Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Browser runtime debugging toolkit — prioritize browser DevTools and CDP tools for runtime inspection and control when debugging UI/CSS/DOM layout, frontend interaction, and rendering issues. Default channel: ego-browser (macOS, runtime-checked) — full interaction, js(), raw cdp(), inherited login state, isolated task space, human-AI handoff. On unavailability or failure degrade along: playwright-mcp → agent-browser (non-macOS); web-access CDP Proxy (lightweight control + login state, curl-parallel); chrome-devtools-mcp (DevTools panels: computed style, network, perf trace). Triggers: 「浏览器调试」「UI 调试」「DOM 检查」「CSS 调试」「页面布局问题」「前端运行时调试」「chrome devtools」「CDP 调试」「登录态调试」 / browser debug, devtools, dom inspect, css debug, runtime debugging, login-state debug.
Guides building Expo/React Native apps with TypeScript on a fixed stack (NativeWind, React Navigation static config, @rn-primitives, TanStack Query, TanStack Form, Zod), covering structural foundations—structure, navigation and deep links, styling, UI primitives and accessibility, data, async states, errors, forms, authentication, and guards—plus platform fixes and translating existing requirements into that implementation. Use when creating an Expo app or changing code in an app whose `package.json` has `expo`, `@react-navigation/native`, and `nativewind`, to follow these conventions.
Write a business report in Word with a fixed structure (executive summary, background, analysis, recommendations, appendix), sourced numbers and a consistent voice. Use when the user asks for a report, memo, review, assessment or analysis document, or to turn notes or data into one.
Comprehensive caching patterns for ASP.NET Core Razor Pages applications. Covers output caching, response caching, memory caching, distributed caching with Redis, cache invalidation strategies, and HybridCache (.NET 9+). Use when implementing caching in Razor Pages applications, choosing between memory and distributed caching, or optimizing application performance with caching.
Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs). Use when listing books, searching/filtering library records, reading/updating metadata, adding/removing formats, exporting books, maintaining custom columns, running library checks, managing FTS indexing/search, or creating catalogs/backups from a Calibre library.
Prepare, validate, import, reconcile, and correct Support Ops daily ticket metrics from Google Sheets or exported JSON into CawPlan's cawplan_csm key-metrics domain. Use when: Support asks to onboard its ticket dashboard data, backfill or upload Support ticket counts, validate a Support metrics export, compare CawPlan metrics with the Support sheet, or generate a safe Apps Script exporter. NOT for: generic CawPlan business metrics, device/app telemetry, editing the Support dashboard UI, producing the weekly Google Doc, or inventing new CSM metric names and tags
Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs/downloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.
A Python package useful for chemistry (mainly physical/analytical/inorganic chemistry). Features include balancing chemical reactions, chemical kinetics (ODE integration), chemical equilibria, ionic strength calculations, and unit handling. Use when working with chemical equations, reaction balancing, kinetic modeling, equilibrium calculations, speciation, pH calculations, ionic strength, activity coefficients, or chemical formula parsing.
Generate client-facing performance reports for Chinese wealth management clients. Adapted from the original client-report skill for A-share portfolios, Chinese regulatory requirements, and local reporting conventions. Triggers on "A股客户报告", "客户持仓报告", "client report China", "wealth report A-share", "客户业绩报告", or "portfolio report for [client]".
Comparable company analysis for A-share equities. Adapts the original comps-analysis skill for Chinese market data sources, A-share trading multiples, and domestic peer selection. Triggers on "A股可比公司", "可比分析", "comps China", "peer comparison A-share", "可比公司分析", or "trading comps [industry]".
Tonghuashun iFinD (51ifind.com) financial data queries. Supports 18 API endpoints for real-time quotes, historical quotes, financial indicators, macroeconomic data, and more across A-shares, funds, bonds, futures, and indices. Chinese financial data query skill powered by THS iFinD (51ifind.com) API. Covers real-time quotes, historical data, financial indicators, macro economics, fund valuation, and more across 18 API endpoints for A-shares, funds, bonds, futures, and indices.
Genre pack: the site-of-the-day aesthetic — the page as a film projected on studio print. Warm paper canvas, near-black ink type, one vivid electric-blue accent, grotesk display, alternating scene canvases, a scrubbed index counter, text-dissolve pins, and a drag-driven card carousel. For portfolios, product launches, agencies, and any brief that wants premium scroll-driven storytelling. Requires taste-gsap for the implementation. Stack on the design-taste core skill.
Claude Code config optimization skill. Use when: - Editing CLAUDE.md, rules/, skills/, agents/, commands/ - User asks about config best practices - Checking optimization status - User says "claude code changelog" or "claude code updates" - User asks about new features or breaking changes in Claude Code
Use this skill to drive Jetpack Compose UI from tests with the high-level action APIs that do not go through a gesture builder — performClick, performScrollTo, performScrollToIndex, performScrollToKey, performScrollToNode, requestFocus, performSemanticsAction, and performFirstLinkClick. Covers picking the correct receiver node (the scrollable container vs an item), the matchers used to find a scroll parent (hasScrollAction, hasScrollToIndexAction, hasScrollToKeyAction, hasScrollToNodeAction), and how the lazy vs non-lazy scrollable cases differ. Use when the developer asks "how do I tap a Compose node", "scroll to an item in a LazyColumn", "click a link inside Text", "trigger a custom semantics action", or reports "Action performScrollTo failed" / "node has no parent layout with a Scroll SemanticsAction" / "ScrollToIndex not defined".
Build, deploy, and test Cloudflare Email Routing Workers with postal-mime MIME parsing, RFC 5322 mimetext replies, and AI auto-response loops. Use when building AI email agents, inbound email parsing, attachment extraction to R2, automated ticket creation, and safe forwarding rules.
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
Review .NET changes for bugs, regressions, architectural drift, missing tests, incorrect async or disposal behavior, and platform-specific pitfalls before you approve or merge them. USE FOR: reviewing a pull request or patch in a .NET repository; checking for behavioral regressions, API misuse, or missing tests; auditing architectural or framework-specific. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Review a specific diff, pull request, or commit range with independent reviewers for correctness, security, maintainability, and repository rules, check each finding against the code, and check fixes against earlier findings. Use when the user asks to review changes, a PR, or commits, or when another skill runs it to review a change or check fixes. Not for whole-codebase or current-state subsystem audits.
Comprehensive codebase audit — adaptive parallel deep analysis (frontend/backend contracts, data integrity, exception handling/security, architecture/technical debt, configuration/caching), structured findings + adversarial verification + baseline comparison, producing a unified severity-ordered report and remediation roadmap. Supports a quick health check mode. Use when user asks to audit, analyze, or review an entire codebase for design issues, find hidden bugs, check architecture health, or asks '全面审查', '代码库审计', '分析设计问题', 'audit codebase', 'health check', '有哪些问题', '快速体检'. Also trigger when user asks to find silent degradation, data flow breakpoints, type mismatches between frontend and backend, or wants to understand technical debt across a project.
Detects and prevents visual misleads, cognitive biases, and data integrity violations in visualizations, dashboards, reports, and presentations. Audits charts for honesty, diagnoses misinterpretation causes, and provides specific fixes. Invoke when user mentions chartjunk, misleading chart, truncated axis, data integrity, visual deception, 3D chart problems, cherry-picking data, or needs to audit visualizations for accuracy. For general design evaluation, use `design-evaluation-audit`. For cognitive foundations, use `cognitive-design`.
Add or modify webhook interceptors in an Adobe Commerce app. Use when the user wants to intercept Commerce operations before or after execution to validate input, append data, or modify behavior. Requires a base app initialized with commerce-app-init.
Use this skill to wire the correct Gradle dependency matrix for Jetpack Compose UI tests. Covers `androidTestImplementation("androidx.compose.ui:ui-test-junit4")`, the `debugImplementation("androidx.compose.ui:ui-test-manifest")` requirement that makes `createComposeRule()` work, the host-test (Robolectric) trio, the accessibility add-ons (`ui-test-accessibility`, `ui-test-junit4-accessibility`), and the `TestManifestGradleConfiguration` lint warning. Use when the user reports `ActivityNotFoundException: ComponentActivity`, `createComposeRule unresolved`, `lint warning ui-test-manifest`, `Cannot find test rule`, or asks "what dependencies do I need for Compose UI tests" / "why won't my Compose test compile".
Use when sending local changes back to the project (an added journal profile, a fixed checklist item, an adapted skill) or reporting a false positive or bug. Finds what changed, scans it for patient data, shows every line and sends nothing until you confirm.
This skill should be used when creating Git commits to ensure they follow the Conventional Commits specification. It provides guidance on commit message structure, types, scopes, and best practices for writing clear, consistent, and automated-friendly commit messages. Use when committing code changes or reviewing commit history.
Open a ready-for-review GitHub pull request for completed local changes, including any needed commit and push. Use when the user asks to open, create, or publish a PR for work that is already done, or when another skill runs it to publish its work.
Master persuasive writing for social media with proven hooks, storytelling frameworks, and psychological triggers. Includes CSV databases with 150+ hooks, power words, carousel structures, and emotional triggers specifically optimized for Instagram swipes and X/Twitter "Read more" clicks. Works with creative-copywriter subagent for intelligent content generation.
Apply these opinionated C# conventions whenever writing or reviewing C# 12 / .NET 8+ code: nullable enabled with warnings as errors, records and primary constructors, pattern matching over cast chains, the Result pattern for expected failures, async all the way with CancellationToken, IOptions config, IHttpClientFactory, and never returning EF entities from an API.
Agent 2 of the video editing pipeline. Finds and removes spoken mistakes — stutters, repeated words, false starts, and retakes (re-recorded lines) — from a talking-head recording. Use after cut-silences, when asked to cut mistakes, remove stutters / repeats / filler restarts, clean up flubs, or keep the best take. Works review-gated: it proposes every cut with context and a reason for approval, then renders only the approved cuts via ffmpeg. Requires a word-level transcript.
Generate full notes for must-read recommendations, maintain concepts, and backfill links. English triggers: "generate paper notes", "batch paper notes". This is pipeline stage 3. 论文笔记生成（3 步流水线的第 3 步）。补充概念库，为推荐论文生成完整笔记，链接回填到推荐文件；目录页默认自动刷新，git 自动化默认关闭。触发词："批量笔记"、"跑一下论文笔记"
Circle reveal (falling droplet + crest-glow liquid-glass) when switching dark/light mode — a switch toggle, an overlay radiating from the CURSOR POSITION (clamped to the button's bounds), a neutral market-style dark-mode palette (GitHub Dark/Vercel/Linear), accepted with real Playwright. Call when the user says 'make dark mode', 'theme toggle', 'switch light and dark', 'circle reveal', 'UI switching effect', or /dark-mode-maker. DIFFERENT from docs-site-macos (that is a macOS documentation site template; dark-mode-maker is a toggle module usable on ANY HTML page).
Use when designing or critiquing aggregate boundaries — phrases like "aggregate", "aggregate root", "should these be one entity or two", "consistency boundary", "transactional consistency", "this aggregate is huge", "should I reference by ID or by object". Defines aggregates as transactional consistency boundaries and the rules for entity references within and across them
Use when identifying DDD anti-patterns and smells in code or design — phrases like "anemic domain model", "primitive obsession", "leaky repository", "smart UI", "transaction script", "god aggregate", "big ball of mud". Catalogs the common DDD anti-patterns with symptoms, why each is wrong, and the pattern skill that explains the fix
Use when mapping relationships between bounded contexts — phrases like "context map", "how do these two services talk", "should we use an anticorruption layer", "shared kernel vs separate ways", "upstream/downstream", "what integration pattern fits here". Catalogs the seven relationship patterns (Shared Kernel, Customer-Supplier, Conformist, Anticorruption Layer, Open Host Service, Published Language, Separate Ways) and the signals that pick one.
Use when the model is "working but feels off" and the user wants to deepen it — phrases like "supple design", "refactor toward deeper insight", "implicit concept", "the model isn't quite right yet", "what would a better model look like", "intention-revealing interfaces", "side-effect-free functions", "assertions in the domain", "conceptual contours". Covers Evans's Part III techniques for evolving a model past its first draft.
Use when behavior does not naturally belong to a single entity or value object—phrases like “domain service”, “this logic spans multiple aggregates”, “where does this go”, “the entity is starting to know too much”, “we need a calculator/coordinator that isn't a thing”. Defines when to introduce a stateless domain service instead of forcing behavior onto an entity. Distinguishes domain services from application and infrastructure services.
Use when creation of an aggregate or complex value object requires non-trivial work — phrases like "factory", "the constructor is doing too much", "construction has business meaning", "how do I create this aggregate", "constructor with twelve parameters". Defines when to introduce a factory and when a constructor or static creation method suffices
Use when designing how aggregates are persisted and retrieved—phrases like “repository”, “how should I load this aggregate”, “JPA repository vs DDD repository”, “leaky repository”, “finder methods”, “the repository is doing too much”. Defines a repository as the abstraction that gives the illusion of an in-memory collection of aggregates. One repository per aggregate root.
Use when the user asks for a PR-style code review for DDD smells—phrases like “is this DDD-clean”, “review this for domain modeling issues”, “what's wrong with this aggregate”, “audit this module for DDD”. Scans a file, diff, or module against the DDD anti-pattern catalog and reports specific violations with citations to the relevant pattern skill. Do NOT use when the user wants new code (route to ddd-implement) or wants to design from scratch (route to ddd-design).
Use when deciding where to spend modeling effort — phrases like "core domain", "supporting subdomain", "generic subdomain", "what's worth building vs buying", "where should the senior engineers work", "is this our competitive edge or just plumbing". Distinguishes Core (competitive edge), Supporting (custom but not differentiating), and Generic (commodity, buy/library) subdomains
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.