Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Design VictoriaMetrics stream aggregation rules to reduce cardinality, sample frequency, or query load. Use whenever the user wants to apply, plan, or troubleshoot stream aggregation (`-streamAggr.config`, `-remoteWrite.streamAggr.config`), asks how to aggregate a high-cardinality metric, mentions downsampling at vmagent, replacing recording rules with stream aggregation, picking the right aggregation output (`total`, `rate_sum`, `sum_samples`, `quantiles`, `histogram_bucket`, etc.), choosing an aggregation interval, deciding where to place vmagent in the delivery pipeline, or whether to scale vmagent for aggregation. Also triggers on "aggregate histograms", "drop labels via vmagent", "reduce ingested samples", "pre-aggregate at vmagent", "stream aggregation accuracy", and "stream aggregation duplicates in cluster".
Use when using Drei helper components with React Three Fiber: controls, environment maps, text rendering, HTML overlays, or performance helpers. Prevents the common mistake of not wrapping useGLTF in Suspense, using wrong Environment preset name, or forgetting makeDefault on controls. Covers 150+ Drei components across controls, environment, text, materials, loaders, performance. Keywords: Drei, @react-three/drei, OrbitControls, Environment, useGLTF, useTexture, Html, Text, Stage, ContactShadows, Instances, helper components, ready-made, quick setup React 3D.
Use when building 3D scenes with React using React Three Fiber (R3F). Prevents the common mistake of mixing imperative Three.js code with R3F's declarative model, creating objects inside useFrame, or forgetting Suspense for loaders. Covers Canvas, useFrame, useThree, useLoader, JSX mapping, event system, performance patterns. Keywords: React Three Fiber, R3F, Canvas, useFrame, useThree, useLoader, @react-three/fiber, 3D React, declarative Three.js, use Three.js with React, JSX 3D components.
Generate cloned narration for the content workspace. Use local IndexTTS2 with the canonical lossless Pluviobyte reference for every local video, voice audition, digital-human narration, and subtitle-ready audio render. Preserve MiniMax only for public-facing articles or tutorials that teach users to connect through the relay service; never use MiniMax for local video production.
Generate AI videos through the 兔子API. Supports models such as Veo, Sora, Kling, and Seedance, with single-video and long-video (multi-segment composition) modes. Use when the user requests video generation, video creation, or a video-generation backend.
Operate the Unity Editor through a local REST API — create, edit and batch-edit GameObjects, components, scripts, scenes, prefabs, assets and materials, run tests — and answer Unity design questions (architecture, script design, patterns) from bundled advisory docs. Use for any Unity Editor task or Unity design question, in any language.
Guide for video analysis and frame-level event detection tasks using OpenCV and similar libraries. This skill should be used when detecting events in videos (jumps, movements, gestures), extracting frames, analyzing motion patterns, or implementing computer vision algorithms on video data. It provides verification strategies and helps avoid common pitfalls in video processing workflows.
Use when the user has 2+ recordings of the same event (each with a `.sync.json` sidecar from wjs-syncing-multicam) and wants them combined into a single MP4 — auto-switching between cams second-by-second on audio energy, with optional picture-in-picture inset. Triggers — “auto-edit multicam”, “做个剪辑”, “切几个机位”, “把这几个视频合成一个”, “combine these angles”, “PiP overlay”.
Use when the user has 2+ video or audio recordings of the same event captured on different devices (cameras, phones, separate audio recorders) and wants them aligned to a single common timeline. Outputs only a lightweight `.sync.json` sidecar per input; original files are never re-encoded. Triggers: "多机位同步", "对齐这几个机位", "match camera timelines", "sync these angles", "audio drift between cameras", "separate audio recorder", "Riverside / Zoom recording that needs to line up"
For releasing or troubleshooting XGENT portal versions from the App repository: frontend dist, backend images, manifest, or first-time onboarding. Submit proposals via release-cli and a release token, and handle CI, pending review, and post-release failures.
Senior accountant and strategic CFO with 20+ years of experience in the tech sector. Use for tax planning, VAT/sales tax compliance, financial forecasting, contractor assessments, or accounting app logic design. Automatically flags tax warnings and savings opportunities. Adapts to the user's jurisdiction by loading the matching reference (e.g. UK tax, persona Inga) from references/.
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.
Use this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer questions about the MaxFrame API, concepts, official examples, and supported pandas APIs; create data processing programs; read and write MaxCompute tables; debug remote or local jobs; and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs or examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.
Yike Storyboard Creation Skill - Complete AI video creation workflow from novel/script to storyboard via conversational interface. Use this skill when users want to create storyboards, produce videos, convert novels/scripts to videos, or generate shot scripts. Trigger scenarios: "storyboard", "novel to video", "shot script", "script parsing", "video creation", "convert novel to video", "generate storyboard".
Expert-level security auditing, compliance, code review, and vulnerability assessment. Use when the user mentions compliance, security review, code review, vulnerability assessment, SOC 2, or GDPR, or when the task involves Audit Types, Audit Frameworks, Audit Process, or Authentication Review.
Use when implementing on-device AI with Apple's Foundation Models framework — prevents context overflow, blocking UI, wrong model use cases, and manual JSON parsing when @Generable should be used. iOS 26+, macOS 26+, iPadOS 26+, axiom-visionOS 26+
Use when implementing haptic feedback, Core Haptics patterns, audio-haptic synchronization, or debugging haptic issues — covers UIFeedbackGenerator, CHHapticEngine, AHAP patterns, and Apple's Causality-Harmony-Utility design principles from WWDC 2021
Expert knowledge for Azure Artifacts development, including troubleshooting, best practices, decision-making, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use for managing feeds, upstream sources, views, .npmrc auth, .artifactignore, GitHub Actions package publishing, and other Azure Artifacts development tasks. Not for Azure DevOps (use azure-devops), Azure Pipelines (use azure-pipelines), Azure Repos (use azure-repos), or Azure Boards (use azure-boards).
Expert knowledge for Azure Container Instances development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, and deployment. Use when configuring ACI networking/IPs, standby pools, Spot containers, GitHub Actions deployments, or secure ACR pulls, and for other Azure Container Instances-related development tasks. Not for Azure Container Apps (use azure-container-apps), Azure Kubernetes Service (AKS) (use azure-kubernetes-service), Azure Virtual Machines (use azure-virtual-machines), or Azure Batch (use azure-batch).
Query browsing history from all synced devices (iPhone, Mac, iPad, desktop). Supports natural language queries for filtering by date, device, domain, and keywords. Uses LLM classification for content categories. Can output to stdout or save as markdown/JSON to Obsidian vault.
Stress-tests business models using Hormozi frameworks to identify scale limitations, bottlenecks, and unit economics gaps. Triggers when a user asks “can this scale,” “what breaks at 10x,” mentions being the bottleneck, wants unit economics reviewed, or asks about business model viability.
Write correct Sarvam AI chat-completion code (Sarvam-105B, Sarvam-30B) — OpenAI-compatible API, streaming, reasoning mode, and the content=None gotcha. Use this skill when building chatbots, Q&A, agents, or Indic LLM features in Python or JS/TS. For a live completion in chat via MCP, use sarvam-mcp instead.
When quota runs out before bed or before leaving, set a one-off local timer that automatically sends a minimal claude -p message after the Claude subscription quota resets, immediately opening a new 5-hour usage window — by the time the user wakes up, much of the new window has already elapsed, effectively gaining a free cooling period. Use when the user says "X hours until quota resets, ping Claude on a timer for me", "I'm going to sleep, ping it at the right time to open a new window", "quota is used up, ping it after the reset", or "set a timer to open a new 5-hour cooling period", or mentions a scheduled ping, pinging Claude, quota ping, opening a window, or automatically sending a message after quota reset. Limited to one-off scheduled tasks and macOS local machine (caffeinate/BSD date); for recurring tasks use /loop or cron, to check when ChatGPT/Codex resets use tibo-reset-codex, and to analyze why quota was exhausted use claude-usage-analyst.
Comprehensive guide for managing Cloudflare DNS with Azure integration. Use when configuring Cloudflare as authoritative DNS provider for Azure-hosted applications, managing DNS records via API, setting up API tokens, configuring proxy settings, troubleshooting DNS issues, implementing DNS security best practices, or integrating External-DNS with Cloudflare for Kubernetes workloads.
Design, analyze, and optimize cold outbound email campaigns for Instantly. Handles end-to-end ICP definition, expert panel scoring (recursive to 90+), sequence copywriting, infrastructure audit, capacity planning, and implementation docs. Use when asked to build cold outbound sequences, optimize cold email, analyze outbound campaigns, build sales sequences, build Instantly sequences, create cold outbound strategies, or design email campaigns. Supports both "start from scratch" and "optimize existing" modes.
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a deployment-settings.json file with per-stage override values. Use when asked to: "configure environment variables", "add env vars", "set up deployment variables", "make site settings environment-specific", "configure ALM variables", "set up env-specific settings", "add deployment settings", "configure per-environment settings"
CSS animation adapter patterns for FrameVideo. Use when authoring CSS keyframes, animation-delay based timing, animation-fill-mode, animation-play-state, or CSS-only motion that FrameVideo must seek deterministically during preview and rendering.
dontbesilent benchmark analysis. Use the five-filter method to find benchmarks worth emulating while filtering out all the noise about “me”. Triggers: /dbs-benchmark, /对标, “帮我找对标”, “我该模仿谁”. Benchmark analysis using dontbesilent's five-filter method. Triggers: /dbs-benchmark, “find me a benchmark”, “who should I copy”.
Manage DingTalk product capabilities, including AI tables, calendar, contacts, documents, bots, tasks, email, meeting notes, AI apps, approvals, logs, and DingTalk Drive. Use when users need to work with spreadsheet data, manage schedules and meetings, look up contacts, send message notifications, handle approval workflows, view meeting-note summaries, create apps, systems, admin backends, or business tools, view daily or weekly reports, or manage DingTalk Drive files.
Email sending integration. Covers Nodemailer (Node.js), Spring Mail (Java), smtplib (Python). Transactional email services: SendGrid, Amazon SES, Resend. Template engines: MJML, React Email. USE WHEN: user mentions "send email", "nodemailer", "SMTP", "SendGrid", "SES", "Resend", "transactional email", "email template", "MJML", "React Email", "spring mail" DO NOT USE FOR: push notifications - use `push-notifications`; SMS - different channel; email parsing/reading
Use when building or reviewing FaasJS plugins and runtime infrastructure: plugin lifecycle hooks including concurrent mount and failed-mount retry behavior, InvokeData mutation, DefineApiInject module augmentation, faas.yaml plugin loading, applyConfig, logger usage, @faasjs/node-utils, loadConfig, loadDotenv, module loaders, and Node-only bootstrap code.
Use when building or reviewing FaasJS React UI, especially @faasjs/ant-design pages, useFaas, useFaasStream, faas requests, CRUD screens, Table faasData, Description faasData, Form faas, conditional FormItem hidden/if behavior, drawers/modals, React hooks, shared state, and React tests.
Asset preprocessing for FrameVideo compositions — text-to-speech narration, Chanjing background music and sound effect downloads, audio/video transcription (Whisper), and background removal for transparent overlays (u2net). Use when generating voiceover from text, downloading BGM or SFX, transcribing speech for captions, removing the background from a video or image to use as a transparent overlay, choosing a TTS voice or whisper model, or chaining these (TTS → transcribe → captions).
SEO/GEO Agent Operations SOP v2 — Rebuilt from real-world operations (analook.com 0→launch, GSC incident, DataForSEO monitoring, gingiris.tools post-migration recovery). What's new in v2: • Step-by-step onboarding (Q1→Q6), multiple choice wherever possible — no big forms • Mandatory daily SEO log — first item is always GSC token status check • Data cross-validation rule: any external metric must come from ≥2 sources before use • Backlink progress tracking (6-week wait → check → alert if not indexed) • New vs. established site strategy matrix (new site <6mo: KD≤20; mature: KD up to 35+) Real incidents baked in: GSC token expired silently for 2 weeks (analook.com), P0 keywords dropped out of Top 100 after domain migration (gingiris.tools), traffic data off by 17× from single-source DataForSEO. Triggers: "SEO agent" | "SEO daily report" | "GSC monitoring" | "DataForSEO" | "GEO agent" | "backlink tracking" | "IndexNow" | "competitor comparison page" | "SEO SOP" | "autonomous SEO" | "GEO triple combo" SEO/GEO Agent 运营 SOP v2 — 基于真实运营经验重写（analook.com 从零建站 + GSC 断档 2 周 + DataForSEO 监控 + gingiris.tools 迁移权重恢复）。 对话式开局、强制日报（GSC token 是第一项）、数据交叉验证铁律、外链进度追踪、新老站区分策略。
Structured logging, distributed tracing, metrics, and health checks for Go services. Covers slog, OpenTelemetry, Prometheus, and observability best practices. Use when: "add logging", "structured logs", "add tracing", "OpenTelemetry", "add metrics", "Prometheus", "observability", "instrument this code". Not for: pprof profiling (go-performance-review), error handling (go-error-handling), health endpoints (go-api-design).
Full-lifecycle B2B SaaS growth, including first-deal blockage diagnosis and pricing commitment validation. The complete path from PMF validation to $10M ARR. Covers PLG / SLG selection, customer interviews, affiliate marketing, channel partnerships, and enterprise sales. Integrates cases from HeyGen, Deel, Vercel, Supabase, and AWS. Distilled from gingiris-b2b-growth.
Adapt a supplied article, draft or text into requested social formats with source attribution and voice checks. Use for X posts or threads, LinkedIn posts or carousels, Xiaohongshu notes and DEV/Zenn drafts; deliver only requested channels without automatic publication. Suitable for content repurposing, social media adaptation and multi-platform drafts.
TỰ BẢO TRÌ framework overstack trên máy user (self-maintain) — migrate llmwiki cũ lên harness (case B) hoặc update bản mới (case C). MỘT lệnh `install-harness.sh --self-heal` tự cài + tự backfill nợ wiki (Origin/index/OKF) + refresh bản đồ năng lực + health-check trong 1 process, không vòng lặp re-run. Trigger: "tự bảo trì framework", "self-maintain", "migrate harness", "update harness", "update overstack", "nâng cấp harness", "cài harness vào dự án cũ", "/harness-update".
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.