCM, or secure key release, and for other Azure Confidential Computing-related development tasks. Not for Azure Enclave (use azure-enclave), Azure Dedicated HSM (use azure-dedicated-hsm), Azure Cloud Hsm (use azure-cloud-hsm), or Azure Payment Hsm (use azure-payment-hsm).
Expert knowledge for Azure Resiliency development, including best practices, security, configuration, and deployment. Use when designing zone-resilient topologies, zone-down drills, backup/replication policies, vault lifecycle, or RBAC, and for other Azure Resiliency-related development tasks. Not for Azure Reliability (use azure-reliability), Azure Service Health (use azure-service-health), Azure Monitor (use azure-monitor), or Azure Site Recovery (use azure-site-recovery).
Expert knowledge for Azure VMware Solution development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring AVS networking/HCX, vSAN ESA/datastores, Horizon/Citrix VDI, JetStream DR, or SQL migrations, and other Azure VMware Solution related development tasks. Not for Azure Baremetal Infrastructure (use azure-baremetal-infrastructure), Azure Large Instances (use azure-large-instances), Azure Nutanix (use azure-nutanix), Azure Virtual Machines (use azure-virtual-machines).
Azure Well-Architected Framework (WAF) for cloud architecture review. PROACTIVELY activate for: (1) Azure architecture review or design, (2) Reliability pillar (availability zones, geo-replication, backup/restore, RPO/RTO), (3) Security pillar (Zero Trust, encryption at rest/in transit, identity, network segmentation), (4) Cost Optimization pillar (rightsizing, reserved instances, savings plans, FinOps), (5) Operational Excellence pillar (IaC, observability, automation), (6) Performance Efficiency pillar (caching, autoscaling, async patterns), (7) Sustainability pillar, (8) WAF Reviews via the WAF Assessment Tool, (9) Microsoft Cloud Adoption Framework (CAF) alignment. Provides: pillar-by-pillar checklist, WAF assessment workflow, common antipatterns by pillar, and Azure Advisor mapping
Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation", or needs vision-capable AI generation.
BingX wallet deposits and withdrawals — query deposit and withdrawal history, get coin network configuration, initiate withdrawals, and fetch deposit addresses. Use when the user asks about BingX deposit records, withdrawal records, coin network fees, withdrawal limits, deposit addresses, or initiating a withdrawal.
Expert-level CodeQL for static analysis, vulnerability detection, and security code scanning. Use when the user mentions static analysis, SAST, vulnerability detection, or github security, or when the task involves writing CodeQL queries, building a CodeQL database, taint tracking, or scanning for injection and hardcoded credentials
Risk-scaled repo execution and code-evidence protocol. Skip architecture-only work, explanation, contract-preserving prose, and status. Use for contract changes, debugging, code review, implementation plans, and Git mutation; mixed tasks: only those parts.
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-*.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating user timing marks.
Write sales copy that converts — landing pages, VSLs, emails, headlines, CTAs, Meta ads, upsell sequences, and anything persuasive. Use this skill whenever the user asks to write, rewrite, punch up, or critique sales copy, direct response copy, VSLs, TSLs, email sequences, ad creative, headlines, CTAs, or landing pages. Also trigger for requests like 'write copy for my offer', 'improve my headline', 'write a subject line', 'help me sell X', or any task involving persuasive writing for commercial purposes. Applies the proven frameworks of Schwartz, Hopkins, Ogilvy, Halbert, Caples, Sugarman, and Collier.
Download and archive Discord attachments, images, and links from a server channel, DM, or Discord Data Package export. Use when asked to "download Discord attachments", "harvest a Discord channel", "archive a DM", or "organize a Discord Data Package"; or when preserving files from a Discord export or conversation.
Send emails, buy forwarding inboxes, manage custom subdomains, and read messages programmatically via x402. USE FOR: - Sending emails (one-off or from custom addresses) - Buying a forwarding inbox ([email protected]) - Purchasing custom email subdomains ([email protected]) - Reading and managing inbox messages programmatically - Setting up catch-all forwarding for subdomains - Managing authorized signers for shared subdomains TRIGGERS: - "send email", "email this to", "notify by email" - "buy inbox", "forwarding address", "email inbox" - "custom domain", "subdomain", "email subdomain" - "read emails", "check inbox", "list messages" - "email address", "disposable email", "temporary email" ALWAYS use `npx agentcash@latest fetch` for stableemail.dev endpoints. IMPORTANT: Use exact endpoint paths from the Quick Reference table below.
Conventions for writing a Markdown explainer that walks the reader through a concept or system. Lays out term-list formatting, Mermaid diagram rules, granularity expectations, and a fixed five-part structure. Use when the user asks for an explainer, a concept write-up, a glossary section, or otherwise wants a system or idea documented for another reader.
Reference for the Rust AI/ML library fandhe-ai. A from-scratch implementation independent of Burn / candle / tch. Includes tape(), tape_for, Tape, Gradients, Tensor, Var, LinearVars, autodiff, kernel fusion, FusionPlan, BackendOps, Device (Cpu / Cuda / Metal), DeviceParamStore, compat::array, compat::Sequential, nn::Module, optim (AdamW / GradScaler), data::DataLoader, ONNX import / export, safetensors, inference::generate / KvCache, and guardrail / self-repair CLI.
Author, explain, diagnose, and validate Splunk search-time field extractions and mappings to Common Information Model (CIM) datasets from representative events, configuration, and search evidence. Use for automatic key-value extraction, regex or delimiter extraction, props.conf EXTRACT and REPORT/transforms.conf rules, SPL extraction commands, aliases, calculated fields, lookups, event types, tags, value normalization, CIM field mapping, and missing or incorrect normalization; do not use for deployment execution, ingestion transport, app installation, knowledge-object governance, data-model acceleration, or unrelated search/dashboard repair.
Query blockchain data across 40+ chains using Flipside's AI agents. Use when working with blockchain data, crypto wallets, DeFi protocols, NFTs, token transfers, or on-chain analytics. Requires the Flipside CLI (https://docs.flipsidecrypto.xyz/get-started/cli)
Multi-framework frontend development. Frameworks: React 18+ (Suspense, hooks, TanStack), Vue 3 (Composition API, Pinia, Nuxt), Svelte 5 (Runes, SvelteKit), Angular (Signals, standalone). Common: TypeScript, state management, routing, data fetching, performance optimization, component patterns. Actions: create, build, implement, style, optimize, refactor components/pages/features. Keywords: React, Vue, Svelte, Angular, component, TypeScript, hooks, Composition API, runes, signals, useSuspenseQuery, Pinia, stores, state management, routing, lazy loading, Suspense, performance, bundle size, code splitting, reactivity, props, events. Use when: creating components in any framework, building pages, fetching data, implementing routing, state management, optimizing performance, organizing frontend code, choosing between frameworks.
Query Google Analytics 4 (GA4) reports via the Analytics Data API v1 and list properties via the Admin API. Use when the user mentions Google Analytics, GA4, website traffic / sessions / users, top pages or sources, conversions, or a realtime report.
Interview the user until the plan is clear, before any code gets written. Use when the user shares a new product idea or feature, or asks to build something whose person, problem, core action, or scope is not already documented in an approved IDEA_SCOPE.md or scoping doc. Also use when they say “grill me”, “poke holes”, “stress-test this”, “what am I missing”, or seem unsure what to build. Skip small fixes, copy tweaks, and work already covered by an approved scoping doc.
SÀN design mặc định của overstack (anti-AI-slop) — mọi UI đứng trên nó: build trang mới, audit, redesign, extract design từ URL/screenshot, và KHÓA HỆ THIẾT KẾ XUYÊN MÀN HÌNH qua design.md (chạy `hallmark redesign` cả app một lần → sinh design.md ở project root → mọi màn hình sau bám cùng hệ token/type/motion, không mỗi màn một kiểu). Gọi khi user nói: 'thiết kế', 'giao diện', 'làm UI/landing page/app mới', 'redesign', 'audit design', 'design system', 'đồng bộ giao diện giữa các màn hình', 'khóa hệ thiết kế', 'sao trang này trông AI-generated', hoặc gọi đích danh hallmark / dùng verb build·audit·redesign·study. Việc chạm UI mà không chắc dùng gì → dùng skill này (nó là sàn, các skill taste khác là flavour bên trên).
Use when the user wants copy-ready AI scientific illustration prompts based on papers, research documents or text, figure captions, proposal or defense materials, or reference images that can be interpreted visually. Triggers include paper figures, scientific illustration, graphical abstracts, mechanism diagrams, technical roadmaps, experimental setup diagrams, model architecture diagrams, multi-panel comparisons, presentation overview figures, reference-image style transfer, creating templates for unfamiliar fields, or uploading or citing PDFs, Word, LaTeX, Markdown, abstracts, methods sections, figure captions, project descriptions, research plans, or reference images. Also use for scientific figure or research illustration prompts, graphical abstract prompts, mechanism diagrams, technical roadmaps, experimental setup diagrams, model architecture diagrams, multi-panel scientific figures, paper or conference figures, or AI image prompts based on papers, research documents, abstracts, methods sections, figure captions, proposals, reference images, PDFs, Word docs, LaTeX files, Markdown files, or research plans.
Analyze V8 heap snapshots to investigate memory leaks and retention issues. Use when given .heapsnapshot files, asked to compare before/after snapshots, asked to find what retains objects, or investigating why objects survive GC. Provides snapshot parsing, comparison, retainer-path helpers, and scratchpad scripts.
Install, configure, run, customize, schedule, and extend Horizon, the profile-driven news radar. Use for first-time Horizon installation, source selection and onboarding, generating or reading daily digests, tuning processing profiles and digest limits, setting up delivery and scheduled runs, diagnosing pipeline results, or contributing scrapers, extractors, profiles, and pipeline changes to this repository. Also use when a user wants to turn reading interests into a personal news radar using Horizon.
Use when designing hosted or background agent infrastructure: sandboxed execution, remote coding environments, warm pools, session persistence, multiplayer collaboration, self-spawning agents, or Modal-style sandboxes.
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.