Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Translate PRDs into detailed UX specifications, including user flows, screen descriptions, components, and interaction patterns. Use when a user has a PRD and needs to define the concrete UI/UX before generating development prompts. Bridges product requirements and implementation details.
Generate videos via Venice. Covers the async /video/quote + /video/queue + /video/retrieve + /video/complete loop, text-to-video, image-to-video, first/last-frame transitions, video-to-video and upscale, audio input, reference images / videos / audio (R2V) and their per-model caps, Kling elements and scene images, Seedance source-matched edit/extend and omni_reference_task_type, H3 Max Multi-Angle camera_trajectory, and replayed async failures. POST /video/transcriptions is retired (410) — use chat completions with video_url.
Image generation and presentations. Use when the user asks for images such as logos, icons, app assets, diagrams, flowcharts, architecture diagrams, patterns, textures, photo edits, or restorations, or needs a presentation or slide deck. Covers nanobanana CLI for image generation and Slidev for presentations.
This skill provides expert-level guidance for VS Code extension development. Use when implementing new extension features, debugging extension code, designing WebView UIs, implementing Language Server Protocol features, or optimizing extension performance. Covers activation events, contribution points, VS Code API patterns, security best practices, testing strategies, and publishing workflows.
Configure WayAI hubs, agents, tools, channels, skills, states, evals, automations, and analytics, plus the Data surface (bases, record types, records, relationships, files, toolsets), and live AI voice calls. Use when creating or editing a hub or hub config; adding/configuring agents, tools, channels, connections, teams, kanban, states, skills, eval scenarios or journeys, automations (scheduled or event-triggered sends and agent runs, webhook-started tasks), voice calls; running analytics or evals; annotating conversation outcomes; reviewing or editing workspace YAML (hub.yaml, agents/*.yaml, base.yaml, record-types/*.yaml) or agent instruction Markdown; designing a base schema, upserting or querying records, linking records with relationships, storing versioned files or attachments, wiring inbound webhooks, triggers or external sources, building MCP toolsets and Actions, scoping base API tokens, or seeding eval fixtures; using the wayai CLI (push, pull, publish, page new, send-message, conversations, sync-skills, create-credential, update-credential, analytics, analytics sql, run-eval, eval capture, eval call, evals sql, org, init, communities, bases, records, record-types, relationships, files, toolsets, actions, triggers, inbound-webhooks, seed, dimensions, access explain); setting up access dimensions (x-access on a record type, an organization's dimensions and values, the values each person, hub and agent may reach, report mode); managing an organization's communities (list, join link, stats, the access list of an invite-only community; settings including who may join, rules, rooms and courses as code; moderators, moderation and what a community's members see); analyzing LLM token/cost spend per message, model, agent, or credential; interpreting WayAI platform terminology (pilot/copilot, preview/production, kanban statuses, AI modes, agent roles, journeys, base, record type, promotion, external_id); or answering how people use the app: end users (agents, tasks, files, the mobile and desktop apps) and support teams (the inbox, claim, transfer, close, the board, Copilot suggestions, consults).
Website replication/cloning methodology. USE WHEN the user says to replicate or clone a website, clone website, copy a site, imitate a site, make one based on this site, reproduce a site, recreate a webpage effect, download this site and adapt it, or replicate an interaction/WebGL/Canvas/Three.js effect. Provides a portable decision tree for “get the actual source first → determine the path → reverse-engineer and break it down → set up the project → replace the content,” covering three branches: static sites, React/Vue/Next content sites, and WebGL-Canvas-heavy frontend sites. Requires checking any executable code in secondhand AI analysis.
Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base. Each wiki is a folder of markdown pages with provenance, plus a shadow FTS5 index so any session can recall it. Use when the user says "start a wiki", "add to wiki", "compile a page", "wiki on X", or wants a long-lived knowledge base on a topic, paper, product, person, project, or codebase.
Search the user's wiki for stored knowledge. Use when the user asks “what do I know about X” or “find Y in the wiki,” before doing external research the wiki may already cover, or when stored context could help the current task and the user hasn't asked—offer once.
Create or update content in the user's wiki—and set it up if none exists yet. Use when the user says “update wiki,” “sync project,” “save this,” “capture this,” “store this research,” “set up my wiki,” “create a wiki,” or “set up a wiki for this project”; wants to distill knowledge from a project, conversation, or research session; or wants to adopt an existing folder of notes as a wiki. When a session produces durable knowledge worth keeping, offer once at a natural wrap-up—never per turn.
Use when exporting or deploying Ultralytics YOLO models in Platform or code — the Platform Export tab and yolo export/model.export() for ONNX, TensorRT, CoreML, Core AI, OpenVINO, LiteRT, NCNN, ExecuTorch, and NPUs (RKNN, QNN, Hailo, Ascend, IMX, Axelera, DeepX, Xilinx), FP16/INT8 quantization, benchmarking, and non-Python runtimes. For inference with .pt weights or Platform endpoints, see yolo-inference.
Set up, refresh, run, and diagnose ZotLit's Native Pandoc Workflow with a user-installed Pandoc CLI. Use when a user wants native Pandoc to convert an Obsidian Markdown file through the ZotLit Pandoc Integration Pair. Requests for ZotLit's built-in Obsidian export belong to its built-in export command.
Draft, audit, or minimally revise English- or Chinese-language academic prose to reduce formulaic, vacuous, mechanically repetitive, or process-leaking language while preserving claims, evidence strength, logical relations, manuscript-wide terminology identity, document-level pattern variation, and scholarly register. Use for papers, abstracts, grants, cover letters, and reviewer responses when the user asks to de-AI, humanize, audit AI-like phrasing, or rewrite text without changing meaning. English is primary; Chinese is supported. Not for detector evasion, policy circumvention, pure translation, non-academic copy, or adding facts, citations, examples, or author experiences that the source does not contain.
Add Wasp's built-in features to your app: auth, email, jobs, and more. These are full-stack, batteries-included features that Wasp handles for you. Use when the user wants to add meta tags, authentication (email, social auth providers), email sending, database setup, styling (tailwind, shadcn), or other Wasp-powered functionality
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to “open a website”, “fill out a form”, “click a button”, “take a screenshot”, “scrape data from a page”, “test this web app”, “login to a site”, “automate browser actions”, or any task requiring programmatic web interaction.
Azure Kubernetes Service (AKS) Automatic mode and 2025 platform features. Proactively activate for: (1) AKS Automatic (managed Kubernetes, zero operational overhead), (2) Karpenter-based autoscaling on AKS, (3) NodePool CRD usage, (4) HPA, VPA, and KEDA on AKS, (5) workload identity and Microsoft Entra integration, (6) AKS billing models (Automatic vs. Standard), (7) AKS 2025 cluster defaults (RBAC, Azure CNI overlay, Cilium), (8) AKS upgrade and version management, (9) GitOps on AKS (Flux, ArgoCD), and (10) AKS observability (Azure Monitor for containers, Managed Prometheus). Provides an AKS Automatic vs. Standard comparison, Karpenter setup, workload identity recipes, KEDA scaler patterns, and an end-to-end AKS Automatic deployment guide.
Debug live Azure Kubernetes Service (AKS) incidents with a read-only, evidence-first investigation. WHEN: pod crashes or Pending, CrashLoopBackOff, OOMKilled, ImagePullBackOff, node NotReady, DNS or ingress failure, connectivity timeout, network policy, SNAT exhaustion, node-pool scaling blocked by QuotaExceeded or InsufficientVCPUQuota, upgrade stuck, spot or zone disruption, a bare VMExtensionProvisioningError or AllocationFailed wrapper, an uncataloged capacity symptom, or “investigate my AKS cluster”. DO NOT USE FOR: packet capture (use aks-network-capture); GPU or model-serving issues (use aks-gpu-inference); cluster creation or provisioning (use azure-kubernetes); cost (use cost-analysis from the optional azure-cost plugin); pod rightsizing (use azure-kubernetes); a fully qualified documented AKS signature with every required nested qualifier (use aks-known-issues); standalone failures on non-AKS Azure resources (use azure-diagnostics). Unqualified errors and open-ended incidents stay here only for AKS.
Inspect ECS instance health, detect anomalies in memory, disk, CPU, load, and resource leaks, and automatically trigger deep diagnosis when critical memory issues are detected. Suitable for routine inspections, troubleshooting, and risk warning scenarios. Trigger keywords: SysOM, inspection, instance diagnosis, memory_usage_rate, memory usage.
Alibaba Cloud ECS File Backup Essential Edition (ECS文件备份基础版). One-click activation, daily automatic backup, 30-day file recovery, and a 100 GiB free quota. Trigger words: ECS file backup, HBR essential edition, Cloud Backup essential, file deletion recovery, free backup quota, ECS data protection, lightweight backup, affordable ECS backup. Exclude: ECS database backup, ECS full-machine backup, full-machine clone, cross-region backup, cross-account backup, KMS-encrypted backup.
Guidance for designing secure APIs on Azure - authentication, authorization, gateway controls, input validation, rate limiting, secret management, and runtime threat detection - aligned to OWASP API Security Top 10 and Azure API Management. WHEN: API security design, secure API, OWASP API Top 10, API authentication, API gateway security, rate limiting, validate JWT, protect backend API, API Management security policies, secure API architecture, BOLA, BFLA. DO NOT USE for general application security or web app design (use security-architecture / threat-modelling) or for API runtime detection only (use defender-for-apis).
Use when users ask about products, APIs, SDKs, models, error codes, examples, or usage for 火山方舟, BytePlus ModelArk, or 字节云方舟 sites and need to find, verify, or cite the latest official documentation. Also use to read official documentation URLs provided by users, compare multiple documents, or add official support to code and troubleshooting conclusions. Choose among documentation MCP, llms.txt, Markdown mirrors, or HTML content based on the capabilities available for the target site, and preserve verifiable sources.
Debug and find the root cause of AscendC operator precision issues. Use when an operator fails precision tests (allclose fails, results are off, output is all zeros/NaN, etc.). Workflow: analyze error distribution → review error-prone code → isolate experiments → instrument with printf/DumpTensor → verify the fix. Keywords: precision debugging, precision issues, inconsistent results, error localization, allclose failure, output deviation, NaN, all zeros, precision debug.
Edits raw recordings into videos for social media using Remotion. Best for Instagram Reels (9:16), but also suitable for other platforms like TikTok, LinkedIn, and YouTube (including 16:9). Use for any video edit, caption, title, graphic, overlay, transition, or animation, or to copy the style of a video.
How to author, edit, and adapt PostHog Signals scouts—the scheduled agents that scan a project and emit findings into the Signals inbox. Use when a user wants to customize a canonical scout for their own setup (narrow its scope, retune its thresholds, add disqualifiers), tweak a scout's schedule or dry-run posture, or write a brand-new scout from scratch for a specific use case (a custom event, a product surface no canonical scout covers). Covers the scout SKILL.md anatomy, the emit contract, the dedupe + scratchpad-memory conventions, the per-team skills-store path vs the canonical in-repo path, and the emit-and-inspect test loop (with dry-run as an optional safety net). Trigger on “write/edit/customize a signals scout,” “new scout for X,” “tune my scout schedule,” “make a scout that watches <event>.”
Expert knowledge for Azure AI Immersive Reader development including best practices, limits & quotas, security, configuration, and integrations & coding patterns. Use when tuning read-aloud/translation, storing user prefs, Entra auth setup, JS SDK integration, or language support, and other Azure AI Immersive Reader related development tasks. Not for Azure AI Language (use azure-language-service), Azure AI Speech (use azure-speech), Azure Translator (use azure-translator), Azure AI services (use microsoft-foundry-tools)
Expert knowledge for Azure Import Export development including troubleshooting, limits & quotas, and security. Use when setting CMK via Key Vault, checking drive limits, validating prerequisites, or debugging Import/Export job failures, and other Azure Import Export related development tasks. Not for Azure Data Box (use azure-data-box-family), Azure Blob Storage (use azure-blob-storage), Azure Files (use azure-files).
Expert knowledge for Azure Open Datasets development including limits & quotas. Use when handling non-Spark dataset downloads, throttling behavior, quota limits, retry logic, or rate-limit workarounds, and other Azure Open Datasets related development tasks. Not for Azure Data Explorer (use azure-data-explorer), Azure Synapse Analytics (use azure-synapse-analytics), Azure Databricks (use azure-databricks), Azure Machine Learning (use azure-machine-learning).
Expert knowledge for Azure Osconfig development including troubleshooting, security, configuration, and integrations & coding patterns. Use when running OSConfig via IoT for commands/networking, SSH Posture Control, agent health, or Windows security baselines, and other Azure Osconfig related development tasks. Not for Azure Update Manager (use azure-update-manager), Azure Automation (use azure-automation), Azure Policy (use azure-policy).
Expert knowledge for Azure Payment Hsm development including troubleshooting, best practices, decision making, architecture & design patterns, security, and configuration. Use when configuring Payment HSM VNets/peering, FastPath, payShield Manager access, SKUs, HA/DR topologies, or traffic routing, and other Azure Payment Hsm related development tasks. Not for Azure Cloud Hsm (use azure-cloud-hsm), Azure Dedicated HSM (use azure-dedicated-hsm), Azure Key Vault (use azure-key-vault), Azure Security (use azure-security).
A professional Four Pillars of Destiny charting and interpretation skill. Trigger when users mention Bazi, the Four Pillars, the Heavenly Stems and Earthly Branches, Day Master, Ten Gods, luck cycles, favorable elements, chart structure, or analysis of the Five Elements and natal chart. Also applies when users want to understand their fate, personality, career, marriage, or finances and explicitly request or imply the Bazi system. Includes full charting, structure assessment, Ten Gods analysis, and luck-cycle projections.
Builds remote MCP (Model Context Protocol) servers on Cloudflare Workers with tools, OAuth authentication, and production deployment. Generates server code, configures auth providers, and deploys to Workers. Use when: user wants to "build MCP server", "create MCP tools", "remote MCP", "deploy MCP", add "OAuth to MCP", or mentions Model Context Protocol on Cloudflare. Also triggers on "MCP authentication" or "MCP deployment". Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
Facilitates structured roleplay, debate, and synthesis to resolve decisions with multiple legitimate perspectives and inherent tensions. Surfaces assumptions that single-viewpoint analysis would miss and integrates competing priorities into coherent recommendations. Use when stakeholders have competing priorities (growth vs. sustainability, speed vs. quality), need to pressure-test ideas from different angles, explore tradeoffs between incompatible values, or synthesize conflicting expert opinions into coherent strategy.
Azure Container Apps with GPU support, serverless capabilities, and Foundry Models. Proactively activate for: (1) Container Apps GPU (serverless GPU workloads), (2) Container Apps with Dapr integration, (3) scale-to-zero AI workloads, (4) Container Apps Jobs (one-shot, scheduled, event-driven), (5) Container Apps Foundry Models integration, (6) revisions and traffic splitting, (7) custom domains and managed certificates, (8) ingress and authentication, (9) Container Apps Environment configuration, and (10) Workload Profiles (Consumption vs. Dedicated). Provides a GPU SKU reference, scale rule examples (HTTP, KEDA), Dapr building-block recipes, traffic-splitting patterns, and end-to-end serverless GPU deployment.
Generate HumanSignal Interfaces for Label Studio Enterprise: single-file JSX annotation screens that run in the sandboxed editor-shell iframe. Use when the user asks for a labeling UI, annotation screen, Document AI interface, data review workflow, or conversion of a React/Claude Design mockup into a Label Studio interface.
Cron and scheduled task management. node-cron, cron expressions, Spring @Scheduled, APScheduler (Python), and distributed scheduling patterns. USE WHEN: user mentions "cron", "scheduled task", "cron job", "node-cron", "@Scheduled", "APScheduler", "periodic task", "crontab" DO NOT USE FOR: job queues with workers - use `job-queues`; one-off delayed tasks - use `job-queues`
Build a panel of your real buyer personas (from a deep scan of any tools you allow it to connect to) and have them debate any decision you bring — a marketing launch, a price increase, a new product, a positioning change, a feature cut. Returns a structured debate, the strongest objections, and a clear recommendation. Use when you want your actual customers in the room before you commit.
Data dashboard and admin panel patterns for information-dense interfaces: app shell layout, KPI tiles, chart selection, data tables, status badges, real-time indicators, and responsive behavior. Use when the user asks to "build a dashboard", "create an admin panel", "design analytics", "make a data view", "build a settings page", "create a table view", "design a CRM", "build an internal tool", or any data-heavy interface work. For general components use ui-design; for marketing KPI/feature cards use card-design; for theming details use dark-mode.
Use this skill when the user is deploying or operating the DOCA Argus Service—the packaged BlueField-side runtime-security container that watches the BlueField and attached host for suspicious activity, integrity violations, and operational anomalies, and forwards findings to a SIEM (Splunk / ELK / Sentinel / syslog). Covers the four-axis config (detection policy, forwarding, sampling, host coverage), running the NGC container on BlueField Arm, and wiring the forwarder. Trigger even without "DOCA Argus" by name—typical implicit phrasings: "container green but no findings arrive", "false-positive flood in Splunk", or "runtime security on a fleet of BlueField-3s". Refuse and route elsewhere for installing DOCA, SIEM-side ingest stanzas, pre-baked detection-rule packs, and metrics observability (DOCA Telemetry). Argus is NVIDIA's currently promoted runtime-security framework, superseding the older App Shield library; name it first for new runtime-security work.
Load environment variables from a .env file into process.env for Node.js applications. Use when configuring apps with secrets, setting up local development environments, managing API keys and database uRLs, parsing .env file contents, or populating environment variables programmatically. Always use this skill when the user mentions .env, even for simple tasks like "set up dotenv" — the skill contains critical gotchas (encrypted keys, variable expansion, command substitution) that prevent common production issues.
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.