Skills
100,696 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Generate stories about institutional outcasts given impossible mandates with minimal resources. Use when you want team dynamics in hostile institutions, David vs. Goliath within organizations, or narrative tension from constraint-driven creativity.
Run a broad web UI review for pages, flows, or component surfaces using audit categories such as layout hierarchy, content clarity, CTA emphasis, visual consistency, interaction states, responsiveness basics, performance signals, and accessibility basics. Use when the user asks to review a UI, audit a page, critique UX polish, check interface quality before launch, or turn vague design-feedback requests into a structured audit packet. Not for accessibility- only remediation, reusable component API design, system-level token governance, or React/runtime performance debugging. Triggers on: UI audit, design review, UX review, interface critique, polish review, landing-page review, dashboard review, usability review, visual consistency, CTA clarity.
End-to-end workflow for public account and self-media content. Automatically matches the user's request to article writing, cover images, in-article illustrations, or style extraction. Supports multiple writing styles. Use when the user mentions writing a public account post, technical blog, account cover, in-article illustrations, step diagrams, presentation graphics, process diagrams, analyzing writing style, cloning a writing style, imitating viral content, or extracting a style. See the reference directory.
A WeChat Pay delegated recurring payment integration solution covering the full lifecycle for recurring deductions and buy-now-pay-later scenarios: contract-only signing, signing during payment, deduction requests, pre-deduction notifications, contract termination, queries, refunds, and reconciliation. Provides five capabilities: solution selection, sample code, business quick reference, quality assessment, and troubleshooting. Use when the user mentions "委托代扣", "周期扣款", "周期扣费", "自动续费", "先享后付", "免密支付", "纯签约", "支付中签约", "预扣费通知", or "申请扣款", or asks to "接入委托代扣", "要委托代扣接口示例代码", or "排查委托代扣问题".
Use this skill whenever the user mentions 微信读书, WeRead, 书架, 读书时间, 读书笔记, 划线, or wants to do anything with their personal reading data. This includes: book search (搜书/找书), shelf inspection, reading progress and time, notes and highlights export, book reviews, reading statistics (weekly/monthly/annual/overall), personalized recommendations, and first-time API key setup. Always use this skill before running any WeRead-related commands — it provides the correct CLI abstractions, domain rules, and error handling patterns.
Use when you need to apply functional programming principles in Java — including writing immutable objects and Records, pure functions, functional interfaces, lambda expressions, Stream API pipelines, Optional for null safety, function composition, higher-order functions, pattern matching for instanceof and switch, sealed classes/interfaces for controlled hierarchies, Stream Gatherers for custom operations, currying/partial application, effect boundary separation, and concurrent-safe functional patterns. This should trigger for requests such as Improve the code with Functional Programming; Apply Functional Programming; Refactor the code with Functional Programming; Refactor Java code to use streams or Optionals safely; Improve immutability and pure functions in Java. Part of Plinth Toolkit
/c-level-agents:brief [topic] — Generate a one-page strategy brief from an office-hours intake. First step in the strategic sprint pipeline. Use when a strategic question needs to be framed before boardroom deliberation — e.g. locking options, assumptions, and success criteria for a pricing change or a market-entry decision.
Bright Data's Python and Node.js SDKs for calling Web Scraper API, SERP, Web Unlocker and Scraper Studio from application code. Use when the user is writing code they keep that calls Bright Data on a schedule or inside a pipeline, when the same job runs again and again, when a Bright Data package is imported in Python or Node.js, when the user wants their own API or service built on top of Bright Data ("build me a scraper API", "wrap this in an endpoint"), or when the user names the SDK. Not for one-off checks typed at a shell, which belong to brightdata-cli. Not for an AI app that chooses its tools at run time, which belongs to brightdata-mcp. Not for install, login or API key problems, which belong to agent-onboarding.
Core reference for DefiLlama MCP tools. Maps DeFi questions to the correct tool call with proper parameters. Covers entity conventions, metric interpretation, stock vs flow distinctions, percentage formatting, and error recovery. Use whenever querying DeFi data — protocol TVL, token prices, chain metrics, fees, revenue, yields, stablecoins, bridges, ETFs, hacks, raises, treasuries, or institutional holdings.
Use when deploying Deno apps to production, asking about Deno Deploy, or working with `deno deploy` CLI commands. Covers deployment workflows, environment variables, KV database access, custom domains, the --tunnel flag for local development, and the `deno deploy` command reference.
Scan package dependencies for known vulnerabilities using Snyk, Dependabot, and OWASP Dependency-Check. Identify and remediate vulnerable libraries in your software supply chain. Use when managing third-party dependencies or implementing software composition analysis.
Expert blueprint for AI pathfinding (tower defense, RTS, stealth) using NavigationAgent2D/3D, NavigationServer, avoidance, and dynamic navigation mesh generation. Use when implementing enemy AI, NPC movement, or obstacle avoidance. Keywords NavigationAgent2D, NavigationRegion2D, pathfinding, NavigationServer, avoidance, baking, NavigationObstacle.
Create, manage, and deploy Helm charts for Kubernetes package management. Build reusable chart templates, manage releases, configure values, and use Helm repositories. Use when packaging Kubernetes applications or managing K8s deployments with Helm.
Identify changes in institutional holdings, strengthening consensus, and portfolio adjustment trends to help determine which companies or sectors are being overweighted, underweighted, or repriced. Use for 13F filings, fund quarterly reports, institutional holdings reviews, and style validation
Mock interview coach for AI engineering roles, built on the interview bank of AI Engineering from Scratch. Asks one question or one incident scenario, stops, and waits for the learner's own answer. Then it grades the answer against the bank, asks follow-ups one at a time, sends each gap to the lessons and manual sections that teach it, and keeps an append-only record in INTERVIEW-LEARNING.md. Trigger phrases: "interview prep", "mock interview", "ask me an interview question", "practise for my AI engineering interview", "run an incident scenario", "debugging round", "system design round", "inference engineer loop", "review my interview gaps", "how ready am I for the interview"
Jungle Scout keyword expansion tool that expands seed keywords into lists of related keywords, with data such as search volume, trends, PPC bids, and ranking difficulty, across 10 Amazon marketplaces including the US, UK, Germany, and Japan. Trigger this skill when users mention keyword expansion, keyword mining, long-tail keyword mining, related keywords, keyword suggestions, keyword research, PPC bid research, keyword competition, keyword discovery, Jungle Scout keywords, keyword expansion, keyword discovery, keyword scout, related keywords, long-tail keywords, keyword suggestions, PPC bid research, keyword competition, seed keyword expansion, or keyword mining. Trigger it even if the user does not explicitly mention “Jungle Scout,” as long as their request involves finding related keywords from a seed keyword and metrics such as search volume and competition.
Jungle Scout product database with multi-criteria filtering for Amazon products by category, price, sales, revenue, reviews, rating, weight, BSR rank, LQS, seller type, and more, covering 10 marketplaces. Trigger this skill when users mention Amazon product research, product database filtering, BSR rank filtering, category-based product research, high-rated low-competition products, FBA product research, Amazon product search, product filtering, Amazon product database, product research, product filtering, BSR rank filter, category product search, niche product finder, FBA product search, Amazon product discovery, low competition products, or Jungle Scout product database. Trigger it even if the user does not explicitly mention “Jungle Scout” or “product database,” as long as their request involves filtering Amazon products by multiple criteria or discovering promising products.
Jungle Scout ASIN sales estimate lookup. Returns daily estimated sales and the latest known price for a specified ASIN over a period of time, covering 10 marketplaces including the US, UK, Germany, and Japan. Trigger this skill when users mention ASIN sales estimates, daily ASIN sales, sales estimates, competitor sales monitoring, average daily sales, sales trends, product sales tracking, Jungle Scout sales data, sales estimates, daily sales, estimated units sold, ASIN sales tracking, competitor sales monitoring, product sales trend, or daily unit sales. Even if the user does not explicitly mention “Jungle Scout”, trigger this skill whenever they need daily sales estimates for an Amazon ASIN over a period of time.
Analyze an ASIN's traffic sources and exposure distribution using SIF (Search Intelligence Framework) data, including comparisons across the current and previous periods and newly added and removed terms. Trigger this skill when the user mentions ASIN traffic sources, traffic structure analysis, organic versus paid traffic share, exposure score breakdown, period comparisons, new or removed traffic keywords, competitor traffic analysis, SP ad keyword counts, brand ad exposure, Amazon's Choice exposure, editorial recommendation exposure, Top Rated exposure, video ad exposure, organic search exposure share, PPC traffic sources, deal traffic sources, recommendation placement breakdown, ASIN traffic analysis, traffic sources, organic traffic share, ad traffic share, exposure analysis, traffic structure, period-over-period comparison, keyword churn, or SIF. Trigger it even if the user does not explicitly mention “SIF,” as long as they want to analyze ASIN traffic sources, exposure channel distribution, period comparisons, or competitor traffic structures.
Develop AI agents, tools, and workflows with Mastra v1 Beta and Hono servers. This skill should be used when creating Mastra agents, defining tools with Zod schemas, building workflows with step data flow, setting up Hono API servers with Mastra adapters, or implementing agent networks. Keywords: mastra, hono, agent, tool, workflow, AI, LLM, typescript, API, MCP.
Frontend implementation and acceptance baseline for PMA-managed React + Vite SPA and internal-tool frontend projects. Covers required quality gates, file-based type-safe routing with TanStack Router, server state with TanStack Query, the shadcn/ui (base-nova) hard lock, Tailwind theming, testing, i18n, nsl-based dev integration, and delivery rules. Use when implementing, scaffolding, upgrading, or validating acceptance of a React/Vite SPA; use pma-cr for code-review workflow.
This skill should be used when the user asks to "prepare conference presentation", "create presentation slides", "design poster", "make academic poster", "write promotion content", "create Twitter thread", or mentions post-acceptance conference preparation. Provides comprehensive workflow for presentation, poster, and promotion content creation.
PostgreSQL database design, migration, and performance optimization best practices. This skill should be used when writing, reviewing, or refactoring database schemas, migrations, or query patterns. Triggers on tasks involving PostgreSQL databases, schema design, migration optimization, or data modeling
This skill should be used when the user asks to "brainstorm a story idea", "I have an idea for a story", "what if", "develop a premise", "is this idea strong enough", "workshop my logline", "premise", "story concept", "what should I write", "short story or novel", "novella or novel", "name my book", "title ideas", or has a spark (an image, a character, a setting, a question) and wants to turn it into a tested premise before starting a story project. NOT for the controlling idea or theme of an existing story (use theme-craft).
Protocol and DeFi risk evaluation covering hack history, oracle dependencies, treasury health, TVL concentration, and yield sustainability. Use when the user asks "is X safe", "how risky is", protocol security, risk analysis, or wants to evaluate risk before investing or depositing funds.
Use when writing or fixing Maya pipeline code in Python: mayapy batch jobs over many scenes, validating and auto-fixing scenes, FBX export for Unreal or Unity (static, skeletal, animation clips, Game Exporter), Alembic or GPU caches, USD export, stages and layers, references and namespaces, PySide6 tool windows, OpenMaya 2.0 plug-ins, or slow playback. Also when an FBX lands with wrong scale, normals, tangents or extra takes, a USD export has one frame or smoothed meshes, or one bad file kills a batch.
Use when posing a sculpt or preparing it for 3D printing in ZBrush: "pose this character", Transpose Master, TPoseMesh, Gizmo posing with masks, ZSphere rig, Proxy Pose, weapon in the hand, stretching after posing, "3D print this", 1/6 scale statue, miniature, resin or FDM, hollowing, wall thickness, drain holes, keys and pins, cutting into parts, 3D Print Hub, Scale Master, Decimation Master, STL or 3MF, size in millimeters.
Expert in threat modeling methodologies, security architecture review, and risk assessment. Masters STRIDE, PASTA, attack trees, and security requirement extraction. Use proactively for security architecture reviews, threat identification, or building secure-by-design systems.
Transform GWAS signals into drug targets and repurposing opportunities. Connects GWAS-significant loci to causal genes via fine-mapping/eQTL, then to druggable proteins via DGIdb/OpenTargets, then to existing drugs via ChEMBL. Use for GWAS-to-target hypothesis generation, druggable-fraction analysis of disease loci, and human-genetics-validated drug-repurposing prioritization.
Change the sync configuration of an existing data warehouse schema — switch sync_type, pick a different incremental_field, set primary_key_columns, choose cdc_table_mode, or change sync_frequency. Use when the user asks “switch my orders table from full refresh to incremental”, “this table is syncing too slowly / too frequently”, “I need to pick a different incremental column”, “set up CDC for this Postgres table”, or when diagnosis of a failing sync pointed to an incremental-field or PK misconfiguration.
Compatibility alias for `react-best-practices`. Use when an existing workflow, setup script, or user explicitly asks for `vercel-react-best-practices`; route general React and Next.js performance work to `react-best-practices` instead. Triggers on: legacy skill name, Vercel React best practices alias, exact-folder compatibility.
Avalonia UI 12 for cross-platform .NET desktop apps: compiled bindings (x:DataType, on by default in 12), StyledProperty/DirectProperty, custom and templated controls, ControlThemes, DataTemplates/ViewLocator, Generic Host + DI, StorageProvider/Clipboard, Native AOT/trimming, and packaging. Load when the user mentions "Avalonia", "AXAML", "x:DataType", "compiled binding", "StyledProperty", "TemplatedControl", "ViewLocator", or "cross-platform desktop"
Set up and audit Blender scenes the way studios do - units and real-world scale, collection layout, naming conventions (SM_/SK_/T_/M_), origins, linking vs appending, library overrides, asset libraries and catalogs, collection exporters, orphan/path cleanup. Use when starting a project, organizing a .blend, or before handoff/export.
Browser automation with two integrations - Chrome DevTools MCP (always available, performance tracing) and Claude-in-Chrome extension (authenticated sessions, GIF recording). Use DevTools for testing/debugging, Claude-in-Chrome for authenticated workflows.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in- progress changes, or asks to "review since X".
Creates comprehensive dashboard and analytics interfaces that combine data visualization, KPI cards, real-time updates, and interactive layouts. Use this skill when building business intelligence dashboards, monitoring systems, executive reports, or any interface that requires multiple coordinated data displays with filters, metrics, and visualizations working together.
MVVM for .NET desktop apps (WPF, Avalonia, WinForms, MAUI) with CommunityToolkit.Mvvm 8.4+ source generators: [ObservableProperty] partial properties, [RelayCommand] async commands, Generic Host + DI, UI-thread dispatching, navigation, messaging, and testable view models. Load when the user mentions "MVVM", "ViewModel", "WPF", "desktop app", "ObservableProperty", "RelayCommand", "ICommand", "INotifyPropertyChanged", "Dispatcher", or "UI thread"
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.