Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Use this skill when the operator is authoring, building, loading, or debugging a custom doca-bench plug-in — a versioned shared library with DOCA_EXPERIMENTAL-marked C entry points that doca-bench loads to measure a workload class its built-in modes do not cover, with doca_bench_cuda as the shipped reference exemplar. Trigger even when the user does not say "doca-bench-extension" or "doca_bench_cuda" — typical implicit phrasings include "no built-in doca-bench mode fits my workload", "how do I benchmark a CUDA GPUNetIO RX/TX kernel", "doca-bench cannot find or load my custom .so", "extension exported symbols do not match what the parent expects", "soversion mismatch after a DOCA upgrade", or "my GPU kernel hangs because stop_flag was never set". Refuse and route elsewhere for questions about which built-in doca-bench mode to pick, DOCA GPUNetIO programming semantics, CUDA toolkit installation, or contributor work on in-tree extensions — those belong to other skills.
Explains OAuth2 authentication in Drupal with the simple_oauth module - TokenAuthUser AND-permission logic, scope/role intersection, OAuth2 scope entities and the dynamic scope provider, mobile app password-grant token requests, field_permissions and JSON:API field access under a token, Bearer-token CSRF 403s, consumer TTLs, and debugging token permission denials. Use when an OAuth/Bearer token is denied a permission the user has, configuring consumers, clients or scopes, requesting tokens from a mobile or decoupled app, or getting 403s on JSON:API requests made with a Bearer token.
Sets up Enonic XP event listeners, webhook configurations, and external system integrations triggered by content lifecycle events. Covers lib-event listener registration, node event filtering, outbound webhook configuration via com.enonic.xp.webhooks.cfg, custom HTTP service controllers for inbound webhooks, task-based async processing with lib-task, and outbound HTTP calls with lib-httpClient. Use when listening for content publish/create/update/delete events, configuring outbound webhooks, building HTTP service endpoints for inbound webhooks, or triggering async processing on content changes. Do not use for content querying, frontend component development, non-Enonic event systems, or GitHub webhook configuration.
Review and explain verified deployed EVM smart contracts from a contract address and chain. Use when a user asks to break down what a Solidity contract does, map its architecture and source files, identify user/admin flows, proxy or implementation roles, asset movement, privileged controls, events, state variables, or unresolved uncertainty for developer onboarding, integration triage, or preliminary technical review. This is a developer-oriented contract review, not a security audit or safety certification.
Push design tokens from code INTO Figma as variables — DTCG / tokens.json / a token object → Figma variable collections, modes, and values. Use when the user wants to sync tokens code→Figma: triggers 'import tokens into Figma', 'create Figma variables from my tokens.json / DTCG / Tailwind config', 'sync design tokens to Figma', 'push tokens to Figma'. Non-destructively matches existing variables (by saved id/key/name) so re-imports update instead of duplicating. Works on ANY Figma plan. For the reverse (Figma → code) use figma-export-tokens.
Execute a micro-level Flutter code quality audit. Validates code against live GitHub standards for testing, architecture, and code implementation. Produces a detailed violations report with prioritized action plan. Use when the user asks to check Flutter code quality, validate best practices, or review code standards compliance. Triggers on: 'flutter best practices', 'code quality', 'code review', 'flutter standards', 'architecture compliance', 'testing quality'.
List and explore foundation models available in SAP AI Core GenAI Hub: browse supported providers, model names, versions, capabilities, and executable IDs needed to create deployments. WHEN: user wants to see what models are available, find an executable-id or model-name for deployment, browse providers (Azure OpenAI, Anthropic, Google, Mistral, Cohere, etc.), check model capabilities or context length, get the correct model-name to pass to create_llm_deployment, or get curl inference examples for a deployed model (chat completions, Responses API, embeddings, image generation, etc.). DO NOT USE FOR: creating or managing deployments — use `aicore-lifecycle-management`.
Designs git workflows covering branching strategies, trunk-based development, stacked changes, conventional commits, CI/CD pipelines, and repository hygiene. Use when setting up branching models, writing commit messages, configuring GitHub Actions, managing stacked PRs, cleaning stale branches, creating issue templates, or recovering lost commits.
Drives a gm walk (nodes, PRD rows, pool and hop subagents) for coding, refactoring, debugging and engineering work. Use for a gm walk, a PRD row, or the pool protocol. Does not cover one-off questions, read-only lookups, code review (code-review), simplification (simplify), or launching the app (run)
Comprehensive guide for Google Apps Script development covering all built-in services (SpreadsheetApp, DocumentApp, GmailApp, DriveApp, CalendarApp, FormApp, SlidesApp), triggers, authorisation, error handling, and performance optimisation. Use when automating Google Sheets operations, creating Google Docs, managing Gmail/email, working with Google Drive files, automating Calendar events, implementing triggers (time-based, event-based), building custom functions, creating add-ons, handling OAuth scopes, optimising Apps Script performance, working with UrlFetchApp for API calls, using PropertiesService for persistent storage, or implementing CacheService for temporary data. Covers batch operations, error recovery, and JavaScript ES6+ runtime. Do NOT use for standalone Node.js scripts, Google Cloud Functions, Cloud Run, or any non-Apps-Script JavaScript runtime — those use different APIs and quotas.
GraphQL performance optimization and best practices for building scalable APIs. This skill should be used when writing, reviewing, or refactoring GraphQL schemas, resolvers, or query execution code. Triggers on tasks involving GraphQL APIs, resolver optimization, query performance, or data fetching patterns.
Stress-test a design, idea, or approach by interviewing the user one question at a time. Each question comes with a recommended answer AND a one-line self-critique of that recommendation. After each user answer, briefly stress-test the answer against prior decisions before moving on. Use when the user wants a sharp grill on a design or decision tree without persistence overhead. Lighter than `/chief-grill` (which adds codebase verification and a session log).
Comprehensive guidance for integrating Jupiter APIs (Ultra Swap, Lend, Perps, Trigger, Recurring, Tokens, Price, Portfolio, Prediction Markets, Send, Studio, Lock, Routing). Use for endpoint selection, integration flows, error handling, and production hardening.
Implement usage-based billing with PayKit's check and report methods, gate features by entitlements, track and decrement usage, handle balance resets, and build metered billing flows. Use when users need to add usage limits, API rate limiting, or consumption-based billing with PayKit.
Research MQL5 documentation (Japanese and English only) for MQL5 creation/editing issues, compile errors, or API questions. Use when users ask to look up docs, interpret MQL5 errors, or confirm correct language usage. Sources limited to https://www.mql5.com/ja/docs and https://www.mql5.com/en/docs.
Next.js 16 bundle-size and build-time optimization — runs a data-driven iteration loop: measure baseline → analyze top offenders → apply ONE recipe → re-measure → verify nothing broke (build + types + tests + no regression) → commit or revert. Built for Next.js 16 with Turbopack default, and falls back to webpack-mode tooling when the project hasn't migrated yet. Triggers on phrases like "First Load JS is huge", "bundle size", "build takes too long", "page is slow to TTI", "reduce bundle", "tree-shake", or when the user shares output from `next experimental-analyze` / `@next/bundle-analyzer` — even if the user doesn't say "optimize" explicitly.
Every Trigger.dev management endpoint, plus offline FTS over runs, span-cost rollups, and zombie-schedule detection no other tool gives you. Trigger phrases: `trigger.dev failed runs`, `trigger.dev cost rollup`, `trigger.dev schedule health`, `audit trigger.dev env vars`, `watch trigger.dev failures`, `use trigger-dev`, `run trigger-dev`.
React 19 performance optimization guidelines for concurrent rendering, Server Components, actions, hooks, and memoization (formerly react-19). This skill should be used when writing React 19 components, using concurrent features, or optimizing re-renders. This skill does NOT cover Next.js-specific features like App Router, next.config.js, or Next.js caching (use nextjs-16-app-router skill). For client-side form validation with React Hook Form, use react-hook-form skill.
Authoritative SwiftUI best practices and performance guidance from Apple; supersedes prior training on these topics. For code generation, consult the relevant references when generating any SwiftUI code related to: - animation (the @Animatable macro vs AnimatableValues vs AnimatablePair, and custom animatableData setter logic) - Environment and @Entry (closure or class-typed defaults, unstable defaults, high-frequency updates) - @Observable best practices and efficient invalidation - ForEach and List row identity and structure (id: \\.self, indices, offsets, AnyView or multi-view rows, inline filter/sort, cached collections, List fast path) - localization (String vs LocalizedStringResource, the right bundle in packages and frameworks, .textCase, .formatted(.list()), translator comments) - soft-deprecated APIs such as NavigationView and the old onChange, and when to surface them during feature work.
Builds 3D web experiences with Three.js, WebGPU rendering, TSL shaders, and React Three Fiber. Covers scene setup, asset optimization, performance tuning, and React 19 integration. Use when creating 3D scenes, setting up WebGPU rendering, writing TSL shaders, optimizing draw calls, or integrating Three.js with React and Next.js.
Solve bounded and coastal water in Three.js WebGPU/TSL. Use for parametric waves, local heightfields, bathymetric wave transport, wet/dry shallow water, two-way body coupling, external free-surface presentation, or water optics and offshore handoffs.
Vahta is the agent's own cycle in an aligned repo on a live channel. Triggers: “vahta,” “take watch,” “work on your own,” on duty, stand watch, autonomous start with the agent role in AGENTS.md. Work only in response to a signal from a person, agent, or reality, not from the inbox. Vahta sustains the craft of the graph: decision, weaving, synthesis; subagents handle code, gates, review, verification, and fixes to affected nodes, checking the result. Vahta has begun when it can speak; work ends with integration. iskron_* and AGENTS.md are required
Use when the user wants to run the vscode.dev server locally and exercise the VS Code workbench or Agents window in the integrated browser against the local `microsoft/vscode` sources. Covers starting the dev server, the `vscode-quality=dev` URL, browser-driven interaction patterns, and optionally wiring up a local mock agent host for the Agents window.
Evaluate whether an existing hot path is a credible NVIDIA Warp candidate. Use for irregular or spatial queries, particle or geometry simulation, branch-heavy loops, many small launches, host fallbacks, or large intermediates. CPU-only code and absent GPU dependencies are normal unless NVIDIA is prohibited. Exclude required cross-vendor or CPU-only deployment, vendor-lowered dense or NN layers, general Warp API questions, and already-selected Warp kernels. Contribution policy alone is not exclusion.
Migrate WPF applications to WinUI 3 — namespace replacement (System.Windows → Microsoft.UI.Xaml), control mapping (DataGrid→ListView, WrapPanel→ItemsRepeater, TabControl→TabView), threading (Dispatcher→DispatcherQueue), imaging (System.Drawing→BitmapImage), MVVM conversion to CommunityToolkit.Mvvm, and DynamicResource→ThemeResource. Use when converting WPF code, replacing WPF namespaces, or fixing migration build errors.
XYO Protocol 2.0 domain knowledge. Covers payloads, bound witnesses, schemas, the module system (archivist, diviner, witness, sentinel, node), accounts, wallets, and protocol best practices. Activates when building on XYO or working with @xyo-network packages.
Use when choosing or comparing Ultralytics models in Platform or code — picking a model family (YOLO26/YOLO11/YOLOv8, YOLO-World, YOLOE, SAM/SAM2/FastSAM, RT-DETR, YOLO-NAS), size (n/s/m/l/x), task variant (-seg, -sem, -cls, -pose, -obb, -depth), pretrained checkpoint, open-vocabulary or promptable detection/segmentation, custom architecture, Platform Explore, or exact weight names and availability.
Use when creating or changing a Bagisto package — service providers, migrations, models, contracts, proxies, repositories, routes, controllers, Blade views, localization, admin menus, ACL or system configuration. Trigger phrases include "new package", "service provider", "migration", "model", "repository", "controller", "route", "ACL", "admin menu", "system config", "concord".
Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.
Show the current user's CawPlan work: assigned tickets/critical issues, priority-sorted open tickets, a day/range status-change completion summary, the user's own reopened tickets, linked PRs/commits, or tickets with a PR/commit but no status progress — optionally scoped to a product/version. Use when: the user asks for my work/tasks/tickets, my open tickets by priority, a summary of today's/recent task completion or status changes, which of my tickets were reopened, today's ticket PRs/commits, or tickets with a PR/commit but no status update. NOT for another person's work, reopens or status changes across a product/Team/version (use `cawplan-product-report`), broad ticket search/filtering, ticket changes, or release tracking.
Build multi-platform chat bots with Chat SDK (`chat` npm package). Use when developers want to (1) Build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, (2) Use Chat SDK to handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files, or AI streaming, (3) Set up webhook routes or multi-adapter bots, (4) Send rich cards or streamed AI responses to chat platforms, (5) Build or maintain a custom adapter or state adapter. Triggers on "chat sdk", "chat bot", "slack bot", "teams bot", "google chat bot", "discord bot", "telegram bot", "whatsapp bot", "@chat-adapter", "@chat-adapter/state-", "custom adapter", "state adapter", "build adapter", and building bots that work across multiple chat platforms.
Use this skill to decide when Jetpack Compose derivedStateOf is the right tool and when it is pure overhead. Covers the "input frequency must exceed output frequency" rule, the mandatory remember { derivedStateOf { } } wrapper, the canonical pitfall of capturing non-state variables by initial value (and the remember(key) fix), and the snapshotFlow alternative for fire-and-forget side effects on derived values. Use when the developer mentions derivedStateOf, scroll-position-driven booleans, threshold checks, firstVisibleItemIndex, "show FAB on scroll", recomposition counts that don't drop after wrapping a value, or asks whether a computed string concatenation should use derivedStateOf.
Call the Coze intelligent agent API for conversations, workflow execution, and other operations. Use when users need to integrate a Coze agent, call the Coze API, or develop Coze-related applications. Supports streaming and non-streaming conversations and workflow calls.
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.