Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Windows and Git Bash compatibility for ADF tooling. PROACTIVELY activate for: (1) MSYS_NO_PATHCONV usage with ADF CLI tools, (2) Git Bash path conversion when running ADF npm builds, (3) PowerShell scripts called from Git Bash for ADF, (4) Azure CLI from Git Bash on Windows for ADF deployments, (5) ARM template export issues on Windows, (6) ADF utilities npm package on Windows, (7) line-ending issues in JSON pipeline definitions. Provides: MSYS environment-variable recipes, npm-on-Windows fixes, PowerShell-from-bash patterns, and Azure CLI authentication on Git Bash.
Write Streamlit app source code that runs well in a PostHog sandbox — the posthog_apps.query() bridge for reading PostHog data, the packages baked into the sandbox image, caching and session state across Streamlit reruns, layout and chart patterns, and the app.py entry point with any helper modules and data files bundled beside it. Use when authoring or debugging the Python source of a PostHog Streamlit app, when a query inside an app fails, or when asked to "write a streamlit app that shows PostHog data".
Use when testing, running, or deploying Ultralytics YOLO inference in Platform or code on images, video, webcams, or streams — Platform Predict and dedicated endpoints, model.predict()/yolo predict, Results API boxes/masks/keypoints, persistent tracking, annotated video, and Solutions such as counting, heatmaps, speed, queues, and parking. For optimized runtime exports, see yolo-export.
Use when Java implementation work should be guided by Test-Driven Development, including maintaining a test list, choosing the next behavior, writing a failing test first, implementing only enough production code to pass, and refactoring while keeping tests green. This should trigger for requests such as Apply TDD; Use test-driven development; Drive this Java change with tests; Write the failing test first; Red-green-refactor this feature. Part of Plinth Toolkit
Lightweight standalone design spec for AI coding agents: codebase scan → bounded clarify pass (3–5 questions, not a grill) → reviewed design doc written to docs/plans/ → independent scored review → stop. No task board, no build. Use when you want a spec to discuss, hand off, or review before committing to implementation. Chains into absolute-work when ready to build. Triggers on "absolute spec", "write a spec", "spec out this feature", "draft a design doc", "I want a spec to hand off / review, don't build it yet".
Algorithmic complexity (Big-O) review — finding nested loops, N+1 queries, exponential recursion, quadratic string builds, and other accidental complexity blowups. Covers Python, JavaScript/TypeScript, Java, Go, and similar languages. Use whenever writing, reviewing, or refactoring code where Big-O matters. Trigger even when the user doesn't mention "Big-O" explicitly — if they're reviewing code for performance, refactoring a hot path, asking "why is this slow," or working with data that scales (loops, recursions, collections, ORM access), apply this skill to classify the time/space complexity and suggest the fix. Especially trigger on tasks like "review for performance," "find slow code," "make this faster," "this code is O(n²)," or when reading code that processes collections.
Review architecture across 7 dimensions (structural, scalability, enterprise readiness, performance, security, ops, data) and provide scored reports. Triggers on: “review architecture,” “critique design,” “audit system,” “assess scalability,” “enterprise readiness,” or “technical due diligence.” Not for diagrams; use architecture-diagram. Not for interactively finding shallow modules or designing one module's interface and seam; use module-deepening.
Plans and builds Drupal Canvas navigation UI (main nav, footer links, sidebar nav, mobile drawers, breadcrumbs) using design decomposition for structure and props/slots, then JSON:API menu or page-context patterns from canvas-data-fetching. Use when the user asks for navigation, header or footer links, menus, menu_items, mobile nav, or breadcrumb trails. Run after canvas-design-decomposition for layout and API sketches; follow canvas-data-fetching for SWR, useJsonApiClient, sortMenu, and menu fallbacks.
Multi-agent investigation for stubborn bugs. Use when: going in circles debugging, need to investigate browser/API interactions, complex bugs resisting normal debugging, or when symptoms don't match expectations. Launches parallel agents with different perspectives and uses Chrome tools for evidence gathering
Build a new service, app, API, agent, bot, script, or tool on this ryra machine. Use this WHENEVER the user wants to develop, build, scaffold, make, create, or start a new project here -- it sets up the ryra service layout (service.toml / test.toml) so the thing can be added, run, and upgraded as a managed service
You are a debugging expert specializing in setting up comprehensive debugging environments, distributed tracing, and diagnostic tools. Configure debugging workflows, implement tracing solutions, and establish troubleshooting practices for development and production environments.
Use when bootstrapping docs or when a task may change public behavior, APIs, CLI commands, configuration, environment variables, schemas, setup, deployment, operations, architecture, release notes, durable project decisions, README, reference docs, changelog, ADRs, playbooks, or agent guidance
Create distinctive, production-grade frontend interfaces with high design quality. Use when building web components, pages, or applications. Includes framework-specific guidance for Tailwind, React, Vue, and Rails/Hotwire ecosystems.
Git 2.49+ features and modern Git workflows (2025-2026). PROACTIVELY activate for: (1) Git 2.49+ features (reftables, sparse-checkout, partial clone, worktrees), (2) git-backfill for partial clones, (3) reftables migration (file backend to reftable backend), (4) sparse-checkout for monorepos, (5) git worktrees for parallel development, (6) partial clone (--filter=blob:none), (7) commit graph and bitmap optimizations, (8) trunk-based development workflows, (9) Git LFS, (10) modern alternatives to legacy commands. Provides: feature reference, version-detection snippets, sparse-checkout configuration, worktree workflow patterns, and migration guidance from older Git versions.
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"
Manages seamless Magento 2 version upgrades and migrations. Use when upgrading Magento versions, migrating from Magento 1, planning upgrade strategies, assessing compatibility, or handling breaking changes. Masters upgrade planning, compatibility assessment, and post-upgrade optimization.
Modern DevOps and CI/CD bash automation patterns with containers and cloud (2025). PROACTIVELY activate for: (1) writing CI/CD scripts (GitHub Actions, GitLab CI, Azure DevOps), (2) container-aware shell scripting (detecting containers, Kubernetes pods), (3) cloud provider helpers (AWS CLI, Azure CLI, gcloud), (4) blue-green and canary deployments via bash, (5) writing idempotent rollback scripts, (6) integrating with Docker/Compose from bash, (7) cross-environment variable management, (8) build matrix orchestration. Provides: copy-pasteable CI snippets, container detection helpers, cloud CLI wrappers, deployment orchestration patterns, and idempotent rollback templates
Motoko language pitfalls, modern syntax, and architecture patterns for the Internet Computer. Covers persistent actors, stable types, mo:core standard library, dot notation, mixins, and common compilation errors. Use when writing Motoko canister code, fixing Motoko compiler errors, or generating Motoko actors. Do NOT use for deployment, icp.yaml, or CLI commands
Write Node.js and Bun backend code the way THIS project already does it, not by generic defaults — a TypeScript-first reference that detects the runtime and carries the real conventions for HTTP servers, Zod boundary validation, typed error handling, pino logging, database access, auth, BullMQ queues, caching, async and graceful-shutdown patterns, security, CLI tooling, testing, and observability, so a change lands idiomatic and review-ready instead of merely running. Use when a task touches this project's Node.js or Bun backend and should follow its conventions rather than generic defaults
Analyzes Remotion compositions for performance issues and provides optimization recommendations. Identifies expensive computations, unnecessary re-renders, large assets, memoization opportunities, and architecture improvements. Use when optimizing render times or when asked to “improve performance,” “speed up renders,” or “optimize Remotion video.”
Scaffolds Remotion project folder structure, base configuration files, and file organization. Focuses only on directory creation, empty file templates, and Remotion configuration. Use when starting a new video project or when asked to “scaffold Remotion project,” “create project structure,” or “setup Remotion folders.”
Stands up one navigable feature the same way every time — a fixed lib/features/<feature>/presentation/ folder (dumb View + one 1:1 Notifier/AsyncNotifier ViewModel + widgets/ + scoped <feature>_providers.dart), downward-only dependencies with no cross-feature imports, reactive reads as scoped StreamProviders over a repository .watch(), every mutation through one repository single-write-path method, typed Result/Failure surfaced as AsyncValue, a typed go_router route carrying identity in path params, ARB parity across locales, family+autoDispose keying, and EdgeInsetsDirectional-only geometry. Use when adding a screen, tab, or feature folder; wiring a feature Notifier/ViewModel or a scoped stream provider; registering a route; adding ARB keys for a new screen; splitting an over-grown feature; or adding a persisted record its View reads.
Helps choose secure, healthy open-source packages by evaluating vulnerability status, maintenance health, popularity, community, and security posture. Use this skill when: - Agent needs to import a new dependency - User asks "which package should I use for X?" - User wants to compare packages (A vs B) - User asks "is this package safe?" - User asks for a "secure alternative" to a package - User mentions "dependency health", "package chooser", or "package security"
Advanced bash string manipulation including parameter expansion, pattern matching, regex, and text processing (2025). PROACTIVELY activate for: (1) parameter expansion (prefix/suffix removal, search/replace, substring), (2) regex matching with [[ =~ ]] and BASH_REMATCH, (3) case modification (uppercase/lowercase), (4) substring extraction without sed/awk, (5) splitting strings into arrays via IFS, (6) escaping for safe interpolation, (7) URL encoding and decoding in pure bash, (8) trimming whitespace, (9) avoiding subshell overhead in tight loops. Provides: parameter-expansion cheat sheet, regex patterns with BASH_REMATCH examples, case-conversion recipes, and IFS-based splitting/joining patterns
Implement the Syncfusion WPF HierarchyNavigator (Breadcrumb) control for hierarchical path navigation. Use this when building breadcrumb or address-bar UIs, binding hierarchical data to a navigation control, or enabling edit mode with AutoComplete path entry in WPF. Covers navigation history, refresh button, progress bar during navigation, and keyboard-driven hierarchical navigation.
Implement Syncfusion WPF Bullet Graph (SfBulletGraph) components for performance indicators and KPI visualization. Use this when displaying metrics against targets, creating dashboard gauges, or visualizing performance in qualitative ranges. This skill covers featured measures, comparative measures, qualitative ranges, goal tracking, and compact data visualization for dashboards.
Implements the Syncfusion WPF ChromelessWindow for custom window chrome and title bar customization. Use this when creating custom window designs, customizing title bars, or implementing borderless windows in WPF applications. Covers title bar customization, background styling, border radius, custom buttons, and native chrome integration.
Implements the Syncfusion WPF DomainUpDown (SfDomainUpDown) control for cycling through predefined item lists using spin buttons. Use this when adding domain selectors, item selectors with up/down buttons, or controls that navigate through collections using increment/decrement buttons in WPF applications. Covers item population, spin button alignment, styling, auto-reverse, and data binding with custom templates.
Implements the Syncfusion WPF DoubleTextBox control for numeric double-precision input with formatting and validation. Use this when adding numeric textboxes, configuring value ranges (MinValue, MaxValue), or customizing number formatting in WPF applications. Covers culture-specific formatting, scroll intervals, watermarks, null values, and range adorners.
Implements the Syncfusion WPF SfNavigationDrawer for slide-out navigation panels and sidebars. Use when building collapsible side panels, hierarchical navigation menus, or responsive drawer display modes (compact/expanded).
Implement Syncfusion WPF Syntax Editor (EditControl) for code editors and advanced text editing applications. Use this when building syntax-highlighted code editors, IDE-like editors, or source code editing interfaces in WPF. Covers syntax highlighting, IntelliSense, find/replace, programming language support, and Visual Studio-style editing features.
Comprehensive guide for implementing Syncfusion WPF TreeView (SfTreeView) control to display hierarchical data in Windows Presentation Foundation applications. Use this when working with tree structures, folder hierarchies, organizational charts, or parent-child data relationships. Supports drag-and-drop reordering, checkbox selection, load-on-demand for large datasets, and inline editing of tree nodes.
Enforces a pure-Dart value-object core that stores every quantity canonically — money as integer minor units keyed to each currency's real ISO-4217 exponent (never *100), physical amounts as SI whole units, timestamps as UTC — and converts only at the presentation edge; forbids double/num money, cross-currency arithmetic, and defaulting an unknown currency to two decimals; routes every division of money through one largest-remainder allocate() primitive so parts always sum to the whole to the exact minor unit; derives totals instead of storing them, links entities by stable id, and injects a Clock instead of DateTime.now. Use when defining or changing Money, Currency, or a unit value object; parsing or formatting an amount; splitting, prorating, discounting, tax/tip, or distributing money; adding a currency or FX rate; converting quantities; or fixing float-money, hardcoded-100, cross-currency, off-by-a-cent, or stored-total-drift bugs.
This skill should be used when the user asks "where should I put this", "can X import from Y", "Angular folder structure", mentions feature isolation, lazy loading placement, dependency violations, architecture audit, circular dependency, import cycle, barrel file, bundle size, initial load performance, signal store placement, state management, or when creating/moving Angular components, services, or modules between folders. Also use when reviewing PRs for architectural compliance, scaffolding new features, or setting up eslint-boundaries. Angular enterprise architecture advisor for placement decisions, dependency rules, isolation patterns, and architectural verification.
Periodic architecture survey — walks the module graph and reports ranked deepening candidates (shallow modules, hypothetical seams, logic behind the wrong seam). Survey, not rescue: it finds candidates and hands them to the captain; it never refactors on its own.
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.