Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Planning skill for transactional notifications, alerts, and reminders. Assesses developer needs across urgency, channel selection, delivery confirmation, and fallback patterns to recommend the right Twilio notification architecture. Handles both “send shipping updates to customers” and “build a multi-channel alert system with delivery confirmation and fallback”
UI5 smart controls (sap.ui.comp) best practices for OData V2 annotation-driven controls. Use when creating/troubleshooting SmartField, SmartForm, SmartFilterBar, SmartChart, SmartLink, SmartMultiInput, or SmartTable. Covers control selection, annotations (ValueList, FieldControl, SemanticObject, UI.LineItem, UI.Chart), mandatory rules, common errors, and per-control API reference. Triggers: "SmartField", "SmartForm", "SmartFilterBar", "SmartChart", "SmartLink", "SmartMultiInput", "sap.ui.comp", "smart control annotations", "OData V2 metadata-driven", "value help annotations", "ValueList annotation", "field control annotation", "semantic object navigation". Keywords: sap.ui.comp, SmartField, SmartForm, SmartFilterBar, SmartChart, SmartLink, SmartMultiInput, SmartTable, ValueHelpDialog, OData V2, annotations, ValueList, FieldControl, SemanticObject, entitySet, ControlConfiguration, GroupConfiguration, textArrangement, FilterProvider, initialise, beforeRebindChart, navigationTargetsObtained
Desktop automation CLI for AI agents (macOS, Linux, Windows). Screenshot, click, type, scroll, drag with native Zig backend. Use this skill when automating desktop apps with computer use models (GPT-5.4, Claude). Covers the screenshot-action feedback loop, coord-map workflow, window-scoped screenshots, and system prompts for accurate clicking
Write a developer value proposition that is specific, provable, and free of puffery. Use when the messaging leans on "powerful," "better," "seamless," or "best-in-class," when claims have no proof, or when the same line is supposed to reach both the developer and the buyer.
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
This is a skill for benchmarking the efficiency of automatic prefix caching in vLLM using fixed prompts, real-world datasets, or synthetic prefix/suffix patterns. Use when the user asks to benchmark prefix caching hit rate, caching efficiency, or repeated-prompt performance in vLLM.
Clone a website — two modes. SNAPSHOT = a faithful, self-contained offline copy of a page (HTML+CSS+JS+images in one file, exact bytes, SingleFile-style). RECONSTRUCT = AI reverse-engineer the page into a clean editable Next.js/Tailwind codebase (design tokens → component specs → parallel builders → visual-diff QA, the ai-website-cloner-template method). Use when the user wants to "clone this site", copy a page's design/UI + interactions, mirror a layout, save offline, or rebuild a site as editable code. Built-now-adapt-later: snapshot builtin works now; faithful live capture + the reconstruct pipeline are one-config engine adapters.
Read this before the first X Money action in a session and again on any X Money error, refusal, or missing capability. Covers the approval rule for every action that moves money (always ask, every time, no exceptions), how the connection works (connection code plus passkey in the X app), how to guide the user through connect, reconnect, and revoke at x.com/i/money/settings/connections, and what each failure message means.
Deploy Alibaba Cloud official tech solutions. Trigger when the user mentions an Alibaba Cloud solution, pastes a solution URL (aliyun.com/solution/tech-solution/...), or wants to deploy an official solution template. Covers both Terraform module deployment and CLI step-by-step execution paths
This skill should be used when users need help analyzing content analytics data, creating reports, identifying trends, calculating ROI, or providing content optimization recommendations. It activates when users ask analytics questions, request reports, need performance analysis, ROI calculations, trend identification, or content optimization recommendations.
Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then work the frontier one ticket per session until the way is clear, and hand the collapsed decisions to /launch as a mission brief. Wayfinding, not building: it produces decisions, never deliverables.
Use when SwiftUI view debugging requires systematic investigation - view updates not working after basic troubleshooting, intermittent UI issues, complex state dependencies, or when Self._printChanges() shows unexpected update patterns - systematic diagnostic workflows with Instruments integration
Use when debugging navigation not responding, unexpected pops, deep links showing wrong screen, state lost on tab switch or background, crashes in navigationDestination, or any SwiftUI navigation failure - systematic diagnostics with production crisis defense
Expert knowledge for Azure Bastion development, including best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations, and coding patterns. Use when configuring Bastion for AKS private clusters, VM scale sets, Entra ID authentication, hub-and-spoke VNets, or IP-based cross-VNet access, or for other Azure Bastion development tasks. Not for Azure Virtual Network (use azure-virtual-network), Azure Virtual Network Manager (use azure-virtual-network-manager), Azure VPN Gateway (use azure-vpn-gateway), or Azure Firewall (use azure-firewall).
Expert knowledge for Azure Cloud Services development, including troubleshooting, best practices, decision-making, limits and quotas, security, configuration, and integrations and coding patterns. Use when managing Guest OS versions, Key Vault certs, .csdef/.cscfg configs, autoscale rules, PowerShell automation, or other Azure Cloud Services development tasks. Not for Azure Virtual Machines (use azure-virtual-machines), Azure App Service (use azure-app-service), Azure Kubernetes Service (AKS) (use azure-kubernetes-service), or Azure Functions (use azure-functions).
Expert knowledge for Azure Local development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when deploying Azure Local racks/SDN, Arc VMs, SFF setups, disconnected Arc gateway, or NVIDIA GPU workloads, and other Azure Local related development tasks. Not for Microsoft Foundry Local (use microsoft-foundry-local), Azure Stack Edge (use azure-stack-edge), Azure Kubernetes Service Edge Essentials (use azure-aks-edge-essentials), Azure IoT Edge (use azure-iot-edge).
Expert knowledge for Azure Managed Redis development including troubleshooting, best practices, decision making, architecture & design patterns, security, configuration, integrations & coding patterns, and deployment. Use when using Azure Managed Redis SDKs, Entra ID auth, clustering/sharding, persistence, or geo-replication, and other Azure Managed Redis related development tasks. Not for Azure Cache for Redis (use azure-cache-redis).
Expert knowledge for Azure SignalR Service development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring SignalR modes, auth/network setup, scaling multi-region hubs, Event Grid/API Mgmt integration, or live tracing, and other Azure SignalR Service related development tasks. Not for Azure Web PubSub (use azure-web-pubsub), Azure Service Bus (use azure-service-bus), Azure Event Hubs (use azure-event-hubs), Azure Relay (use azure-relay).
Analyze and compare construction bids, proposals, estimates, and subcontractor quotes. Assigns line items to UniFormat II headings, compares absolute cost and cost per unit, produces a leveling spreadsheet (CSV or Excel) and a concise PDF report with scope overlap matrix, contractual term comparison, and a recommendation. Use when the user provides one or more bid documents (PDFs, spreadsheets, or text) to analyze or compare, or asks to "level bids", "compare bids", "bid tabulation", "bid comparison", "bid analysis", or "analyze this bid/quote/proposal" for a construction project.
Audit a website or UI and de-AI it — find the patterns that make it look template-generated (in both design and copy) and return specific, prioritized fixes that push it toward editorial, premium, human-crafted. Reviews layout, color, type, spacing, motion, accessibility, AND the words. Use after building or generating any frontend, or when a site looks "fine but generic" and you can't say why.
Respond to phishing incidents by analyzing reported emails, extracting indicators, sandboxing URLs/attachments, assessing credential compromise, quarantining malicious messages organization-wide, and remediating affected accounts. Use when investigating a reported phishing or credential-phishing email, a suspected spearphishing incident, or when a mailbox-wide purge and account remediation is needed.
Guided flow creation wizard. Use when the user wants to create a new flow interactively. Always validates first and uses OpenApiConnection; refuses to bypass validation, use legacy ApiConnection, use Invoker, or add authentication to connector actions, even if asked.
Read and publish on CSDN (blog.csdn.net) with the user's own login cookies (BYOC) — list their published articles with view/like/comment stats, inspect one article, and publish a new article. Use when the user mentions CSDN, "我的 CSDN 文章", reading their article stats (阅读/点赞), or publishing/发文 to CSDN.
Build Model Context Protocol (MCP) servers in C#/.NET against the current ModelContextProtocol 2.x NuGet packages. Helps with cases the model gets wrong without guidance — stale versions (0.x preview or 1.x-era defaults), the v2 stateless-by-default HTTP flip, the 2026-07-28 spec deprecations (roots/sampling/logging), MCP Apps and Tasks extension packages, elicitation URL mode, per-session HTTP wiring, OAuth and reverse-proxy deploy specifics, and debugging MapMcp / STDIO / Streamable-HTTP errors. Also covers STDIO and Streamable HTTP transports (SSE is deprecated), tools, prompts, resources, completions, and a basic .NET MCP client. Trigger when the user says or implies any .NET MCP server work: ModelContextProtocol, McpServerTool, MapMcp, WithStdioServerTransport, “MCP server in C#”, “MCP tool in dotnet”, “expose this as MCP”, or names a primitive (prompt/resource/elicitation/MCP App) in a .NET context. Skip for MCP work in other languages.
Perform evidence-driven, multi-subsystem audits of real codebases to find correctness bugs, race conditions, security gaps, stale documentation, dead code, and production-readiness risks. Use when asked to audit a system end-to-end, verify agent-written code before shipping, analyze a subsystem for correctness across multiple modules, or produce a structured risk report for a real implementation. Prefer other skills for a single isolated bug, a proposal or document review, or a dedicated dead-code cleanup
Help fantasy players make start/sit, waiver, streaming, trade, draft and keeper decisions using current player news, usage, matchups and their league's scoring. Use for choosing between players, finding pickups, evaluating a deal or filling a roster need, even without an explicit research request. Excludes generic sports scores, betting and changing league rosters.
Build serverless TypeScript functions on Zavu Cloud — declare agents + tools in code with defineAgent / defineTool, deploy with `npx zavudev deploy`, debug with `npx zavudev agents executions`. Use this skill whenever the user wants code-driven AI agents, custom tool handlers, or event-driven business logic.
Run a git merge, PR merge, conflict resolution, or rollback safely — readiness-checked and BACKED UP before anything touches shared history. Assesses branch/CI/review state and conflict risk, tags a backup point before non-trivial merges, resolves conflicts without dropping either side (regenerating lockfiles, not hand-editing), validates the result, then cleans up or rolls back — routing to the worktree specialist when isolated execution is safer. Never claims success with unresolved conflicts or failing validation, prefers `git revert` over `reset` on shared branches, and requires explicit confirmation before destructive rollback, force-push, or branch deletion. Use only when the user explicitly asks to merge, resolve conflicts, or roll back.
Idiomatic Go design patterns: functional options, builder, factory, strategy, middleware chain, pub/sub, and other patterns adapted for Go's type system. Use when: "design pattern", "functional options", "builder pattern", "factory pattern", "strategy pattern", "middleware chain", "option pattern", "how to structure this". Not for: interface design (go-interface-design), package layout (go-architecture-review), concurrency patterns (go-concurrency-review).
Expert-level toolkit for modular Godot 4.7+ CLI automation and headless build orchestration. Use when you need to: (1) Build complex scene trees or UI layouts programmatically, (2) Automate expert 3D asset pipelines (glTF -> Collision), (3) Optimize procedural geometry headlessly (CSG -> Static Mesh), or (4) Engineer production-grade CI/CD pipelines. Set GODOT_PATH env var for custom engine location. Keywords: Godot CLI, headless, CI, export, builder, 4.7.
Initialize a Harness Engineering framework in the current project. Use when user says 'harness', 'init harness', 'initialize framework', 'setup harness engineering', '/harness', or wants to set up a Plan-Build-Verify development workflow with specialized agents (planner, generator, evaluator). Creates CLAUDE.md, agent definitions, command templates, hooks, and documentation structure for autonomous AI-driven development
Minimal 8-slide arrow-key keynote — each slide has its own solid-color background (indigo / cream / crimson / emerald / gray / purple / white / charcoal), coordinated colors, a 160px display title separated by a 4px short, thick accent line, a Mono list with arrow → prefixes, ← → kbd hints at bottom left and the slide number at bottom right, with generous breathing room. Ideal for keynotes, launches, and public talks where “there’s something to say but not much to show”.
Red-amber warning deck — top/bottom 45° red-and-black hazard stripes, red strikethrough negative titles, L1/L2/L3 green/amber/red tier cards, dot-status alert boxes, policy-yaml code blocks (red left border + bad keyword highlights), red-and-green checklists, Q1 incident stacked bar chart. Suitable for safety / risk / incident reviews / red teaming / pre-launch AI reviews / policy-as-code.
White-background editorial-style deck — pure white background + 10-color rainbow bar at the top, 80–110px display titles, purple→blue→green→orange→pink gradient text, macaron soft-card group (pink/purple/blue/green/orange), black .focus pill with white text, oversized quote block. Also suitable for both Xiaohongshu posts and widescreen PPTs.
Use the Hyper CLI to run Hyper marketing skills from a terminal. Use when the user wants to use `hyperai`, inspect live tool schemas, run a tool by its canonical name, switch connected accounts, or run marketing tools outside an MCP-native agent host.
A panel of 66 investing greats. Given a stock’s dimensions.json and raw_data.json, 66 investors each score it using their own methodology and output a Pydantic Signal (signal/confidence/score/verdict/comment). Covers nine schools: classic value, growth, macro hedge, technical trend, Chinese value, A-share momentum trading, quantitative systems, tech leaders, and AI positioning hunters. Use when the user asks for “the panel,” “what do 65 investing greats think,” “would [someone] buy it,” or “run an investor vote.”
In a project with a .keep-the-why, or when asked about Keep the Why or to set it up, extract and preserve the reasoning code cannot explain — decisions, rejected alternatives, workarounds, incidents, constraints — plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) — only why. Also the place for questions about how this skill works, complaints, feedback and settings changes about it. Anywhere else — no .keep-the-why, no such request — this skill is neither used nor offered nor named, not even in a closing offer to record something.
Local and self-hosted text-to-speech with Kokoro, the ~82M-parameter open-weight (Apache 2.0) model by hexgrad. Use when synthesizing speech offline, on-device, in the browser, or on your own server without per-character API cost — for high-volume narration, audiobooks, privacy-constrained pipelines, and prototyping. Covers running Kokoro via the Python `kokoro` package, ONNX / kokoro-js in the browser, and the OpenAI-compatible Kokoro-FastAPI wrapper; picking voices and language codes; blending voices; chunking long text; controlling pronunciation via misaki/espeak-ng; and judging when Kokoro is the right tool versus when its lack of voice cloning, narrow emotional range, and weaker non-English quality mean you should reach for a hosted or larger model instead. Not for voice cloning, expressive/emotional character performance, or high-fidelity multilingual work — say so and route elsewhere.
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.