Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
In an external XGENT.ai Portal app's own repo, generate its companion CLAUDE.md / PRODUCT.md / DESIGN.md (with AGENTS.md written as a mirror) — read app.manifest.json and code facts, ask once about anything missing, fill in three ready-to-use documents from templates, leave no placeholders, and never overwrite existing files. Use when the task is "initialize/onboard a new external app repo", "add CLAUDE.md / AGENTS.md / PRODUCT.md / DESIGN.md to this app repo", "add a design document that impeccable can read", or when the user has just received an empty app repo or one with only code and no specs; apps inside the portal monorepo and non-XGENT projects do not use this skill. Use in an external XGENT portal app's own repo to scaffold its CLAUDE.md / PRODUCT.md / DESIGN.md (AGENTS.md is written as a mirror of CLAUDE.md) from the app manifest and repo facts — one round of questions, no leftover placeholders, never overwrites existing files.
Expert in building 3D experiences for the web using Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and adding depth to web experiences. Use for: 3D websites, three.js, WebGL, react three fiber, and 3D experiences
Accessibility as part of building, not a pass afterwards. Semantic HTML first, keyboard order and focus management, visible focus, names for every control, ARIA only where HTML cannot, live regions, reduced motion, contrast, hit sizes, forms with linked labels and errors, headings and landmarks, inert layers, zoom to 200%, and how to test with a screen reader in five minutes. Use when building any interactive UI, when asked to make something accessible, or when a review needs an accessibility pass.
Integrate the Temps Node.js SDKs for server-side platform access, KV storage, and Blob storage. Use when the user wants to: (1) Call the Temps platform API from Node.js (deployments, projects, analytics, session replay, etc.), (2) Use Temps KV (key-value) storage, (3) Use Temps Blob storage for files, (4) Server-side integration with a Temps project, (5) Backend access to Temps resources. Triggers: "temps node sdk", "temps kv", "temps blob", "backend integration", "node.js temps", "@temps-sdk/node-sdk".
Use ado-axi to work with Azure DevOps — work items, pull requests, pipelines, repositories, and raw REST calls — through token-efficient TOON output. Use when the task involves Azure DevOps, ADO, boards, work items, WIQL, pull requests, code reviews, build pipelines, or Azure Repos.
Use when the user asks to generate, create, or scaffold ADVPL/TLPP code for TOTVS Protheus -- User Functions, Static Functions, TLPP classes, MVC (Model/View/Controller), REST APIs, SOAP web services, entry points (pontos de entrada), TReport/FWMsPrinter reports, jobs, or workflows. Also triggers on Portuguese phrasing like "gerar codigo", "criar rotina", "criar fonte", "novo ponto de entrada", "criar classe tlpp", "gerar api rest", "criar mvc", or routine name patterns like FATA001/MATA010. Covers naming conventions, Hungarian notation, namespace rules, identifier length limits, and mandatory User Function/error-handling structure.
Compile an agent-optimized changelog by cross-referencing git history with plans and documentation. Use when asked to "update changelog", "compile history", "document project evolution", or proactively after major milestones, architectural changes, or when stale/deprecated information is detected that could confuse coding agents.
Wraps existing Python agent as Agent Stack service using agentstack-sdk with minimal compatibility changes and no business-logic rewrites. Use when migrating, wrapping, or deploying an existing plain Python or framework-based agent to Agent Stack; not for non-Python runtimes or building new agent from scratch.
Structure AI and ML product decisions with the rigour of any product decision. Use when building AI-powered features, evaluating LLM integrations, designing AI products, or assessing AI readiness. Produces a complete AI product canvas covering problem definition, model approach, data requirements, evaluation framework, UX design, responsible AI checklist, and launch monitoring plan.
Use when reasoning about how Apple delivers and serves its experiences — the observable web delivery/infra (multi-CDN, mzstatic image-transform URLs, image formats, HLS adaptive video, caching, HTTP/2-3) and the reverse-engineered, INFERRED server-side architecture (CloudKit, APNs, StoreKit, Sign in with Apple, Private Cloud Compute, iCloud sync). Part of the apple-design family. Keywords: apple cdn, akamai, mzstatic, image transform url, srcset picture, HLS m3u8, http3 quic, cache-control immutable, content-hash fingerprint, frame-sequence delivery, createImageBitmap, KTX texture, video scrub, cloudkit, APNs push, StoreKit, sign in with apple, private cloud compute, icloud sync, conflict resolution, backend, infrastructure, reverse-engineered, inferred architecture.
Implement right-to-left (RTL) layouts for Arabic web and mobile applications. Use when user asks about RTL layout, Arabic text direction, bidirectional (bidi) text, Arabic CSS, "right to left", or needs to build Arabic UI. Covers CSS logical properties, Tailwind RTL, React/Next.js RTL setup, Arabic typography, and font selection. Do NOT use for Arabic RTL (similar but different typography) unless user explicitly asks for shared RTL patterns.
Use when managing GitCode repositories with the oh-gc CLI — including authentication, issues, PRs, reviewers, testers, labels, releases, and repository configuration. Use this skill when the user wants to commit code, create an ISSUE, create a PR, update a PR, or perform other GitCode web operations.
Use when authenticating or authorizing requests to any Mailtrap API (Email Send, Email Testing/Sandbox, Templates, Contacts, Sending Domains, Suppressions). Use when picking the auth header, choosing token scope, storing tokens safely, or resolving the Mailtrap account_id. Use before writing or generating any Mailtrap API call.
Design backup, restore, sync, export, recovery, data durability, cloud/local storage, versioning, migration, deletion, and disaster recovery systems. Use when building or reviewing backup strategy for SaaS, mobile apps, desktop utilities, games, user-generated content, account data, or business-critical workflows.
Build stunning glassmorphism dark-mode interfaces with Next.js and Tailwind CSS v4. Use when creating any frontend UI, component, page, or application. Specializes in glass-like translucent surfaces, luminous color palettes on dark backgrounds, fluid animations with Framer Motion, and premium visual polish. Always generates dark-mode-first, glassmorphic, production-grade code with exceptional aesthetic quality.
Explains how to use Salesforce BLIP-2 (Q-Former bridging a frozen image encoder and an LLM such as OPT or FlanT5) through HuggingFace Transformers and LAVIS for image captioning, visual question answering, image-text matching, and feature extraction. Use when generating captions for images, building a VQA system, doing zero-shot image-text understanding without task-specific training, matching or retrieving images against text, or fitting a BLIP-2 model into limited GPU memory with INT8/INT4 quantization. Prefer LLaVA or InstructBLIP for instruction-following multimodal chat, and CLIP for plain image-text similarity.
Integration guide for the Bloque SDK — a TypeScript SDK for programmable financial accounts, cards with spending controls, and multi-asset transfers. Use when the user asks to "integrate Bloque", "create a card", "set up spending controls", "handle card webhooks", "transfer funds", "create pockets", "set up MCC routing", "share balances between any mediums", "same balance across pockets/cards/Polygon/bank", "set up cashback", "auto-save on purchases", "round-up savings", "cashback programs", or build any fintech feature on the Bloque platform.
Write and review changelogs, release notes, app-store update notes, launch notes, migration notes, breaking-change notices, and customer-facing product update communication for SaaS, apps, games, developer tools, desktop software, and marketplaces. Use when a release needs clear user value, risk communication, upgrade guidance, or support-aware wording.
Convert a git log, commit list, or release notes into a polished, user-facing changelog. Use when writing release notes, generating a CHANGELOG.md entry, or documenting what changed in a version. Produces a structured changelog section with version header, categorised changes, and migration notes. For an already-curated change list use changelog-writer instead.
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
Before implementing a feature, hear out the requirement, then research existing libraries / tools / local packages (monorepo components) that already solve it. Use when scoping a new feature, evaluating build-vs-reuse, or asked to find existing solutions before writing code.
Chrome Extensions (Manifest V3) performance optimization guidelines (formerly chrome-extensions). This skill should be used when writing, reviewing, or refactoring Chrome extension code to ensure optimal performance patterns. Triggers on tasks involving service workers, content scripts, message passing, storage APIs, or extension development.
Build async message queues with Cloudflare Queues for background processing. Use when: handling async tasks, batch processing, implementing retries, configuring dead letter queues, managing consumer concurrency, or troubleshooting queue timeout, batch retry, message loss, or throughput exceeded.
Frontend-focused code review skill for React/TypeScript/Tailwind projects. Analyzes code quality, security vulnerabilities (XSS, CSRF), performance issues, accessibility (WCAG), React best practices, hooks usage, component architecture, responsive design, and SEO. Use when users request code review, want feedback on components, ask about frontend security, performance optimization, or accessibility compliance. Provides actionable feedback with severity levels and fix suggestions.
Implement a framework-agnostic version badge component with a tooltip showing build info (version, commit, branch, timestamp) and recent changelog entries. Use when the user wants to add a version display to their app header or footer, surface build information in the UI, expose recent changelog entries as a tooltip, or when they mention "version badge", "build info display", or "commit SHA in UI". Supports Next.js, Nuxt, SvelteKit, Vite+React, and plain React/Vue/Svelte.
Check and configure Justfile with standard recipes for project standards. Use when setting up a new Justfile for a project, auditing an existing Justfile for missing standard recipes, migrating from Makefile to Justfile, or ensuring Justfile follows team conventions (groups, comments, settings). Natural triggers: "set up justfile", "migrate makefile to justfile", "add just recipes".
How team-level patterns flow up into Bitwarden's Technical Strategy Ideas backlog and back down through BW Initiatives into team epics and stories. Covers recognizing which team-level patterns belong in the TSI backlog, framing an idea well enough for Architecture to evaluate it, the ARCH idea ↔ BW Initiative linkage, and defining epic-level and story-level work downward from an initiative. Use when noticing a cross-team pattern of pain that exceeds one team's scope, when surfacing ideas to the architecture group, when understanding how an initiative connects back to its originating idea, or when breaking epic-level work out of an initiative onto a team.
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.