Skills
98,284 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Expert blueprint for console platforms (PlayStation, Xbox, Nintendo Switch) covering controller-first UI, certification requirements (TRCs/TCRs), platform services (achievements, cloud saves), and performance compliance. Use when targeting console releases or implementing gamepad-only interfaces. Keywords: console, PlayStation, Xbox, Switch, TRC, TCR, certification, controller, gamepad, achievements.
Expert blueprint for VR platforms (Meta Quest, PSVR, SteamVR, Pico), covering the XR toolkit (OpenXR), comfort settings (vignetting, snap turning, teleportation), motion controls, hand tracking, and 90+ FPS requirements. Use when targeting VR headsets or implementing immersive 3D experiences. Keywords: VR, XR, OpenXR, Meta Quest, motion sickness, comfort, locomotion, XRController3D, foveated rendering.
Integrates Power Pages Web API into a site's frontend code with proper permissions and deployment. Orchestrates the full integration lifecycle: code integration, table permissions setup, and deployment for Dataverse CRUD operations. Also supports PAC-downloaded non-SPA sites by preferring native Forms, Lists, and Liquid before custom Web API JavaScript. Use when the user wants to add Web API calls, connect to Dataverse, add data fetching to their frontend, or integrate a non-SPA page with Dataverse
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and also on clear knowledge-closeout intent without the name: syncing or tidying project docs/rules/memory after development ("把文档和记忆整理一下", "收尾时把文档同步掉", "docs 和代码对不上了"), stale or conflicting CLAUDE.md/memory, a clean handoff to a teammate or a fresh session, or auditing whether workspace rules are actually followed. Do not trigger for pure coding/refactoring/debugging tasks, tidying data or prose (JSON, 周报, changelog announcements), or a bare "整理" with no project-knowledge context.
Compose new Rails backend pages and refactor existing Rails UI to use premium blocks from templates/application-ui. Use when requests mention ERB views, Rails partials, admin/dashboard screens, Tailwind UI assembly, or replacing custom markup with existing premium blocks while preserving behavior, accessibility, and Turbo/Stimulus hooks.
Build and run AI-generated Bright Data scrapers from the terminal via `bdata scraper create` and `bdata scraper run`. Use this skill whenever the user wants to generate a scraper from a natural-language description, build a custom scraper without writing code, turn a URL + plain-English description into a reusable scraper, run an existing Bright Data collector against a URL, or batch-scrape a list of URLs through one collector. Triggers on phrases like 'build me a scraper for', 'create a scraper that extracts', 'generate a scraper from a description', 'turn this URL into a scraper', 'run this scraper on', 'run my collector', 'batch scrape', 'scrape these URLs', 'scrape a list of URLs', 'competitive pricing table', 'scraper studio', `scraper create`, `scraper run`, `--urls`, `--input-file`, `collector_id`, `automate_template`, or `/dca/`. Covers the AI flow (template create → trigger AI generation → poll progress), the single-URL run flow (async + poll by default, `--sync` for fast pages), the multi-URL batch flow (`--urls` / `--input-file` → one `/dca/trigger` call with array body), and the silent auto-fallback to the batch endpoint when a URL expands past the realtime page limit. Requires the Bright Data CLI.
ALWAYS use this skill when building UI with @govtechsg/sgds-web-component or when a user mentions SGDS or Singapore Design System—even if they don't explicitly ask for help. This is the mandatory entry point for all SGDS development: it guides you to the right skill for setup, components, utilities, forms, theming, page layouts, block templates, and data visualisation. Read this before writing any SGDS application code.
Guide the user to add a data source, connection, or API connector to a Canvas App via Power Apps Studio, then verify and continue. Use when the user asks to add a data source, connection, API, or connector; connect to SharePoint / Dataverse / SQL / Excel / OneDrive / Teams / Office 365; or make similar requests to make new data available to the app. Do not use when the user asks to list or describe existing data sources—call list_data_sources or list_apis directly instead.
Generates CRUD REST API endpoints with request validation, TypeScript types, consistent response formats, error handling, and documentation. Includes route handlers, validation schemas (Zod/Joi), typed responses, and usage examples. Use when building "REST API", "CRUD endpoints", "API routes", or "backend endpoints".
Delegate coding tasks to Codex CLI for execution, or discuss implementation approaches with it. CodeX is a cost-effective, strong coder — great for batch refactoring, code generation, multi-file changes, test writing, and multi-turn implementation tasks. Use when the plan is clear and needs hands-on coding. Claude handles architecture, strategy, copywriting, and ambiguous problems better.
Move content between platforms, domains, or URL structures while preserving SEO equity, user bookmarks, and integrations. Use this skill when planning a CMS migration, replatforming, consolidating sites, changing URL structures, or merging content from multiple sources. Triggers on content migration, replatform, CMS migration, domain migration, URL restructure, redirect map, site merge, content consolidation, migration plan, post-migration drop. Also triggers when planning a launch that involves moving existing content.
CSS animation adapter patterns for HyperFrames. Use when authoring CSS keyframes, animation-delay based timing, animation-fill-mode, animation-play-state, or CSS-only motion that HyperFrames must seek deterministically during preview and rendering.
Analyzes existing code to generate structured learning entries documenting patterns, decisions, and concepts. Works on files, directories, or entire projects. Supports selective (3–5 per file) and exhaustive modes, plus source annotations for fine-grained control.
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling, triggers, ad blockers, and quota/billing scenarios.
Builds .NET UI apps across Blazor (Server, WASM, Hybrid, Auto), MAUI (XAML, MVVM, Shell, Native AOT), Uno Platform (MVUX, Extensions, Toolkit), WPF (.NET 8+, Fluent theme), WinUI 3 (Windows App SDK, MSIX, Mica/Acrylic, adaptive layout), and WinForms (high-DPI, dark mode) with JS interop, accessibility (SemanticProperties, ARIA), localization (.resx, RTL), platform bindings (Java.Interop, ObjCRuntime), and framework selection. Spans 20 topic areas. Do not use for backend API design or CI/CD pipelines.
Godot expert auditor: Aurelius. Exhaustive never-list enforcement and architectural slap-down for Godot 4.7 projects. Use when auditing signal decay, ObjectDB orphans, typed Array/Dictionary slop, material.duplicate batch breaks, export case-sensitivity, Expression.execute risks, or sector never-lists. Keywords: auditor, Aurelius, never-list, signal decay, ObjectDB orphans, typed Array, export case-sensitivity, instance uniforms, PackedScene.get_state.
Expert blueprint for sports games (FIFA, NBA 2K, Rocket League, Tony Hawk) covering physics-based ball interaction, team AI formations, contextual input, and match umpire/score authority. Broadcast framing routes to godot-camera-systems. Use when building soccer, basketball, hockey, racing sports, or arcade sports games. Keywords ball physics, magnus effect, formation AI, team tactics, contextual controls, steering behaviors.
Expert blueprint for stealth games (Splinter Cell, Hitman, Dishonored, Thief) covering AI detection systems, vision cones, sound propagation, alert states, light and shadow mechanics, and systemic design. Use when building stealth-action, tactical infiltration, or immersive sim games requiring enemy awareness systems. Keywords: vision cone, detection, alert state, sound propagation, light level, systemic AI, gradual detection.
Author a working Claude Code hook from a plain-English description of what it should guarantee or do. Describe the behavior (“never let the agent edit my migrations,” “don't stop until the tests pass,” “log every command”); this skill picks the right lifecycle event, writes the hook script, and wires it into .claude/settings.json. Use when you want a deterministic guarantee or automation in your AI Layer and don't want to write the hook by hand. The meta-tool for the hooks primitive.
Interactively explore HOW to approach an intent (a PRD, epic, brief, or free-form idea) and decide the high-level architecture — the approach, stack, libraries, data shape, and risks the intent left open. A working session with a CTO/staff-engineer advisor that asks questions, proposes 2–3 options with trade-offs, recommends a direction with reasoning, and flags what to de-risk with a spike. Produces a high-level architecture decision doc — a separate page linked to the epic in your tracker (Confluence/Jira), or folded into the PRD/epic, or a standalone doc — NOT a task-by-task implementation plan (that comes later, per ticket, with piv-plan-implementation).
Strategic product leadership specializing in product strategy, roadmap development, feature prioritization, and cross-functional coordination. Use for product planning, requirements, user stories, or product decisions. Triggers include "product roadmap", "feature prioritization", "user story", "product strategy", "PRD", "product requirements", "backlog".
Complete reference for all SGDS utility classes with the sgds: prefix. Use when users ask about setup, background-color, text-color, border-color, border-width, border-radius, typography, spacing, grid, dimension, opacity, color-semantics, or any sgds: Tailwind utility class. Also covers Tailwind v4 imports, theme switching, and framework integration for utilities
Advanced Tailwind CSS component patterns with CVA (class-variance-authority) and variant management. Proactively activate for: (1) building reusable component variants with CVA, (2) compound variants for complex states, (3) safe class composition with tailwind-merge, (4) conditional classes with the clsx/cn utility, (5) styling Headless UI / Radix UI primitives with Tailwind, (6) shadcn/ui patterns, (7) component slot patterns (asChild), (8) polymorphic components, and (9) prop-driven design tokens. Provides CVA setup recipes, cn utility implementation, compound-variant patterns, shadcn/ui-style component templates, and asChild slot examples
Advanced and operational chat.agent capabilities for Trigger.dev, loaded on demand. Load this when working on the raw Sessions primitive (sessions / SessionHandle), a custom chat transport or the realtime wire protocol, durable sub-agents (AgentChat, chat.stream.writer), human-in-the-loop, steering, actions, background injection (chat.defer / chat.inject), fast starts (preload, Head Start via @trigger.dev/sdk/chat-server), context resilience (compaction, recovery boot, OOM, large payloads), chat.local run-scoped state, offline testing with mockChatAgent, or prerelease/version upgrades. For the everyday chat.agent({...}) definition and the useTriggerChatTransport happy path, use the trigger-authoring-chat-agent skill instead.
Writes and reviews SwiftUI WidgetKit code for Home Screen, Lock Screen, StandBy, and watch widgets — timeline providers and reload policies, StaticConfiguration / AppIntentConfiguration, user-configurable widgets, widget families and sizing, accented/tinted rendering modes, interactive widgets and Controls (Control Center), Live Activities and the Dynamic Island, Smart Stack relevance, push-updated widgets, and visionOS / CarPlay / macOS surfaces. Use when building a widget extension, a timeline provider, a Lock Screen or accessory widget, a watch complication, an interactive button/toggle widget, a Control Center control, a Live Activity, or fixing a widget that won't update or render correctly in tinted mode.
How to make UI5 Web Components applications accessible. Covers accessibility APIs (accessibleName, accessibleNameRef, accessibleDescription, accessibleRole, accessibilityAttributes), label-input relationships, invisible messaging, keyboard handling, high contrast themes, and screen reader support. Use when the user asks about ARIA attributes, screen readers, keyboard navigation, accessibility properties, or making their app accessible
Build AI agents with the Strands Agents SDK—the open-source framework (the agent “brain”) for writing agent logic, tools, and multi-agent systems in Python. Model-agnostic, with AWS Bedrock by default. Covers Agent, the @tool decorator, model providers (BedrockModel), multi-agent patterns (agents-as-tools, Swarm, Graph), conversation management, and streaming. Every import is verified against official Strands docs. To deploy a Strands agent on AWS, use the aws-harness skill. Triggers on Strands, Strands Agents, Strands SDK, agent framework, agents as tools, Swarm, Graph multi-agent, BedrockModel.
Claude Code + Codex parallel pipeline for bootstrapping Trellis coding specs. CC analyzes the repo with GitNexus (knowledge graph) + ABCoder (AST), creates Trellis task PRDs with full architectural context and MCP tool instructions, then Codex agents run those tasks in parallel to fill spec files. Use when: bootstrapping coding guidelines, setting up Trellis specs, 'bootstrap specs for codex', 'create spec tasks', 'CC + Codex spec pipeline', 'initialize coding guidelines with code intelligence'. Also triggers when user wants to set up GitNexus or ABCoder MCP for multi-agent spec generation.
Fast, CI-friendly check for entries whose source files have changed since the last verification. Compares entry source files against git diff without reading source code and flags stale entries in index.json. Use in CI pipelines or before releases to detect outdated documentation
Document coding decisions, patterns, and language features in real time as you write code. Activate at the start of a coding session to capture the reasoning behind each meaningful decision. Creates structured learning entries in the .decodie/ directory
Generate a high-level overview of a file, directory, or project—answering “what is this and how is it organized.” Produces a single summary entry covering purpose, structure, entry points, and dependencies. Re-running on the same target overwrites the existing overview
Design and run a documentation system for a team or product. Use this skill when planning what to document, choosing a documentation tool, organizing existing docs, fixing stale documentation, designing a maintenance cadence, or scoping technical writing work. Triggers on documentation, docs, tech writing, knowledge base, wiki, runbook, README, internal docs, doc audit, doc maintenance, stale docs, where do we document. Also triggers when the team is repeatedly answering the same questions or when onboarding takes too long.
Environment-specific adaptation rules for EdgeOne Makers Skills running in sandboxed or restricted AI coding environments (e.g. WorkBuddy). Trigger when the user is working in WorkBuddy or a sandboxed IDE where CLI prompts hang and the network is proxy-isolated (but browser login still works). Covers non-interactive CLI flags, network isolation workarounds, login in a sandbox, proxy bypass, file preview constraints (MUST use http:// via a dev server, NEVER file://, NEVER python -m http.server / npx serve), and dev server requirements.
Build modern web applications with React, Vue, Angular, or Svelte, focusing on performance and accessibility. Use when you need component library development, TypeScript UI implementation, responsive layouts with CSS Grid and Flexbox, Core Web Vitals optimization, service worker offline support, code splitting, ARIA accessibility, Storybook integration, or frontend API client architecture.
The operational playbook for launching a feature well. Covers positioning, internal alignment, customer communications, sales enablement, support readiness, rollout strategy, monitoring with predefined rollback triggers, post-launch measurement against spec hypotheses, and the discipline that distinguishes shipping from releasing from actually launching. Triggers on launch plan, feature launch, launch checklist, ship vs release, rollout strategy, gradual rollout, sales enablement, support readiness, launch announcement, post-launch measurement, launch failure, or declaring victory too early. Also triggers when planning a launch of any size or for any segment, auditing an existing launch process, fixing the “we shipped it but the metric did not move” problem, or building a launch checklist for the team.
Build and edit Fern documentation: turn an OpenAPI spec into a published docs site (fern init --docs, fern generate --docs, --guest when there is no Fern account), MDX pages, navigation, docs.yml config, custom components, landing pages, and changelog entries. Use when asked to build or publish API docs with Fern, even when no fern/ directory exists yet, or when working in a Fern docs repo (a fern/ directory with docs.yml). Routes to a detailed reference per task.
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.