Skills
99,951 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when the user asks to implement, execute, or complete tasks in section `14. Tarefas` of `specs/{id}-{slug}/spec.md`, create the code defined by the single source of truth, continue the next ready task, or finish the feature. Also use when an automatic transition starts or resumes delivery. Use for production; for creating tests only, use specsfy-06-tdd-bdd, and for decomposition only, use specsfy-05-tasks.
When the user wants to improve their ability to use narratives and case studies to make benefits tangible and memorable. Also use when the user mentions "telling stories," "case studies," "customer examples," "narrative selling," "making it relatable," or "show don't tell."
Manage a task backlog through the tasks-axi CLI - add, list, show, start, and complete tasks; track blocked-by dependencies, structured holds, and a ready queue; prune and normalize a hand-editable backlog.md. Use whenever a task touches backlog or task state: filing or dispatching work, recording a PR or report on completion, finding dispatchable or held work, or trimming the Done list.
Core rendering pipeline for three.js using WebGLRenderer and WebGPURenderer, canvas sizing, device pixel ratio, color space and tone mapping, output encoding, WebGL/WebGPU render targets, Info statistics, and addon overlay renderers (CSS2D/CSS3D/SVG). Use when tuning the draw loop, performance, or switching WebGPU vs WebGL; for EffectComposer passes use threejs-postprocessing; for XR session lifecycle use threejs-webxr; for shader graphs use threejs-node-tsl.
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. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Parses Kubernetes API server audit logs (JSON lines) to detect exec-into-pod, secret access, RBAC modifications, privileged pod creation, and anonymous API access, and builds SIEM detection rules from the event patterns. Use when investigating a suspected cluster compromise, reconstructing what an attacker did through the API server, or writing Kubernetes-specific detection content. Keywords: audit policy, audit log, kube-apiserver, exec into pod, RBAC change, anonymous access, detection rules. Do not use for syscall-level detection inside a running container - use detecting-container-runtime-threats-with-falco.
Deploy Next.js to Cloudflare Workers with full App Router, Pages Router, ISR, and SSG support. Load when creating Next.js projects for Workers, migrating from Vercel/next-on-pages, configuring caching (R2/KV/D1), accessing Cloudflare bindings via getCloudflareContext, or fixing bundle size issues.
Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
Create distinctive, production-grade static sites with React, Tailwind CSS, and shadcn/ui — no mockups needed. Generates bold, memorable designs from plain text requirements with anti-AI-slop aesthetics, mobile-first responsive patterns, and single-file bundling. Use when building landing pages, marketing sites, portfolios, dashboards, or any static web UI. Supports both Vite (pure static) and Next.js (Vercel deploy) workflows.
Build code-first notification workflows with @novu/framework. Use when defining workflows in TypeScript (Zod / JSON Schema / Class Validator), composing channel steps (email, SMS, push, chat, in-app) with action steps (delay, digest, custom), exposing Step Controls for non-technical teammates, rendering React/Vue/Svelte Email templates, hosting the Bridge Endpoint inside Next.js, Express, NestJS, Remix, Nuxt, SvelteKit, H3, or AWS Lambda, syncing to Novu Cloud via CLI / GitHub Actions, securing production with HMAC, or implementing translations, hydration, multi-channel orchestration, and LLM-powered notification logic in code.
Integrate Novu's in-app notification inbox into web applications. Supports React, Next.js, and vanilla JavaScript. Includes the Inbox component (bell icon + notification feed), composable components (Bell, Notifications, InboxContent, Preferences), headless hooks, branded theming, custom render props, multi-tenancy via contexts, tabs, localization, and HMAC security. Use when adding an in-app notification center, bell icon, notification feed, real-time notification updates, or building a personalized and branded notification experience
Search and query past Claude Code, Codex, Kimi Code, Kiro, OMP, and Pi session history. Reactive: when the user asks "how did I fix X", "what did we do last time", "find the session where", "上次怎么修的", "之前的session", "历史记录". Proactive: when the user references past work you lack context for, when you're about to modify a file with complex edit history, when the user says "继续之前的" or "continue where we left off", or when understanding prior decisions would improve your current response. Memory: when the user says "记住这个", "remember this", "写入记忆", "save this conclusion", or when you determine a retrieval result contains a conclusion worth persisting.
Generate professional product packaging designs using each::sense AI. Create box designs, food packaging, cosmetic containers, beverage labels, supplement bottles, coffee bags, candle packaging, gift boxes, shopping bags, and product labels.
Playwright browser automation API, web scraping, and tooling. Covers locator strategies, assertions, API testing, stealth mode, anti-bot bypass, authenticated sessions, screenshots/PDFs, Docker deployment, configuration, debugging, and MCP integration with AI agents. Prevents documented errors including CI timeout hangs, extension testing failures, and navigation issues. Use when automating browsers, scraping protected sites, bypassing bot detection, generating screenshots/PDFs, configuring Playwright Test, troubleshooting Playwright errors, or learning Playwright API patterns. For E2E test architecture, Page Object Models, CI sharding strategies, or test organization patterns, use the e2e-testing skill instead
Comprehensive SecOps skill for application security, vulnerability management, compliance, and secure development practices. Includes security scanning, vulnerability assessment, compliance checking, and security automation. Use when implementing security controls, conducting security audits, responding to vulnerabilities, or ensuring compliance requirements.
Use when the user wants to turn an item from `specs/inbox/`, an opportunity, a problem, or an existing item into a backlog item ready for specification, including through an automatic transition. Researches duplicates and references, creates or updates `specs/backlog/`, asks adaptive questions, applies MCR-10, and produces a testable brief. To simply store text without questions, use specsfy-01-inbox; do not use to write spec.md, tasks, tests, or implementation.
Use quando o usuário pede para validar, revisar, auditar ou checar se `specs/{id}-{slug}/spec.md` segue o formato rígido Specsfy/2.0 e está pronto para planejar. Use também quando uma transição automática pedir prova do Definition Gate ou nova validação após correção. Use antes do Ato II. Registre gates na seção 13 do mesmo arquivo; não crie checklist, relatório, plan.md ou outro artefato.
Use when the user requests TDD, BDD, tests derived from the specification's reference Gherkin, traceability between `spec.md` and tests, or a RED-GREEN-REFACTOR cycle. Also use when an automatic transition requests materialization, RED, or test verification. Use to edit sections 11–13 and run tests; `specsfy-07-implement` remains responsible for production tasks in section 14 of the same file.
Use to project milestone status from specs and backlog, identify missing links, suggest adjustments, and update only derived blocks. Do not use to invent product goals, change confirmed exit criteria, or complete milestones without human validation.
three.js cameras: Camera base, PerspectiveCamera, OrthographicCamera, CubeCamera, ArrayCamera, StereoCamera; projection matrices, aspect, FOV, orthographic frustum sizes, near/far planes, and dynamic environment maps with CubeCamera. Use when placing views, rendering reflections, or multi-view splits; for XR projections and eye matrices use threejs-webxr; for post pass camera tricks use threejs-postprocessing alongside threejs-renderers
three.js Scene graph root object, linear Fog and exponential FogExp2, Scene.background for solid colors or textures, and high-level environment background concepts that tie to PMREM and loaders in other skills. Use when configuring world container, atmospheric fog, or background; for HDR env map file loading use threejs-loaders; for GPU texture settings after load use threejs-textures; for tone mapping use threejs-renderers
Helps outline and draft UGC-style scripts for paid social ads. Use when the user has an ad concept and wants to write a script for creator content. Triggers: "UGC script", "creator script", "talking head script", "testimonial script", "influencer script", "write a script", "script for TikTok", "script for Reels"
Use as the FIRST action on any research, investigation, or codebase-understanding request — "research X", "investigate X", "look into X", "dig into X", "search X", "explore X", "understand X", "why is this like this" — before Glob, Grep, or Read. Recorded intent lives in Entire checkpoints on the server, not in local files, so an empty or unfamiliar working copy is not a reason to skip it. Routes to the right Entire sub-skill (search, recall, explain, what-happened, replay, teach, review, session-handoff).
Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: “remember this”, “save this”, “note this”, “what did we discuss about...”, “check your notes”, “clean up memories”. Also use proactively when discovering valuable findings worth preserving.
Expert knowledge for Azure Pipelines development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations, coding patterns, and deployment. Use for configuring YAML pipelines, agents and triggers, GitHub-hosted agents, classic-to-YAML migration, Kubernetes/VM deployments, and other Azure Pipelines development tasks. Not for Azure DevOps (use azure-devops), Azure Boards (use azure-boards), Azure Repos (use azure-repos), or Azure Test Plans (use azure-test-plans)
Create distinctive, production-grade static sites with React, Tailwind CSS, and shadcn/ui — no mockups needed. Generates bold, memorable designs from plain text requirements with anti-AI-slop aesthetics, mobile-first responsive patterns, and single-file bundling. Use when building landing pages, marketing sites, portfolios, dashboards, or any static web UI. Supports both Vite (pure static) and Next.js (Vercel deploy) workflows.
Expert patterns for Godot audio including AudioStreamPlayer variants (2D positional, 3D spatial), AudioBus mixing architecture, dynamic effects (reverb, EQ, compression), audio pooling for performance, music transitions (crossfade, bpm-sync), and procedural audio generation. Use for music systems, sound effects, spatial audio, or audio-reactive gameplay. Trigger keywords: AudioStreamPlayer, AudioStreamPlayer2D, AudioStreamPlayer3D, AudioBus, AudioServer, AudioEffect, music_crossfade, audio_pool, positional_audio, reverb, bus_volume
Draws original design-and-coding scenes as SVG cards (480x360) in a framed-panel cartoon style. Identifying traits are a soft pastel card with a periwinkle-violet panel framed in thin navy, outline-only clouds and a pale lavender floor band with dashes inside it; L-shaped corner brackets outside two corners; white speech bubbles, UI cards and bushes that break out over the frame edge; and a semi-real character with a thin navy outline (1.25 px), muted flat fills, navy hair with violet highlights, blush and short paired hatch marks. Covers people working with laptops, screens, UI parts and devices. Use when someone asks for a framed panel, window-frame or picture-frame illustration, pastel violet cartoon, outlined flat character scene, empty-state, onboarding or 404 art, a blog header, a feature spot, a support, about or team page illustration, or a marketing card with a person.
Implement, review, or improve Live Activities and Dynamic Island experiences in iOS apps using ActivityKit. Use when building real-time updating widgets for the Lock Screen and Dynamic Island — delivery tracking, sports scores, ride-sharing status, workout timers, media playback, or any time-sensitive information that updates in real time. Also use when working with ActivityKit, ActivityAttributes, Activity lifecycle (request/update/end), Dynamic Island layouts (compact/minimal/expanded), push-to-update Live Activities, or Lock Screen live widgets.
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.
Graham cigar-butt batch screener — runs Benjamin Graham's NCAV / net-net / defensive-investor hard filters across an index or market universe and returns a ranked candidate list with NCAV ratio, PE, PB, dividend yield, debt coverage, 5y earnings stability, Graham buy price, and a dynamic value-trap warning. Longbridge CLI first; MCP fallback if CLI unavailable; WebSearch fills genuine gaps (PMI, sector outlook). Every figure footnoted to its source. Auto-switches model for banks / insurance / REITs and flags <2y IPOs and suspended names. Triggers: “格雷厄姆筛选”, “格雷厄姆筛股”, “捡烟蒂榜单”, “烟蒂股榜”, “NCAV筛选”, “NCAV排行榜”, “净流动资产筛选”, “防御型投资者筛股”, “撿煙蒂榜單”, “煙蒂股榜”, “NCAV篩選”, “淨流動資產篩選”, “防禦型投資者篩股”, “Graham screen”, “Graham screener”, “NCAV screen”, “net-net screen”, “net-net list”, “cigar-butt screen”, “defensive investor screen”, “liquidation value screen”, “Benjamin Graham screen”.
Write, run, optimize, or troubleshoot DuckDB SQL against MotherDuck, including AI functions such as prompt_jev for in-SQL classification. Use for any SQL that targets MotherDuck, even simple queries, because MotherDuck has its own dialect and naming rules.
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.