Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Read this skill for every frontend, UI, or UX task, including small fixes, styling, components, interaction design, accessibility, reviews, and design-only advice across web, native, game, and embedded interfaces. For new or changed design decisions, visually research at least two comparable products and read relevant UX/UI guidance before proposing or coding. Study videos or live interactions for flows and motion, then visually verify the result.
Evidence-first research workflow for external web/source research and internal codebase investigation. Use when the user invokes $research, asks to research, investigate, audit what exists, compare options, understand current implementation, gather evidence, inspect docs, look up current facts, or answer repo-grounded questions before implementation. Prefer optional parallel agents for broad, separable research lanes such as external sources, codebase evidence, docs, risks, and competitor or alternative analysis.
Analyze code quality based on "Clean Code" principles. Identify naming, function size, duplication, over-engineering, and magic number issues with severity ratings and refactoring suggestions. Use when the user requests code quality checks, refactoring advice, Clean Code analysis, code smell detection, or mentions terms like code review, code quality, refactoring check.
Review or refactor React / Next.js code for performance and reliability using a prioritized rule library (waterfalls, bundle size, server/client data fetching, re-renders, rendering). Use when writing React components, Next.js pages (App Router), optimizing bundle size, improving performance, or doing a React/Next.js performance review.
Manages the rhdh-plugin-export-overlays repository and Extensions Catalog: onboard plugins, update upstream versions, repair export or publish failures, inspect workspace health, triage the overlay PR backlog by label, staleness and merge readiness, and trigger /publish. Use for source.json, plugins-list.yaml, backstage.json, catalog metadata, overlay CI, plugin import, overlay PRs, or testing exact PR artifacts before merge. For code-level review of a pull request, use /rhdh-pr-review. To promote an rhdh-plugins release through overlays into rhdh-plugin-catalog, use /rhdh-plugin-midstream-propagate.
Six-phase playbook for running ownership transitions in either direction — receiving work from another team (initiative handoffs from shepherds, frameworks from Platform, operational responsibilities from SRE), or originating a transition (handing off a built framework, transitioning a shepherded initiative, or moving operational responsibilities). Applies Bitwarden's Work Transition Playbook from whichever side a team is on. Use when a team is about to take on or hand off transferred work, when preparing materials or sessions, when the support period is underway, or when running a pulse check or retrospective on a handoff.
When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," or "breadcrumb schema." For broader SEO issues, see seo-audit.
Load PROACTIVELY when task involves connecting external services or third-party APIs. Use when user says "add email sending", "integrate a CMS", "set up file uploads", "add analytics", or "connect to S3". Covers email services (Resend, SendGrid), CMS platforms (Sanity, Contentful, Payload), file upload solutions (UploadThing, Cloudinary, S3), analytics integration, webhook handling, error recovery, and credential management.
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
Builds, tests, and analyzes bounded process-based discrete-event simulations in Python with SimPy 4.1.2: Environment, Timeout, Process, AnyOf/AllOf conditions, interrupts, Resource, PriorityResource, PreemptiveResource, Container, Store, time-weighted monitoring, and replication-based output analysis, plus bundled safe CLIs. Use when modeling queues, production lines, logistics, or service operations with generator processes; when contending entities need shared resources or preemption; when instrumenting queue length or utilization correctly; when running independent replications with seeds and confidence intervals; when debugging event ordering or run(until=) boundaries. Not for continuous-time ODE or agent-based modeling frameworks.
AI-powered git commit message generation. Uses LLM to summarize changes and create meaningful commit messages. Triggers when user wants to commit changes, amend/squash commits, or needs LLM to summarize changes for commit messages. Chinese triggers: 提交, 提交代码, 提交更改, 提交修改, 要提交, commit, 提交信息, git 提交, 生成提交信息.
SparkScan single-barcode scanning with the pre-built scanning UI in native Android (Kotlin/Java) projects. Use for integration, scan settings, result handling, UI customization, SDK version migration, replacing a third-party barcode scanning library, or troubleshooting.
Generate and validate JSON-LD structured data, supporting Schema.org types such as Article, BlogPosting, Organization, WebPage, Product, and LocalBusiness. Automatically detects page type, validates syntax, checks required fields, and provides a link to the Google Rich Results test tool and Next.js component code examples.
Design and audit subscription and entitlement systems for SaaS, mobile apps, games, desktop utilities, and marketplaces across plans, trials, renewals, grace periods, downgrades, upgrades, restore purchases, refunds, revocations, usage limits, ledger events, and support tooling. Use when pricing, billing, access, or account state must stay consistent after payment changes.
Database migration patterns with the Supabase CLI: npx supabase migration new, zero-downtime migrations, data backfill strategies, schema versioning, rollback strategies, and TypeScript type generation. Use when creating database migrations, performing zero-downtime schema changes, backfilling data in production, managing schema versions, or planning rollback strategies. Trigger with "supabase migration", "supabase schema change", "supabase zero downtime", "supabase rollback", "supabase db push", "supabase migration new".
Implement Syncfusion Linear Gauge component to visualize numerical values in a linear manner with support for pointers, ranges, annotations, and interactive features. Use this skill to create responsive gauge controls with customizable appearance, animations, and accessibility.
Guide for implementing and customizing the Syncfusion Progress Bar component in ASP.NET Core applications. Use this skill when the user needs to create progress indicators showing task completion, file upload/download status, data loading states, circular progress visualizations, segmented progress tracking, or animated progress bars. Essential for building user-friendly feedback mechanisms that clearly communicate progress to end users.
Create and configure Syncfusion Stock Chart controls in ASP.NET Core applications. Use this skill when building financial data visualizations with stock charts, candlestick series, technical indicators, or trading dashboards. Covers setup, series types, data binding, legends, indicators, and user interactions.
Implements Syncfusion Flutter Maps (SfMaps) for interactive geographical data visualization in Flutter apps. Use when working with shape layers, tile layers, choropleth maps, or map markers and overlays. This skill covers GeoJSON rendering, OpenStreetMap/Bing Maps integration, bubbles, legends, tooltips, zoom and pan, and spatial data visualization.
Implements Syncfusion Flutter Pyramid Charts (SfPyramidChart, PyramidSeries) for proportional and hierarchical data visualization. Use when working with pyramid charts, funnel-style visualizations, or segment-based data comparisons in Flutter. This skill covers series configuration, segment exploding, gap ratio, PyramidMode, data labels, legends, and tooltip customization.
Implements Syncfusion Flutter Spark Charts (SfSparkLineChart, SfSparkAreaChart, SfSparkBarChart, SfSparkWinLossChart) for compact, lightweight data visualization. Use when working with micro charts, sparklines, KPI indicators, or inline trend charts in Flutter dashboards. This skill covers chart configuration, data binding, markers, tooltips, and trackball for all four spark chart types.
Implements Syncfusion Flutter TreeMap (SfTreemap) for visualizing hierarchical and proportional data in Flutter apps. Use when working with treemap layouts, nested rectangles, drill-down navigation, or hierarchical data visualization. This skill covers layouts, labels, tooltips, legends, selection, color mapping, and drilldown navigation.
Applies a modified Fagan Inspection methodology to resolve persistent bugs and complex issues. Use when several fix or debugging attempts have already failed and a methodical root-cause analysis warranting a Fagan inspection is needed. For first-pass diagnosis of a reproducible bug or regression use diagnose-hard-problem. Do not use for simple troubleshooting.
Use this skill when fetching data, managing server state, or handling API mutations in the Svelte frontend. Covers createQuery, createMutation, query keys, cache invalidation, optimistic updates, and WebSocket-driven refetching. Apply when adding API calls, managing loading/error states, or coordinating cache updates after mutations.
Unified team skill for roadmap-driven development workflow. Coordinator discusses roadmap with user, then dispatches phased execution pipeline (plan -> execute -> verify). All roles invoke this skill with --role arg. Triggers on "team roadmap-dev".
Turn a technical design doc into a product/QA-readable technical review markdown (business language + Mermaid). Hard-gates §1 background/goals until the user explicitly approves before writing the file. Triggers — 「技术评审文档」「生成评审文档」「design to review」「tech review doc」「写技术评审」. Do NOT use for marketing articles (article-writer), code PDCA (solve-workflow), or AI de-slop rewriting (humanizer).
Create structured technical specification documents that bridge product requirements and engineering implementation. Use when writing a tech spec, engineering spec, system design doc, or API specification. Produces a complete spec with problem statement, proposed solution, data model, API design, alternatives considered, security considerations, testing plan, and rollout strategy.
Replaces the agent's reflex of piping a command straight through `tail -n N` or `head -n N` with `tee` to a file inside a `mktemp -d` directory followed by the same `tail` / `head`. The truncated view stays the same; the full output stays recoverable. Skipped for outputs expected to be very long.
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.