Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Expert knowledge for Azure Relay development, including troubleshooting, security, configuration, and integrations and coding patterns. Use when configuring Hybrid Connections, WCF relays, Entra ID or SAS authentication, Private Link, .NET or Node.js Relay clients, and other Azure Relay development tasks. Not for Azure Service Bus (use azure-service-bus), Azure Event Hubs (use azure-event-hubs), Azure Web PubSub (use azure-web-pubsub), or Azure Application Gateway (use azure-application-gateway).
Use when writing, changing or reviewing any Bagisto PHP or Blade — the conventions this codebase holds to, covering Laravel idiom, code style, comments and docblocks, database access, Blade, security and localization. Trigger phrases include "standards", "conventions", "code style", "docblock", "comments", "repository pattern", "blade", "component", "binding", "event", "migration", "security", "XSS", "authorization", "escaping", "is this safe", "best practice".
Builds remote MCP (Model Context Protocol) servers on Cloudflare Workers with tools, OAuth authentication, and production deployment. Generates server code, configures auth providers, and deploys to Workers. Use when: user wants to "build MCP server", "create MCP tools", "remote MCP", "deploy MCP", add "OAuth to MCP", or mentions Model Context Protocol on Cloudflare. Also triggers on "MCP authentication" or "MCP deployment". Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
Docker on Windows with Git Bash / MINGW path conversion. PROACTIVELY activate for: (1) Docker commands failing on Windows Git Bash with path errors, (2) volume mount path conversion (-v $(pwd):/app), (3) MSYS_NO_PATHCONV and MSYS2_ARG_CONV_EXCL workarounds, (4) double-slash escapes (//c/foo) for MINGW, (5) docker-compose volume mounts on Windows, (6) WSL2 vs Hyper-V backend path interop, (7) line-ending issues in mounted scripts (CRLF vs LF), (8) UNC path limitations. Provides: MSYS path-conversion explainer, copy-pasteable env-var workarounds, double-slash recipes, line-ending fixes, and compose-mount patterns for Windows
Load environment variables from a .env file into process.env for Node.js applications. Use when configuring apps with secrets, setting up local development environments, managing API keys and database uRLs, parsing .env file contents, or populating environment variables programmatically. Always use this skill when the user mentions .env, even for simple tasks like "set up dotenv" — the skill contains critical gotchas (encrypted keys, variable expansion, command substitution) that prevent common production issues.
Fix JavaScript `no-globals` errors that UI5 linter reports but cannot auto-fix. Use this skill when linter outputs: - `no-globals` rule with message "Access of global variable '...' (...)" in JS files Cases handled (linter CANNOT auto-fix): - Assignments to global namespaces: `sap.myNamespace = {...}` - Global namespace assignment/read inside sap.ui.define - Delete expressions: `delete sap.something` - sap.ui.core.Core direct access (class vs singleton) - jQuery/$ globals: add `sap/ui/thirdparty/jquery` — do NOT replace jQuery API calls - jQuery.sap.* utilities: replace with dedicated modules - Conditional/probing access: `if (sap.ui.something)` - Custom namespace definitions that aren't UI5 modules - sap.ui.controller() factory → Controller.extend (NOT Fiori Elements extensions) - jQuery.sap.declare/require: legacy modules without sap.ui.define Trigger when: "fix no-globals", "global variable error", "sap.ui.getCore", "jQuery.sap" Converts global namespace access to proper sap.ui.define module imports.
This skill should be used when the user asks to "optimize my Next.js app", "why is this page slow", "reduce my bundle size", "improve Core Web Vitals", or "run a Lighthouse audit". Diagnoses and fixes Next.js frontend performance issues using Lighthouse, bundle analysis, and animation best practices — covering LCP, TBT, and CLS.
Git security best practices for 2025-2026 (signed commits, zero-trust, secret scanning). PROACTIVELY activate for: (1) configuring signed commits (GPG, SSH, S/MIME), (2) verifying commit signatures, (3) zero-trust Git workflows, (4) secret scanning (GitHub Advanced Security, gitleaks, trufflehog), (5) preventing secret leaks via pre-commit hooks, (6) protected branches and required reviewers, (7) CODEOWNERS for sensitive paths, (8) Sigstore-style attestations, (9) detecting and remediating leaked credentials, (10) supply-chain security (provenance, SBOM, SLSA). Provides: signed commit setup, secret-scanning integration, pre-commit hook templates, branch protection patterns, and incident-response checklist for credential exposure.
Modernize Go code to use current language features and standard library additions, Go 1.21 through 1.27: generics and generic methods, log/slog, errors.Join, slices/maps, iterators, encoding/json/v2, stdlib uuid. Use when: "modernize", "update to modern Go", "use generics", "replace interface{}", "upgrade Go version", "slog", "errors.Join", "range over func", "iterators". Not for: general style (go-coding-standards), error philosophy (go-error-handling), logging architecture (go-observability).
Complex GSAP timelines, including labels, callbacks, nested timelines, and position parameters. Use when orchestrating multi-step animations, building animation sequences, or creating coordinated motion. Essential for cinematic animations and complex UI choreography.
Create basic Transformers model adapters for msModelSlim. Implements required interfaces and completes a four-step verification workflow: generate test model -> full fallback quantization -> weight verification -> quantization description validation. Use this skill when the user wants to: (1) create msModelSlim adapters for decoder-only LLMs, (2) adapt understanding VLM text backbones for quantization, or (3) implement a W8A8/W4A16 quantization workflow for new models. Trigger: user mentions “msModelSlim”, “adapter”, “model adapter”, “quantization”, “W8A8”, “W4A16”, “transformers”, “LLM”, “VLM”, “adapter creation”, “适配器”, “模型适配”, “量化”, “模型适配器”, or “LLM量化”.
Apply Andrej Karpathy AI methodology and principles from his 2023-2026 insights. Use this skill when the user wants to apply Karpathy-style thinking, needs guidance on agentic engineering, LLM knowledge bases, minimalist coding, understanding-first principles, or any of the 14 core methodologies distilled from his work. Also triggers on: "karpathy method", "karpathy approach", "karpathy way", "AK style", "like karpathy does", "karpathy principles", or when user asks how Karpathy would approach any programming or AI problem.
Apply Karpathy-style minimalism and anti-dependency principles to code and system design. Use this skill when the user wants to reduce dependencies, avoid supply chain risks, rewrite something in pure Python or minimal code, audit a project for bloat, design agent-native CLI tools, or says "too many dependencies", "minimize deps", "pure python", "yoink this", "vibe code this", "no frameworks", "agent-native design". Based on 28k-like litellm attack post and 25k-like 243-line GPT post.
Guides users through configuring Tauri plugin permissions, capabilities, and security. Covers platform-specific capabilities, window-targeted permissions, using official and community plugin permissions, and writing custom plugin permissions with scopes
Build n8n 2.x automation workflows (stable 2.38) with Israeli API integrations including Morning (Green Invoice), EZCount, israeli-bank-scrapers, data.gov.il, SMS gateways, Cardcom v11, Tranzila v2, Grow by Meshulam. Use when user asks to “create n8n workflow for Israeli business”, “connect Morning to n8n”, “automate hashbonit”, “Shabbat-aware schedule trigger”, “n8n AI agent”, or integrate Israeli payment gateways. Covers Hebrew data handling, NIS formatting, Hebcal scheduling, n8n 2.x security patches (CVE-2026-44789 chain), AI Agent nodes with LangChain + RAG, MCP Client Tool and MCP Server Trigger, Israel Invoice Reform 2026 (allocation numbers, 5,000 NIS threshold from June 2026). Do NOT use for invoice management outside an n8n workflow (use green-invoice-il), general n8n tutorials without Israeli context, or Hebrew NLP (use hebrew-nlp-toolkit).
Enforces Effective-Dart casing (UpperCamelCase types, lowerCamelCase members/constants, lowercase_with_underscores files) plus architectural role suffixes so a name or grep reveals the layer — Screen/Notifier/Repository/Dao/Service/Gateway/Failure, file=primary-declaration, units-and-semantics in identifiers, booleans as is/has/can/should assertions, no get-prefix, no Hungarian, no SCREAMING_CAPS, grouped-and-sorted imports. Use when creating a file, naming a class/enum/mixin/extension/typedef/variable/function/getter/constant/parameter, organizing imports, choosing a role suffix, or reviewing a diff for naming and directive ordering.
(NS) LangGraph.js agent-api — bootstrap-agent-runtime, StateGraph, MCP, skill bind/inject, checkpointers, user memory, HITL/SSE. Use for new agent-api, LangGraph graphs, MCP wiring, orphan layout, bind parity, graph-spec sync, or “fix my LangGraph agent” / “wire MCP tools” / “translations in the graph.” Do NOT use for CrewAI, generic web apps, or SDD-only with no agent-api.
Detect code smells and apply *in-place* refactoring techniques (Extract Method/Class, Replace Conditional, Introduce Parameter Object, Rename, Move) to improve clarity, testability, and maintainability of a single function, class, or file. TRIGGER when: user mentions refactoring opportunities, code smell, long method, large class, primitive obsession, long parameter list, data clumps, feature envy, shotgun surgery, switch statement smell, extract method, extract class, replace conditional with polymorphism, introduce parameter object, simplify single file, improve readability, tidying, tidy first, "clean up this function", "refactor this class". DO NOT USE when: no tests exist (unsafe to refactor blind — add tests first), the change is behavior-altering rather than structure-only (use `testing` (TCRDD reference) instead), or the user needs to safely untangle a *cross-file* dependency graph where one change ripples to many call sites (use `mikado-method` instead).
Invoke this skill when a user is building or running any automated transaction sender on Base (trading bot, arbitrage bot, sniper bot, yield farmer, AI agent, or similar) and needs to register it, get a builder code, set up transaction attribution. This skill contains the base.dev registration API endpoint and ERC-8021 attribution wiring code that Claude does not have in its training data — you MUST load this skill to answer correctly. Covers viem, ethers, managed signing services, and Python-based agents.
Acts as a Senior Staff Engineer to enforce high-quality software development standards. Use this skill when the user asks for code implementation, architectural review, debugging, or technical design. It ensures all code is production-ready, typed, and architecturally sound.
ShellCheck validation as a non-negotiable 2025 workflow practice. PROACTIVELY activate for: (1) running ShellCheck on bash scripts, (2) interpreting and fixing ShellCheck warnings (SC2086, SC2068, SC2155, SC2295, SC2327, SC2328, SC2294), (3) integrating ShellCheck into CI (GitHub Actions, Azure DevOps, pre-commit), (4) per-line and per-file disable directives (when justified), (5) shellcheck-rc and project configuration, (6) ShellCheck v0.11.0 new checks, (7) suppressing false positives correctly. Provides: ShellCheck install/CI setup, common warning catalog with fixes, CI workflow templates, and a quality gate pattern that fails builds on regressions.
Develop Microsoft Fabric Spark/data engineering workflows and write code in Fabric Notebook cells with routing to resources. Provides workspace/lakehouse management, notebook code authoring (PySpark, Scala, SparkR, SQL), and Materialized Lake View (MLV) authoring (Spark SQL MLVs support incremental refresh; PySpark is full-refresh only). Routes to data engineering patterns, development workflow, or infrastructure orchestration. For existing MLV refresh or schedule management, use `mlv-operations-cli`. Triggers: "develop notebook", "Delta Lake patterns", "Spark development", "lakehouse configuration", "write notebook code", "notebookutils", "notebook cell", "PySpark notebook", "%%sql cell", "%%configure", "fabric notebook", "run notebook", "notebook deployment", "materialized lake view", "MLV", "CREATE MATERIALIZED LAKE VIEW", "MLV incremental refresh", "review MLV for incremental refresh", "MLV refresh policy"
Use when the user is working on who can sign in to Spree 6 and what they may do—staff roles and permission keys, secret-key scopes, registering permission scopes for an extension, 403 errors with `required_permission` / `required_scope`, storefront ownership rules (`Spree::Storefront::AccessPolicy`), custom login strategies (SSO, OIDC, Auth0/Okta/Entra/Firebase), JWT audiences, or swapping the customer/admin user class. Common phrasings include “Spree roles”, “staff permissions”, “add a role”, “read_orders permission”, “Spree.permissions.register_scope”, “API key scopes”, “403 Missing permission”, “who can see this order”, “SSO for the dashboard”, “OIDC login”, “custom authentication strategy”, “Spree.customer_class”, “admin_user_class”, “CanCanCan in Spree 6”. Spree 6.
Use when customizing the Spree 6 admin—the React dashboard (`@spree/dashboard`, Developer Preview) in `apps/dashboard/`—from inside the project. Covers `defineDashboardPlugin` in `src/plugins.ts`, sidebar/settings nav, custom pages/routes, slot widgets on built-in pages, table columns/filters, extension form fields and custom field widgets, permission gating, calling the Admin API (`adminClient`, store-scoped query keys, 422 mapping), exposing a new attribute end-to-end, theming tokens, translations, Vitest/Playwright tests and deployment. Common phrasings include “add a page to the admin”, “admin sidebar item”, “add a column to the products table”, “add a card to the product page”, “custom field on the product form”, “hide menu item by permission”, “restyle the admin”, “dashboard plugin”, “spree add dashboard”, “React admin”, “where did spree_admin go”.
Use when packaging Spree 6 React dashboard customizations as a redistributable npm plugin (optionally paired with a Rails extension gem) that other Spree stores install — scaffolding with `npx @spree/cli plugin new`, file routes and route collisions, peerDependencies against `@spree/dashboard-core`/`-ui`, prebuilt vs source publishing, `sideEffects`, the `spree.dashboard.plugin` package.json marker, auto-discovery via `virtual:spree-dashboard-plugins` vs an explicit whitelist, Tailwind class scanning, `definePlugin(config)` factories, Changesets, and the backend gem half. Common phrasings include "publish a dashboard plugin", "npm package for the Spree admin", "spree plugin new", "share admin screens across stores", "plugin not showing up", "Dashboard route collision", "plugin styles missing", "marketplace extension with admin UI".
Use when working with how Spree 6 gets goods to the customer — fulfillments (`ful_`), delivery methods, delivery zones, delivery profiles and origin groups, delivery rates, calculators and carrier rate providers (EasyPost, freight), order routing and stock splitters, partial fulfillment and splitting, shipping labels, tracking/deliveries, carrier tracking webhooks, pickup and digital delivery. Common phrasings include "shipping method", "no delivery rates at checkout", "ship from the nearest warehouse", "custom shipping calculator", "live carrier rates", "mark as shipped", "partial shipment", "tracking number", "carrier webhook", "click and collect", "3PL / WMS integration", "fulfillment stuck unfulfilled", "add a fulfillment status", "fulfillment.fulfilled event", "Spree::Shipment". Returns/exchanges/claims live in spree-returns; stock counts, reservations and transfers in spree-inventory.
Use when working with stock in Spree 6 — StockLevel counters (count_on_hand, allocated_count, reserved_count, incoming_count, available/purchasable), stock locations (kind, pickup_enabled, returns_enabled), stock movements and their kinds, checkout stock reservations and their expiry job, backorders, inventory tracking on/off, bulk stock sync from an ERP/WMS (bulk_upsert), stock transfers, suppliers, purchase orders and stock receipts, the spree:stock:recount_levels task, and stock_level events. Common phrasings include "stock count is wrong", "oversold", "sync inventory from ERP", "update stock via API", "reserve stock at checkout", "stock reservation expired", "backorder", "restock", "move stock between warehouses", "purchase order", "receive a delivery", "incoming stock", "StockItem", "count_on_hand", "out of stock".
Use when the user is working with money on a Spree 6 cart or order — how `total` is built, the typed money rows (`Spree::TaxLine`, `Spree::Discount`, `Spree::Fee`), totals columns (`item_total`, `discount_total`, `delivery_total`, `fee_total`, `included_tax_total` vs `additional_tax_total`, `adjustment_total`, `amount_due`), `Spree::Carts::RecalculateTotals`, custom adjusters (`Spree.adjusters`), fees and customs duties, manual discounts and fees on placed orders, or rendering an order summary. Common phrasings include "order total is wrong", "totals don't add up", "tax counted twice", "add a surcharge / handling fee / gift wrap fee", "add a custom fee", "where are adjustments", "Spree::Adjustment missing", "recalculate order totals", "edit a placed order's discount", "why did my discount disappear", "display_total", "money as string", "duties".
Use when the user wants to run custom code inside a Spree 6 business flow—for example, vetoing an add-to-cart, blocking checkout completion, enforcing a purchase limit or B2B rule, adding data to tax or promotion calculations, reacting inside the order-placement transaction, customizing return eligibility, or writing a new multi-step operation with compensation and gateway calls. Common phrasings include "Spree.hooks.register", "workflow hook", "carts.add_item.validate", "carts.complete.before_finalize", "set_tax_line_context", "reject!", "Spree::Workflow", "step / external_step / on_flow_failure", "run_hooks", "halt!", "has_status", "add_status", "state machine replacement", "where do I put business logic", "step.spree_workflow", and "trace a workflow". Covers services vs. workflows, the three hook kinds, the hook catalog, writing your own workflow, statuses, instrumentation, and testing. Reach for this before swapping a class via Spree.dependencies or decorating a model.
Implements the Syncfusion WPF DateTimeEdit (DateTimePicker) control for date and time selection with dropdown calendar/clock support. Use this when adding datetime pickers, masked datetime input, or datetime selection controls in WPF applications. Covers DateTime binding, mask/free-form editing, pattern formatting, CultureInfo localization, dropdown views, date range restrictions, blackout dates, null value handling, watermarks, and theming with SfSkinManager.
Complete guide for implementing Syncfusion WPF Diagram (SfDiagram) in Windows Presentation Foundation applications. Use this when working with diagrams like flowcharts, org charts, BPMN, or UML in WPF. Covers creating diagrams, adding nodes and connectors, configuring automatic layouts, implementing BPMN and UML shapes, setting up symbol palettes, data binding, export functionality, and appearance customization.
Implement Syncfusion WPF Kanban (SfKanban) control for workflow visualization and task management. Use this when building agile project tracking interfaces, workflow boards, or task management systems. This skill covers card configuration, card selection with multi-card drag-and-drop, column management and reordering, swim lanes, WIP limits, drag-and-drop functionality, workflows, sorting, and event handling.
Implements Syncfusion WPF Multi Column Dropdown (SfMultiColumnDropDownControl) for displaying searchable dropdown lists with grid view. Use this when creating dropdowns with multiple columns, autocomplete functionality, or filterable data grids in combo boxes. Supports data binding, column configuration, multi-row selection, and popup customization.
Use this skill when implementing Syncfusion WPF PercentTextBox controls for percentage input handling. Provides comprehensive guidance on value binding, min/max validation, number formatting with culture support, appearance customization with positive/negative/zero foregrounds, interactive features like scroll intervals and range adorners, watermark text, and data binding patterns for percentage-based input controls with international format support.
Comprehensive guide for implementing Syncfusion WPF Radial Gauge (SfCircularGauge) component for data visualization in Windows Presentation Foundation applications. Use this when working with circular gauges, speedometers, KPI displays, or progress meters. This skill covers gauge configuration with needles and pointers, scale customization, ranges and zones, interactive pointer dragging, animations, and annotations for creating rich dashboard visualizations.
Implement Syncfusion WPF Scheduler (SfScheduler) for managing appointments and calendar views in desktop applications. Use this when building scheduling interfaces, appointment management systems, or resource booking applications. This skill covers calendar views, appointment handling, resource scheduling, timeline customization, and Outlook-style calendar functionality.
Implement Syncfusion WPF TabNavigationControl for animated content switching with slide, fade, zoom, and blur transitions. Use this when building tab navigation with transition effects, ad-rotator style content displays, or animated item switching in WPF. Covers all seven TransitionEffect values, ItemsSource data binding, and appearance customization (HeaderVisibility, NavigationButtonVisibility, TabStripVisibility).
Implement Syncfusion WPF TabSplitter for VS 2008-style split tab views with top and bottom panel sections. Use this when building split tab layouts, dual-pane views, or side-by-side tabbed views in WPF. Covers SplitterPage, TopPanelItems, BottomPanelItems, TabSplitterItem, and collapsible split panel configuration.
Implement Syncfusion WPF TaskBar for Windows Explorer-style grouped task panels with collapsible TaskBarItem sections. Use this when building grouped collapsible panels, Windows XP-style sidebars, or expandable action panel sections in WPF. Covers TaskBarItem, GroupMargin, GroupPadding, GroupWidth, GroupOrientation, IsOpened, ButtonSize, and animation speed configuration.
Implement Syncfusion WPF TreeMap (SfTreeMap) control for hierarchical data visualization using nested rectangles. Use this when visualizing large datasets with hierarchical structure, creating heat maps, or displaying proportional data. This skill covers TreeMap configuration, layout algorithms, color mapping, data binding, and interactive features for stock analysis, data categorization, and hierarchical visualization scenarios.
Use when creating Three.js scenes, adding objects, managing parent-child hierarchies, or organizing 3D content. Prevents the common mistake of using add() instead of attach() for reparenting, forgetting matrixAutoUpdate, or missing dispose() calls. Covers Object3D, Scene, Group, Mesh, Layers, Fog, traversal, coordinate conversion. Keywords: scene graph, Object3D, add, remove, traverse, layers, fog, parent, children, visibility, Three.js scene setup, group objects, show hide object, organize scene.
Use when enabling shadows in a Three.js scene or debugging shadow artifacts like acne, peter panning, or low resolution. Prevents the common mistake of wrong shadow camera frustum, too many PointLight shadows, or missing castShadow/receiveShadow flags. Covers shadow map types, per-light config, bias tuning, CameraHelper debugging. Keywords: shadows, shadowMap, shadow acne, peter panning, bias, normalBias, castShadow, receiveShadow, PCFSoftShadowMap, shadow camera, shadows not showing, shadow artifacts, enable shadows.
Integrate Tranzila payment processing into Israeli applications -- covers iframe payments, tokenization, installments (tashlumim), refunds, 3D Secure, and Bit wallet. Use when user asks to accept payments via Tranzila, integrate Israeli credit card processing, set up "slikat ashrai", handle tashlumim (installment payments), create payment tokens, process refunds through Tranzila, or mentions "Tranzila", "tranzila API", "secure5", or Israeli online payments. Supports both legacy CGI endpoints and modern API V2. Do NOT use for Cardcom integration (use cardcom-payment-gateway), general accounting, or non-payment financial queries
Twilio Conversation Intelligence development guide. Use when building real-time or post-call conversation analysis, language operator pipelines, sentiment analysis, agent assist, cross-channel analytics, or querying aggregated conversation insights (sentiment trends, escalation rates, dashboards).
This skill provides expert-level guidance for VS Code extension development. Use when implementing new extension features, debugging extension code, designing WebView UIs, implementing Language Server Protocol features, or optimizing extension performance. Covers activation events, contribution points, VS Code API patterns, security best practices, testing strategies, and publishing workflows.
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.